summaryrefslogtreecommitdiffstats
path: root/ml/dlib/python_examples
diff options
context:
space:
mode:
Diffstat (limited to 'ml/dlib/python_examples')
-rw-r--r--ml/dlib/python_examples/LICENSE_FOR_EXAMPLE_PROGRAMS.txt20
-rwxr-xr-xml/dlib/python_examples/cnn_face_detector.py85
-rwxr-xr-xml/dlib/python_examples/correlation_tracker.py72
-rwxr-xr-xml/dlib/python_examples/face_alignment.py91
-rwxr-xr-xml/dlib/python_examples/face_clustering.py127
-rwxr-xr-xml/dlib/python_examples/face_detector.py84
-rwxr-xr-xml/dlib/python_examples/face_jitter.py97
-rwxr-xr-xml/dlib/python_examples/face_landmark_detection.py100
-rwxr-xr-xml/dlib/python_examples/face_recognition.py123
-rwxr-xr-xml/dlib/python_examples/find_candidate_object_locations.py54
-rwxr-xr-xml/dlib/python_examples/global_optimization.py47
-rwxr-xr-xml/dlib/python_examples/max_cost_assignment.py57
-rw-r--r--ml/dlib/python_examples/requirements.txt3
-rwxr-xr-xml/dlib/python_examples/sequence_segmenter.py197
-rwxr-xr-xml/dlib/python_examples/svm_binary_classifier.py68
-rwxr-xr-xml/dlib/python_examples/svm_rank.py155
-rwxr-xr-xml/dlib/python_examples/svm_struct.py343
-rwxr-xr-xml/dlib/python_examples/train_object_detector.py183
-rwxr-xr-xml/dlib/python_examples/train_shape_predictor.py135
19 files changed, 2041 insertions, 0 deletions
diff --git a/ml/dlib/python_examples/LICENSE_FOR_EXAMPLE_PROGRAMS.txt b/ml/dlib/python_examples/LICENSE_FOR_EXAMPLE_PROGRAMS.txt
new file mode 100644
index 00000000..2bdbd569
--- /dev/null
+++ b/ml/dlib/python_examples/LICENSE_FOR_EXAMPLE_PROGRAMS.txt
@@ -0,0 +1,20 @@
+The intent of the example programs supplied with the dlib C++ library is
+to both instruct users and to also provide a simple body of code they
+may copy and paste from. To make this as painless as possible all the
+example programs have been placed into the public domain.
+
+
+This work is hereby released into the Public Domain.
+To view a copy of the public domain dedication, visit
+http://creativecommons.org/licenses/publicdomain/ or send a
+letter to
+ Creative Commons
+ 171 Second Street
+ Suite 300,
+ San Francisco, California, 94105, USA.
+
+
+Public domain dedications are not recognized by some countries. So
+if you live in an area where the above dedication isn't valid then
+you can consider the example programs to be licensed under the Boost
+Software License.
diff --git a/ml/dlib/python_examples/cnn_face_detector.py b/ml/dlib/python_examples/cnn_face_detector.py
new file mode 100755
index 00000000..75357a62
--- /dev/null
+++ b/ml/dlib/python_examples/cnn_face_detector.py
@@ -0,0 +1,85 @@
+#!/usr/bin/python
+# The contents of this file are in the public domain. See LICENSE_FOR_EXAMPLE_PROGRAMS.txt
+#
+# This example shows how to run a CNN based face detector using dlib. The
+# example loads a pretrained model and uses it to find faces in images. The
+# CNN model is much more accurate than the HOG based model shown in the
+# face_detector.py example, but takes much more computational power to
+# run, and is meant to be executed on a GPU to attain reasonable speed.
+#
+# You can download the pre-trained model from:
+# http://dlib.net/files/mmod_human_face_detector.dat.bz2
+#
+# The examples/faces folder contains some jpg images of people. You can run
+# this program on them and see the detections by executing the
+# following command:
+# ./cnn_face_detector.py mmod_human_face_detector.dat ../examples/faces/*.jpg
+#
+#
+# COMPILING/INSTALLING THE DLIB PYTHON INTERFACE
+# You can install dlib using the command:
+# pip install dlib
+#
+# Alternatively, if you want to compile dlib yourself then go into the dlib
+# root folder and run:
+# python setup.py install
+# or
+# python setup.py install --yes USE_AVX_INSTRUCTIONS --yes DLIB_USE_CUDA
+# if you have a CPU that supports AVX instructions, you have an Nvidia GPU
+# and you have CUDA installed since this makes things run *much* faster.
+#
+# Compiling dlib should work on any operating system so long as you have
+# CMake installed. On Ubuntu, this can be done easily by running the
+# command:
+# sudo apt-get install cmake
+#
+# Also note that this example requires scikit-image which can be installed
+# via the command:
+# pip install scikit-image
+# Or downloaded from http://scikit-image.org/download.html.
+
+import sys
+import dlib
+from skimage import io
+
+if len(sys.argv) < 3:
+ print(
+ "Call this program like this:\n"
+ " ./cnn_face_detector.py mmod_human_face_detector.dat ../examples/faces/*.jpg\n"
+ "You can get the mmod_human_face_detector.dat file from:\n"
+ " http://dlib.net/files/mmod_human_face_detector.dat.bz2")
+ exit()
+
+cnn_face_detector = dlib.cnn_face_detection_model_v1(sys.argv[1])
+win = dlib.image_window()
+
+for f in sys.argv[2:]:
+ print("Processing file: {}".format(f))
+ img = io.imread(f)
+ # The 1 in the second argument indicates that we should upsample the image
+ # 1 time. This will make everything bigger and allow us to detect more
+ # faces.
+ dets = cnn_face_detector(img, 1)
+ '''
+ This detector returns a mmod_rectangles object. This object contains a list of mmod_rectangle objects.
+ These objects can be accessed by simply iterating over the mmod_rectangles object
+ The mmod_rectangle object has two member variables, a dlib.rectangle object, and a confidence score.
+
+ It is also possible to pass a list of images to the detector.
+ - like this: dets = cnn_face_detector([image list], upsample_num, batch_size = 128)
+
+ In this case it will return a mmod_rectangless object.
+ This object behaves just like a list of lists and can be iterated over.
+ '''
+ print("Number of faces detected: {}".format(len(dets)))
+ for i, d in enumerate(dets):
+ print("Detection {}: Left: {} Top: {} Right: {} Bottom: {} Confidence: {}".format(
+ i, d.rect.left(), d.rect.top(), d.rect.right(), d.rect.bottom(), d.confidence))
+
+ rects = dlib.rectangles()
+ rects.extend([d.rect for d in dets])
+
+ win.clear_overlay()
+ win.set_image(img)
+ win.add_overlay(rects)
+ dlib.hit_enter_to_continue()
diff --git a/ml/dlib/python_examples/correlation_tracker.py b/ml/dlib/python_examples/correlation_tracker.py
new file mode 100755
index 00000000..4493a55b
--- /dev/null
+++ b/ml/dlib/python_examples/correlation_tracker.py
@@ -0,0 +1,72 @@
+#!/usr/bin/python
+# The contents of this file are in the public domain. See LICENSE_FOR_EXAMPLE_PROGRAMS.txt
+#
+# This example shows how to use the correlation_tracker from the dlib Python
+# library. This object lets you track the position of an object as it moves
+# from frame to frame in a video sequence. To use it, you give the
+# correlation_tracker the bounding box of the object you want to track in the
+# current video frame. Then it will identify the location of the object in
+# subsequent frames.
+#
+# In this particular example, we are going to run on the
+# video sequence that comes with dlib, which can be found in the
+# examples/video_frames folder. This video shows a juice box sitting on a table
+# and someone is waving the camera around. The task is to track the position of
+# the juice box as the camera moves around.
+#
+#
+# COMPILING/INSTALLING THE DLIB PYTHON INTERFACE
+# You can install dlib using the command:
+# pip install dlib
+#
+# Alternatively, if you want to compile dlib yourself then go into the dlib
+# root folder and run:
+# python setup.py install
+# or
+# python setup.py install --yes USE_AVX_INSTRUCTIONS
+# if you have a CPU that supports AVX instructions, since this makes some
+# things run faster.
+#
+# Compiling dlib should work on any operating system so long as you have
+# CMake installed. On Ubuntu, this can be done easily by running the
+# command:
+# sudo apt-get install cmake
+#
+# Also note that this example requires scikit-image which can be installed
+# via the command:
+# pip install scikit-image
+# Or downloaded from http://scikit-image.org/download.html.
+
+import os
+import glob
+
+import dlib
+from skimage import io
+
+# Path to the video frames
+video_folder = os.path.join("..", "examples", "video_frames")
+
+# Create the correlation tracker - the object needs to be initialized
+# before it can be used
+tracker = dlib.correlation_tracker()
+
+win = dlib.image_window()
+# We will track the frames as we load them off of disk
+for k, f in enumerate(sorted(glob.glob(os.path.join(video_folder, "*.jpg")))):
+ print("Processing Frame {}".format(k))
+ img = io.imread(f)
+
+ # We need to initialize the tracker on the first frame
+ if k == 0:
+ # Start a track on the juice box. If you look at the first frame you
+ # will see that the juice box is contained within the bounding
+ # box (74, 67, 112, 153).
+ tracker.start_track(img, dlib.rectangle(74, 67, 112, 153))
+ else:
+ # Else we just attempt to track from the previous frame
+ tracker.update(img)
+
+ win.clear_overlay()
+ win.set_image(img)
+ win.add_overlay(tracker.get_position())
+ dlib.hit_enter_to_continue()
diff --git a/ml/dlib/python_examples/face_alignment.py b/ml/dlib/python_examples/face_alignment.py
new file mode 100755
index 00000000..53df7a3e
--- /dev/null
+++ b/ml/dlib/python_examples/face_alignment.py
@@ -0,0 +1,91 @@
+#!/usr/bin/python
+# The contents of this file are in the public domain. See LICENSE_FOR_EXAMPLE_PROGRAMS.txt
+#
+# This example shows how to use dlib's face recognition tool for image alignment.
+#
+# COMPILING/INSTALLING THE DLIB PYTHON INTERFACE
+# You can install dlib using the command:
+# pip install dlib
+#
+# Alternatively, if you want to compile dlib yourself then go into the dlib
+# root folder and run:
+# python setup.py install
+# or
+# python setup.py install --yes USE_AVX_INSTRUCTIONS
+# if you have a CPU that supports AVX instructions, since this makes some
+# things run faster. This code will also use CUDA if you have CUDA and cuDNN
+# installed.
+#
+# Compiling dlib should work on any operating system so long as you have
+# CMake installed. On Ubuntu, this can be done easily by running the
+# command:
+# sudo apt-get install cmake
+#
+# Also note that this example requires OpenCV and Numpy which can be installed
+# via the command:
+# pip install opencv-python numpy
+# Or downloaded from http://opencv.org/releases.html
+
+import sys
+
+import dlib
+import cv2
+import numpy as np
+
+if len(sys.argv) != 3:
+ print(
+ "Call this program like this:\n"
+ " ./face_alignment.py shape_predictor_5_face_landmarks.dat ../examples/faces/bald_guys.jpg\n"
+ "You can download a trained facial shape predictor from:\n"
+ " http://dlib.net/files/shape_predictor_5_face_landmarks.dat.bz2\n")
+ exit()
+
+predictor_path = sys.argv[1]
+face_file_path = sys.argv[2]
+
+# Load all the models we need: a detector to find the faces, a shape predictor
+# to find face landmarks so we can precisely localize the face
+detector = dlib.get_frontal_face_detector()
+sp = dlib.shape_predictor(predictor_path)
+
+# Load the image using OpenCV
+bgr_img = cv2.imread(face_file_path)
+if bgr_img is None:
+ print("Sorry, we could not load '{}' as an image".format(face_file_path))
+ exit()
+
+# Convert to RGB since dlib uses RGB images
+img = cv2.cvtColor(bgr_img, cv2.COLOR_BGR2RGB)
+
+# Ask the detector to find the bounding boxes of each face. The 1 in the
+# second argument indicates that we should upsample the image 1 time. This
+# will make everything bigger and allow us to detect more faces.
+dets = detector(img, 1)
+
+num_faces = len(dets)
+if num_faces == 0:
+ print("Sorry, there were no faces found in '{}'".format(face_file_path))
+ exit()
+
+# Find the 5 face landmarks we need to do the alignment.
+faces = dlib.full_object_detections()
+for detection in dets:
+ faces.append(sp(img, detection))
+
+# Get the aligned face images
+# Optionally:
+# images = dlib.get_face_chips(img, faces, size=160, padding=0.25)
+images = dlib.get_face_chips(img, faces, size=320)
+for image in images:
+ cv_bgr_img = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
+ cv2.imshow('image',cv_bgr_img)
+ cv2.waitKey(0)
+
+# It is also possible to get a single chip
+image = dlib.get_face_chip(img, faces[0])
+cv_bgr_img = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
+cv2.imshow('image',cv_bgr_img)
+cv2.waitKey(0)
+
+cv2.destroyAllWindows()
+
diff --git a/ml/dlib/python_examples/face_clustering.py b/ml/dlib/python_examples/face_clustering.py
new file mode 100755
index 00000000..36261387
--- /dev/null
+++ b/ml/dlib/python_examples/face_clustering.py
@@ -0,0 +1,127 @@
+#!/usr/bin/python
+# The contents of this file are in the public domain. See LICENSE_FOR_EXAMPLE_PROGRAMS.txt
+#
+# This example shows how to use dlib's face recognition tool for clustering using chinese_whispers.
+# This is useful when you have a collection of photographs which you know are linked to
+# a particular person, but the person may be photographed with multiple other people.
+# In this example, we assume the largest cluster will contain photos of the common person in the
+# collection of photographs. Then, we save extracted images of the face in the largest cluster in
+# a 150x150 px format which is suitable for jittering and loading to perform metric learning (as shown
+# in the dnn_metric_learning_on_images_ex.cpp example.
+# https://github.com/davisking/dlib/blob/master/examples/dnn_metric_learning_on_images_ex.cpp
+#
+# COMPILING/INSTALLING THE DLIB PYTHON INTERFACE
+# You can install dlib using the command:
+# pip install dlib
+#
+# Alternatively, if you want to compile dlib yourself then go into the dlib
+# root folder and run:
+# python setup.py install
+# or
+# python setup.py install --yes USE_AVX_INSTRUCTIONS
+# if you have a CPU that supports AVX instructions, since this makes some
+# things run faster. This code will also use CUDA if you have CUDA and cuDNN
+# installed.
+#
+# Compiling dlib should work on any operating system so long as you have
+# CMake installed. On Ubuntu, this can be done easily by running the
+# command:
+# sudo apt-get install cmake
+#
+# Also note that this example requires scikit-image which can be installed
+# via the command:
+# pip install scikit-image
+# Or downloaded from http://scikit-image.org/download.html.
+
+import sys
+import os
+import dlib
+import glob
+from skimage import io
+
+if len(sys.argv) != 5:
+ print(
+ "Call this program like this:\n"
+ " ./face_clustering.py shape_predictor_5_face_landmarks.dat dlib_face_recognition_resnet_model_v1.dat ../examples/faces output_folder\n"
+ "You can download a trained facial shape predictor and recognition model from:\n"
+ " http://dlib.net/files/shape_predictor_5_face_landmarks.dat.bz2\n"
+ " http://dlib.net/files/dlib_face_recognition_resnet_model_v1.dat.bz2")
+ exit()
+
+predictor_path = sys.argv[1]
+face_rec_model_path = sys.argv[2]
+faces_folder_path = sys.argv[3]
+output_folder_path = sys.argv[4]
+
+# Load all the models we need: a detector to find the faces, a shape predictor
+# to find face landmarks so we can precisely localize the face, and finally the
+# face recognition model.
+detector = dlib.get_frontal_face_detector()
+sp = dlib.shape_predictor(predictor_path)
+facerec = dlib.face_recognition_model_v1(face_rec_model_path)
+
+descriptors = []
+images = []
+
+# Now find all the faces and compute 128D face descriptors for each face.
+for f in glob.glob(os.path.join(faces_folder_path, "*.jpg")):
+ print("Processing file: {}".format(f))
+ img = io.imread(f)
+
+ # Ask the detector to find the bounding boxes of each face. The 1 in the
+ # second argument indicates that we should upsample the image 1 time. This
+ # will make everything bigger and allow us to detect more faces.
+ dets = detector(img, 1)
+ print("Number of faces detected: {}".format(len(dets)))
+
+ # Now process each face we found.
+ for k, d in enumerate(dets):
+ # Get the landmarks/parts for the face in box d.
+ shape = sp(img, d)
+
+ # Compute the 128D vector that describes the face in img identified by
+ # shape.
+ face_descriptor = facerec.compute_face_descriptor(img, shape)
+ descriptors.append(face_descriptor)
+ images.append((img, shape))
+
+# Now let's cluster the faces.
+labels = dlib.chinese_whispers_clustering(descriptors, 0.5)
+num_classes = len(set(labels))
+print("Number of clusters: {}".format(num_classes))
+
+# Find biggest class
+biggest_class = None
+biggest_class_length = 0
+for i in range(0, num_classes):
+ class_length = len([label for label in labels if label == i])
+ if class_length > biggest_class_length:
+ biggest_class_length = class_length
+ biggest_class = i
+
+print("Biggest cluster id number: {}".format(biggest_class))
+print("Number of faces in biggest cluster: {}".format(biggest_class_length))
+
+# Find the indices for the biggest class
+indices = []
+for i, label in enumerate(labels):
+ if label == biggest_class:
+ indices.append(i)
+
+print("Indices of images in the biggest cluster: {}".format(str(indices)))
+
+# Ensure output directory exists
+if not os.path.isdir(output_folder_path):
+ os.makedirs(output_folder_path)
+
+# Save the extracted faces
+print("Saving faces in largest cluster to output folder...")
+for i, index in enumerate(indices):
+ img, shape = images[index]
+ file_path = os.path.join(output_folder_path, "face_" + str(i))
+ # The size and padding arguments are optional with default size=150x150 and padding=0.25
+ dlib.save_face_chip(img, shape, file_path, size=150, padding=0.25)
+
+
+
+
diff --git a/ml/dlib/python_examples/face_detector.py b/ml/dlib/python_examples/face_detector.py
new file mode 100755
index 00000000..eed3732b
--- /dev/null
+++ b/ml/dlib/python_examples/face_detector.py
@@ -0,0 +1,84 @@
+#!/usr/bin/python
+# The contents of this file are in the public domain. See LICENSE_FOR_EXAMPLE_PROGRAMS.txt
+#
+# This example program shows how to find frontal human faces in an image. In
+# particular, it shows how you can take a list of images from the command
+# line and display each on the screen with red boxes overlaid on each human
+# face.
+#
+# The examples/faces folder contains some jpg images of people. You can run
+# this program on them and see the detections by executing the
+# following command:
+# ./face_detector.py ../examples/faces/*.jpg
+#
+# This face detector is made using the now classic Histogram of Oriented
+# Gradients (HOG) feature combined with a linear classifier, an image
+# pyramid, and sliding window detection scheme. This type of object detector
+# is fairly general and capable of detecting many types of semi-rigid objects
+# in addition to human faces. Therefore, if you are interested in making
+# your own object detectors then read the train_object_detector.py example
+# program.
+#
+#
+# COMPILING/INSTALLING THE DLIB PYTHON INTERFACE
+# You can install dlib using the command:
+# pip install dlib
+#
+# Alternatively, if you want to compile dlib yourself then go into the dlib
+# root folder and run:
+# python setup.py install
+# or
+# python setup.py install --yes USE_AVX_INSTRUCTIONS
+# if you have a CPU that supports AVX instructions, since this makes some
+# things run faster.
+#
+# Compiling dlib should work on any operating system so long as you have
+# CMake installed. On Ubuntu, this can be done easily by running the
+# command:
+# sudo apt-get install cmake
+#
+# Also note that this example requires scikit-image which can be installed
+# via the command:
+# pip install scikit-image
+# Or downloaded from http://scikit-image.org/download.html.
+
+import sys
+
+import dlib
+from skimage import io
+
+
+detector = dlib.get_frontal_face_detector()
+win = dlib.image_window()
+
+for f in sys.argv[1:]:
+ print("Processing file: {}".format(f))
+ img = io.imread(f)
+ # The 1 in the second argument indicates that we should upsample the image
+ # 1 time. This will make everything bigger and allow us to detect more
+ # faces.
+ dets = detector(img, 1)
+ print("Number of faces detected: {}".format(len(dets)))
+ for i, d in enumerate(dets):
+ print("Detection {}: Left: {} Top: {} Right: {} Bottom: {}".format(
+ i, d.left(), d.top(), d.right(), d.bottom()))
+
+ win.clear_overlay()
+ win.set_image(img)
+ win.add_overlay(dets)
+ dlib.hit_enter_to_continue()
+
+
+# Finally, if you really want to you can ask the detector to tell you the score
+# for each detection. The score is bigger for more confident detections.
+# The third argument to run is an optional adjustment to the detection threshold,
+# where a negative value will return more detections and a positive value fewer.
+# Also, the idx tells you which of the face sub-detectors matched. This can be
+# used to broadly identify faces in different orientations.
+if (len(sys.argv[1:]) > 0):
+ img = io.imread(sys.argv[1])
+ dets, scores, idx = detector.run(img, 1, -1)
+ for i, d in enumerate(dets):
+ print("Detection {}, score: {}, face_type:{}".format(
+ d, scores[i], idx[i]))
+
diff --git a/ml/dlib/python_examples/face_jitter.py b/ml/dlib/python_examples/face_jitter.py
new file mode 100755
index 00000000..ee959846
--- /dev/null
+++ b/ml/dlib/python_examples/face_jitter.py
@@ -0,0 +1,97 @@
+#!/usr/bin/python
+# The contents of this file are in the public domain. See LICENSE_FOR_EXAMPLE_PROGRAMS.txt
+#
+# This example shows how faces were jittered and augmented to create training
+# data for dlib's face recognition model. It takes an input image and
+# disturbs the colors as well as applies random translations, rotations, and
+# scaling.
+
+#
+# COMPILING/INSTALLING THE DLIB PYTHON INTERFACE
+# You can install dlib using the command:
+# pip install dlib
+#
+# Alternatively, if you want to compile dlib yourself then go into the dlib
+# root folder and run:
+# python setup.py install
+# or
+# python setup.py install --yes USE_AVX_INSTRUCTIONS
+# if you have a CPU that supports AVX instructions, since this makes some
+# things run faster. This code will also use CUDA if you have CUDA and cuDNN
+# installed.
+#
+# Compiling dlib should work on any operating system so long as you have
+# CMake installed. On Ubuntu, this can be done easily by running the
+# command:
+# sudo apt-get install cmake
+#
+# Also note that this example requires OpenCV and Numpy which can be installed
+# via the command:
+# pip install opencv-python numpy
+#
+# The image file used in this example is in the public domain:
+# https://commons.wikimedia.org/wiki/File:Tom_Cruise_avp_2014_4.jpg
+import sys
+
+import dlib
+import cv2
+import numpy as np
+
+def show_jittered_images(jittered_images):
+ '''
+ Shows the specified jittered images one by one
+ '''
+ for img in jittered_images:
+ cv_bgr_img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
+ cv2.imshow('image',cv_bgr_img)
+ cv2.waitKey(0)
+
+if len(sys.argv) != 2:
+ print(
+ "Call this program like this:\n"
+ " ./face_jitter.py shape_predictor_5_face_landmarks.dat\n"
+ "You can download a trained facial shape predictor from:\n"
+ " http://dlib.net/files/shape_predictor_5_face_landmarks.dat.bz2\n")
+ exit()
+
+predictor_path = sys.argv[1]
+face_file_path = "../examples/faces/Tom_Cruise_avp_2014_4.jpg"
+
+# Load all the models we need: a detector to find the faces, a shape predictor
+# to find face landmarks so we can precisely localize the face
+detector = dlib.get_frontal_face_detector()
+sp = dlib.shape_predictor(predictor_path)
+
+# Load the image using OpenCV
+bgr_img = cv2.imread(face_file_path)
+if bgr_img is None:
+ print("Sorry, we could not load '{}' as an image".format(face_file_path))
+ exit()
+
+# Convert to RGB since dlib uses RGB images
+img = cv2.cvtColor(bgr_img, cv2.COLOR_BGR2RGB)
+
+# Ask the detector to find the bounding boxes of each face.
+dets = detector(img)
+
+num_faces = len(dets)
+
+# Find the 5 face landmarks we need to do the alignment.
+faces = dlib.full_object_detections()
+for detection in dets:
+ faces.append(sp(img, detection))
+
+# Get the aligned face image and show it
+image = dlib.get_face_chip(img, faces[0], size=320)
+cv_bgr_img = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
+cv2.imshow('image',cv_bgr_img)
+cv2.waitKey(0)
+
+# Show 5 jittered images without data augmentation
+jittered_images = dlib.jitter_image(image, num_jitters=5)
+show_jittered_images(jittered_images)
+
+# Show 5 jittered images with data augmentation
+jittered_images = dlib.jitter_image(image, num_jitters=5, disturb_colors=True)
+show_jittered_images(jittered_images)
+cv2.destroyAllWindows()
diff --git a/ml/dlib/python_examples/face_landmark_detection.py b/ml/dlib/python_examples/face_landmark_detection.py
new file mode 100755
index 00000000..35194131
--- /dev/null
+++ b/ml/dlib/python_examples/face_landmark_detection.py
@@ -0,0 +1,100 @@
+#!/usr/bin/python
+# The contents of this file are in the public domain. See LICENSE_FOR_EXAMPLE_PROGRAMS.txt
+#
+# This example program shows how to find frontal human faces in an image and
+# estimate their pose. The pose takes the form of 68 landmarks. These are
+# points on the face such as the corners of the mouth, along the eyebrows, on
+# the eyes, and so forth.
+#
+# The face detector we use is made using the classic Histogram of Oriented
+# Gradients (HOG) feature combined with a linear classifier, an image pyramid,
+# and sliding window detection scheme. The pose estimator was created by
+# using dlib's implementation of the paper:
+# One Millisecond Face Alignment with an Ensemble of Regression Trees by
+# Vahid Kazemi and Josephine Sullivan, CVPR 2014
+# and was trained on the iBUG 300-W face landmark dataset (see
+# https://ibug.doc.ic.ac.uk/resources/facial-point-annotations/):
+# C. Sagonas, E. Antonakos, G, Tzimiropoulos, S. Zafeiriou, M. Pantic.
+# 300 faces In-the-wild challenge: Database and results.
+# Image and Vision Computing (IMAVIS), Special Issue on Facial Landmark Localisation "In-The-Wild". 2016.
+# You can get the trained model file from:
+# http://dlib.net/files/shape_predictor_68_face_landmarks.dat.bz2.
+# Note that the license for the iBUG 300-W dataset excludes commercial use.
+# So you should contact Imperial College London to find out if it's OK for
+# you to use this model file in a commercial product.
+#
+#
+# Also, note that you can train your own models using dlib's machine learning
+# tools. See train_shape_predictor.py to see an example.
+#
+#
+# COMPILING/INSTALLING THE DLIB PYTHON INTERFACE
+# You can install dlib using the command:
+# pip install dlib
+#
+# Alternatively, if you want to compile dlib yourself then go into the dlib
+# root folder and run:
+# python setup.py install
+# or
+# python setup.py install --yes USE_AVX_INSTRUCTIONS
+# if you have a CPU that supports AVX instructions, since this makes some
+# things run faster.
+#
+# Compiling dlib should work on any operating system so long as you have
+# CMake installed. On Ubuntu, this can be done easily by running the
+# command:
+# sudo apt-get install cmake
+#
+# Also note that this example requires scikit-image which can be installed
+# via the command:
+# pip install scikit-image
+# Or downloaded from http://scikit-image.org/download.html.
+
+import sys
+import os
+import dlib
+import glob
+from skimage import io
+
+if len(sys.argv) != 3:
+ print(
+ "Give the path to the trained shape predictor model as the first "
+ "argument and then the directory containing the facial images.\n"
+ "For example, if you are in the python_examples folder then "
+ "execute this program by running:\n"
+ " ./face_landmark_detection.py shape_predictor_68_face_landmarks.dat ../examples/faces\n"
+ "You can download a trained facial shape predictor from:\n"
+ " http://dlib.net/files/shape_predictor_68_face_landmarks.dat.bz2")
+ exit()
+
+predictor_path = sys.argv[1]
+faces_folder_path = sys.argv[2]
+
+detector = dlib.get_frontal_face_detector()
+predictor = dlib.shape_predictor(predictor_path)
+win = dlib.image_window()
+
+for f in glob.glob(os.path.join(faces_folder_path, "*.jpg")):
+ print("Processing file: {}".format(f))
+ img = io.imread(f)
+
+ win.clear_overlay()
+ win.set_image(img)
+
+ # Ask the detector to find the bounding boxes of each face. The 1 in the
+ # second argument indicates that we should upsample the image 1 time. This
+ # will make everything bigger and allow us to detect more faces.
+ dets = detector(img, 1)
+ print("Number of faces detected: {}".format(len(dets)))
+ for k, d in enumerate(dets):
+ print("Detection {}: Left: {} Top: {} Right: {} Bottom: {}".format(
+ k, d.left(), d.top(), d.right(), d.bottom()))
+ # Get the landmarks/parts for the face in box d.
+ shape = predictor(img, d)
+ print("Part 0: {}, Part 1: {} ...".format(shape.part(0),
+ shape.part(1)))
+ # Draw the face landmarks on the screen.
+ win.add_overlay(shape)
+
+ win.add_overlay(dets)
+ dlib.hit_enter_to_continue()
diff --git a/ml/dlib/python_examples/face_recognition.py b/ml/dlib/python_examples/face_recognition.py
new file mode 100755
index 00000000..da2bdbc5
--- /dev/null
+++ b/ml/dlib/python_examples/face_recognition.py
@@ -0,0 +1,123 @@
+#!/usr/bin/python
+# The contents of this file are in the public domain. See LICENSE_FOR_EXAMPLE_PROGRAMS.txt
+#
+# This example shows how to use dlib's face recognition tool. This tool maps
+# an image of a human face to a 128 dimensional vector space where images of
+# the same person are near to each other and images from different people are
+# far apart. Therefore, you can perform face recognition by mapping faces to
+# the 128D space and then checking if their Euclidean distance is small
+# enough.
+#
+# When using a distance threshold of 0.6, the dlib model obtains an accuracy
+# of 99.38% on the standard LFW face recognition benchmark, which is
+# comparable to other state-of-the-art methods for face recognition as of
+# February 2017. This accuracy means that, when presented with a pair of face
+# images, the tool will correctly identify if the pair belongs to the same
+# person or is from different people 99.38% of the time.
+#
+# Finally, for an in-depth discussion of how dlib's tool works you should
+# refer to the C++ example program dnn_face_recognition_ex.cpp and the
+# attendant documentation referenced therein.
+#
+#
+#
+#
+# COMPILING/INSTALLING THE DLIB PYTHON INTERFACE
+# You can install dlib using the command:
+# pip install dlib
+#
+# Alternatively, if you want to compile dlib yourself then go into the dlib
+# root folder and run:
+# python setup.py install
+# or
+# python setup.py install --yes USE_AVX_INSTRUCTIONS
+# if you have a CPU that supports AVX instructions, since this makes some
+# things run faster. This code will also use CUDA if you have CUDA and cuDNN
+# installed.
+#
+# Compiling dlib should work on any operating system so long as you have
+# CMake installed. On Ubuntu, this can be done easily by running the
+# command:
+# sudo apt-get install cmake
+#
+# Also note that this example requires scikit-image which can be installed
+# via the command:
+# pip install scikit-image
+# Or downloaded from http://scikit-image.org/download.html.
+
+import sys
+import os
+import dlib
+import glob
+from skimage import io
+
+if len(sys.argv) != 4:
+ print(
+ "Call this program like this:\n"
+ " ./face_recognition.py shape_predictor_5_face_landmarks.dat dlib_face_recognition_resnet_model_v1.dat ../examples/faces\n"
+ "You can download a trained facial shape predictor and recognition model from:\n"
+ " http://dlib.net/files/shape_predictor_5_face_landmarks.dat.bz2\n"
+ " http://dlib.net/files/dlib_face_recognition_resnet_model_v1.dat.bz2")
+ exit()
+
+predictor_path = sys.argv[1]
+face_rec_model_path = sys.argv[2]
+faces_folder_path = sys.argv[3]
+
+# Load all the models we need: a detector to find the faces, a shape predictor
+# to find face landmarks so we can precisely localize the face, and finally the
+# face recognition model.
+detector = dlib.get_frontal_face_detector()
+sp = dlib.shape_predictor(predictor_path)
+facerec = dlib.face_recognition_model_v1(face_rec_model_path)
+
+win = dlib.image_window()
+
+# Now process all the images
+for f in glob.glob(os.path.join(faces_folder_path, "*.jpg")):
+ print("Processing file: {}".format(f))
+ img = io.imread(f)
+
+ win.clear_overlay()
+ win.set_image(img)
+
+ # Ask the detector to find the bounding boxes of each face. The 1 in the
+ # second argument indicates that we should upsample the image 1 time. This
+ # will make everything bigger and allow us to detect more faces.
+ dets = detector(img, 1)
+ print("Number of faces detected: {}".format(len(dets)))
+
+ # Now process each face we found.
+ for k, d in enumerate(dets):
+ print("Detection {}: Left: {} Top: {} Right: {} Bottom: {}".format(
+ k, d.left(), d.top(), d.right(), d.bottom()))
+ # Get the landmarks/parts for the face in box d.
+ shape = sp(img, d)
+ # Draw the face landmarks on the screen so we can see what face is currently being processed.
+ win.clear_overlay()
+ win.add_overlay(d)
+ win.add_overlay(shape)
+
+ # Compute the 128D vector that describes the face in img identified by
+ # shape. In general, if two face descriptor vectors have a Euclidean
+ # distance between them less than 0.6 then they are from the same
+ # person, otherwise they are from different people. Here we just print
+ # the vector to the screen.
+ face_descriptor = facerec.compute_face_descriptor(img, shape)
+ print(face_descriptor)
+ # It should also be noted that you can also call this function like this:
+ # face_descriptor = facerec.compute_face_descriptor(img, shape, 100)
+ # The version of the call without the 100 gets 99.13% accuracy on LFW
+ # while the version with 100 gets 99.38%. However, the 100 makes the
+ # call 100x slower to execute, so choose whatever version you like. To
+ # explain a little, the 3rd argument tells the code how many times to
+ # jitter/resample the image. When you set it to 100 it executes the
+ # face descriptor extraction 100 times on slightly modified versions of
+ # the face and returns the average result. You could also pick a more
+ # middle value, such as 10, which is only 10x slower but still gets an
+ # LFW accuracy of 99.3%.
+
+
+ dlib.hit_enter_to_continue()
+
+
diff --git a/ml/dlib/python_examples/find_candidate_object_locations.py b/ml/dlib/python_examples/find_candidate_object_locations.py
new file mode 100755
index 00000000..a5c38642
--- /dev/null
+++ b/ml/dlib/python_examples/find_candidate_object_locations.py
@@ -0,0 +1,54 @@
+#!/usr/bin/python
+#
+# This example shows how to use find_candidate_object_locations(). The
+# function takes an input image and generates a set of candidate rectangles
+# which are expected to bound any objects in the image.
+# It is based on the paper:
+# Segmentation as Selective Search for Object Recognition by Koen E. A. van de Sande, et al.
+#
+# Typically, you would use this as part of an object detection pipeline.
+# find_candidate_object_locations() nominates boxes that might contain an
+# object and you then run some expensive classifier on each one and throw away
+# the false alarms. Since find_candidate_object_locations() will only generate
+# a few thousand rectangles it is much faster than scanning all possible
+# rectangles inside an image.
+#
+#
+# COMPILING/INSTALLING THE DLIB PYTHON INTERFACE
+# You can install dlib using the command:
+# pip install dlib
+#
+# Alternatively, if you want to compile dlib yourself then go into the dlib
+# root folder and run:
+# python setup.py install
+# or
+# python setup.py install --yes USE_AVX_INSTRUCTIONS
+# if you have a CPU that supports AVX instructions, since this makes some
+# things run faster.
+#
+# Compiling dlib should work on any operating system so long as you have
+# CMake installed. On Ubuntu, this can be done easily by running the
+# command:
+# sudo apt-get install cmake
+#
+# Also note that this example requires scikit-image which can be installed
+# via the command:
+# pip install scikit-image
+# Or downloaded from http://scikit-image.org/download.html.
+
+
+
+import dlib
+from skimage import io
+
+image_file = '../examples/faces/2009_004587.jpg'
+img = io.imread(image_file)
+
+# Locations of candidate objects will be saved into rects
+rects = []
+dlib.find_candidate_object_locations(img, rects, min_size=500)
+
+print("number of rectangles found {}".format(len(rects)))
+for k, d in enumerate(rects):
+ print("Detection {}: Left: {} Top: {} Right: {} Bottom: {}".format(
+ k, d.left(), d.top(), d.right(), d.bottom()))
diff --git a/ml/dlib/python_examples/global_optimization.py b/ml/dlib/python_examples/global_optimization.py
new file mode 100755
index 00000000..e3fb3f8c
--- /dev/null
+++ b/ml/dlib/python_examples/global_optimization.py
@@ -0,0 +1,47 @@
+#!/usr/bin/python
+# The contents of this file are in the public domain. See LICENSE_FOR_EXAMPLE_PROGRAMS.txt
+#
+#
+# This is an example illustrating the use of the global optimization routine,
+# find_min_global(), from the dlib C++ Library. This is a tool for finding the
+# inputs to a function that result in the function giving its minimal output.
+# This is a very useful tool for hyper parameter search when applying machine
+# learning methods. There are also many other applications for this kind of
+# general derivative free optimization. However, in this example program, we
+# simply show how to call the method. For that, we use a common global
+# optimization test function, as you can see below.
+#
+#
+# COMPILING/INSTALLING THE DLIB PYTHON INTERFACE
+# You can install dlib using the command:
+# pip install dlib
+#
+# Alternatively, if you want to compile dlib yourself then go into the dlib
+# root folder and run:
+# python setup.py install
+#
+# Compiling dlib should work on any operating system so long as you have
+# CMake installed. On Ubuntu, this can be done easily by running the
+# command:
+# sudo apt-get install cmake
+#
+
+import dlib
+from math import sin,cos,pi,exp,sqrt
+
+# This is a standard test function for these kinds of optimization problems.
+# It has a bunch of local minima, with the global minimum resulting in
+# holder_table()==-19.2085025679.
+def holder_table(x0,x1):
+ return -abs(sin(x0)*cos(x1)*exp(abs(1-sqrt(x0*x0+x1*x1)/pi)))
+
+# Find the optimal inputs to holder_table(). The print statements that follow
+# show that find_min_global() finds the optimal settings to high precision.
+x,y = dlib.find_min_global(holder_table,
+ [-10,-10], # Lower bound constraints on x0 and x1 respectively
+ [10,10], # Upper bound constraints on x0 and x1 respectively
+ 80) # The number of times find_min_global() will call holder_table()
+
+print("optimal inputs: {}".format(x));
+print("optimal output: {}".format(y));
+
diff --git a/ml/dlib/python_examples/max_cost_assignment.py b/ml/dlib/python_examples/max_cost_assignment.py
new file mode 100755
index 00000000..8e284e6c
--- /dev/null
+++ b/ml/dlib/python_examples/max_cost_assignment.py
@@ -0,0 +1,57 @@
+#!/usr/bin/python
+# The contents of this file are in the public domain. See LICENSE_FOR_EXAMPLE_PROGRAMS.txt
+#
+# This simple example shows how to call dlib's optimal linear assignment
+# problem solver. It is an implementation of the famous Hungarian algorithm
+# and is quite fast, operating in O(N^3) time.
+#
+# COMPILING/INSTALLING THE DLIB PYTHON INTERFACE
+# You can install dlib using the command:
+# pip install dlib
+#
+# Alternatively, if you want to compile dlib yourself then go into the dlib
+# root folder and run:
+# python setup.py install
+# or
+# python setup.py install --yes USE_AVX_INSTRUCTIONS
+# if you have a CPU that supports AVX instructions, since this makes some
+# things run faster.
+#
+# Compiling dlib should work on any operating system so long as you have
+# CMake installed. On Ubuntu, this can be done easily by running the
+# command:
+# sudo apt-get install cmake
+#
+
+import dlib
+
+# Let's imagine you need to assign N people to N jobs. Additionally, each
+# person will make your company a certain amount of money at each job, but each
+# person has different skills so they are better at some jobs and worse at
+# others. You would like to find the best way to assign people to these jobs.
+# In particular, you would like to maximize the amount of money the group makes
+# as a whole. This is an example of an assignment problem and is what is solved
+# by the dlib.max_cost_assignment() routine.
+
+# So in this example, let's imagine we have 3 people and 3 jobs. We represent
+# the amount of money each person will produce at each job with a cost matrix.
+# Each row corresponds to a person and each column corresponds to a job. So for
+# example, below we are saying that person 0 will make $1 at job 0, $2 at job 1,
+# and $6 at job 2.
+cost = dlib.matrix([[1, 2, 6],
+ [5, 3, 6],
+ [4, 5, 0]])
+
+# To find out the best assignment of people to jobs we just need to call this
+# function.
+assignment = dlib.max_cost_assignment(cost)
+
+# This prints optimal assignments: [2, 0, 1]
+# which indicates that we should assign the person from the first row of the
+# cost matrix to job 2, the middle row person to job 0, and the bottom row
+# person to job 1.
+print("Optimal assignments: {}".format(assignment))
+
+# This prints optimal cost: 16.0
+# which is correct since our optimal assignment is 6+5+5.
+print("Optimal cost: {}".format(dlib.assignment_cost(cost, assignment)))
diff --git a/ml/dlib/python_examples/requirements.txt b/ml/dlib/python_examples/requirements.txt
new file mode 100644
index 00000000..8fa92c8a
--- /dev/null
+++ b/ml/dlib/python_examples/requirements.txt
@@ -0,0 +1,3 @@
+scikit-image>=0.9.3
+opencv-python
+numpy
diff --git a/ml/dlib/python_examples/sequence_segmenter.py b/ml/dlib/python_examples/sequence_segmenter.py
new file mode 100755
index 00000000..335e475f
--- /dev/null
+++ b/ml/dlib/python_examples/sequence_segmenter.py
@@ -0,0 +1,197 @@
+#!/usr/bin/python
+# The contents of this file are in the public domain. See LICENSE_FOR_EXAMPLE_PROGRAMS.txt
+#
+# This example shows how to use dlib to learn to do sequence segmentation. In
+# a sequence segmentation task we are given a sequence of objects (e.g. words in
+# a sentence) and we are supposed to detect certain subsequences (e.g. the names
+# of people). Therefore, in the code below we create some very simple training
+# sequences and use them to learn a sequence segmentation model. In particular,
+# our sequences will be sentences represented as arrays of words and our task
+# will be to learn to identify person names. Once we have our segmentation
+# model we can use it to find names in new sentences, as we will show.
+#
+# COMPILING/INSTALLING THE DLIB PYTHON INTERFACE
+# You can install dlib using the command:
+# pip install dlib
+#
+# Alternatively, if you want to compile dlib yourself then go into the dlib
+# root folder and run:
+# python setup.py install
+# or
+# python setup.py install --yes USE_AVX_INSTRUCTIONS
+# if you have a CPU that supports AVX instructions, since this makes some
+# things run faster.
+#
+# Compiling dlib should work on any operating system so long as you have
+# CMake installed. On Ubuntu, this can be done easily by running the
+# command:
+# sudo apt-get install cmake
+#
+import sys
+import dlib
+
+
+# The sequence segmentation models we work with in this example are chain
+# structured conditional random field style models. Therefore, central to a
+# sequence segmentation model is some method for converting the elements of a
+# sequence into feature vectors. That is, while you might start out representing
+# your sequence as an array of strings, the dlib interface works in terms of
+# arrays of feature vectors. Each feature vector should capture important
+# information about its corresponding element in the original raw sequence. So
+# in this example, since we work with sequences of words and want to identify
+# names, we will create feature vectors that tell us if the word is capitalized
+# or not. In our simple data, this will be enough to identify names.
+# Therefore, we define sentence_to_vectors() which takes a sentence represented
+# as a string and converts it into an array of words and then associates a
+# feature vector with each word.
+def sentence_to_vectors(sentence):
+ # Create an empty array of vectors
+ vects = dlib.vectors()
+ for word in sentence.split():
+ # Our vectors are very simple 1-dimensional vectors. The value of the
+ # single feature is 1 if the first letter of the word is capitalized and
+ # 0 otherwise.
+ if word[0].isupper():
+ vects.append(dlib.vector([1]))
+ else:
+ vects.append(dlib.vector([0]))
+ return vects
+
+
+# Dlib also supports the use of a sparse vector representation. This is more
+# efficient than the above form when you have very high dimensional vectors that
+# are mostly full of zeros. In dlib, each sparse vector is represented as an
+# array of pair objects. Each pair contains an index and value. Any index not
+# listed in the vector is implicitly associated with a value of zero.
+# Additionally, when using sparse vectors with dlib.train_sequence_segmenter()
+# you can use "unsorted" sparse vectors. This means you can add the index/value
+# pairs into your sparse vectors in any order you want and don't need to worry
+# about them being in sorted order.
+def sentence_to_sparse_vectors(sentence):
+ vects = dlib.sparse_vectors()
+ has_cap = dlib.sparse_vector()
+ no_cap = dlib.sparse_vector()
+ # make has_cap equivalent to dlib.vector([1])
+ has_cap.append(dlib.pair(0, 1))
+
+ # Since we didn't add anything to no_cap it is equivalent to
+ # dlib.vector([0])
+ for word in sentence.split():
+ if word[0].isupper():
+ vects.append(has_cap)
+ else:
+ vects.append(no_cap)
+ return vects
+
+
+def print_segment(sentence, names):
+ words = sentence.split()
+ for name in names:
+ for i in name:
+ sys.stdout.write(words[i] + " ")
+ sys.stdout.write("\n")
+
+
+
+# Now let's make some training data. Each example is a sentence as well as a
+# set of ranges which indicate the locations of any names.
+names = dlib.ranges() # make an array of dlib.range objects.
+segments = dlib.rangess() # make an array of arrays of dlib.range objects.
+sentences = []
+
+sentences.append("The other day I saw a man named Jim Smith")
+# We want to detect person names. So we note that the name is located within
+# the range [8, 10). Note that we use half open ranges to identify segments.
+# So in this case, the segment identifies the string "Jim Smith".
+names.append(dlib.range(8, 10))
+segments.append(names)
+names.clear() # make names empty for use again below
+
+sentences.append("Davis King is the main author of the dlib Library")
+names.append(dlib.range(0, 2))
+segments.append(names)
+names.clear()
+
+sentences.append("Bob Jones is a name and so is George Clinton")
+names.append(dlib.range(0, 2))
+names.append(dlib.range(8, 10))
+segments.append(names)
+names.clear()
+
+sentences.append("My dog is named Bob Barker")
+names.append(dlib.range(4, 6))
+segments.append(names)
+names.clear()
+
+sentences.append("ABC is an acronym but John James Smith is a name")
+names.append(dlib.range(5, 8))
+segments.append(names)
+names.clear()
+
+sentences.append("No names in this sentence at all")
+segments.append(names)
+names.clear()
+
+
+# Now before we can pass these training sentences to the dlib tools we need to
+# convert them into arrays of vectors as discussed above. We can use either a
+# sparse or dense representation depending on our needs. In this example, we
+# show how to do it both ways.
+use_sparse_vects = False
+if use_sparse_vects:
+ # Make an array of arrays of dlib.sparse_vector objects.
+ training_sequences = dlib.sparse_vectorss()
+ for s in sentences:
+ training_sequences.append(sentence_to_sparse_vectors(s))
+else:
+ # Make an array of arrays of dlib.vector objects.
+ training_sequences = dlib.vectorss()
+ for s in sentences:
+ training_sequences.append(sentence_to_vectors(s))
+
+# Now that we have a simple training set we can train a sequence segmenter.
+# However, the sequence segmentation trainer has some optional parameters we can
+# set. These parameters determine properties of the segmentation model we will
+# learn. See the dlib documentation for the sequence_segmenter object for a
+# full discussion of their meanings.
+params = dlib.segmenter_params()
+params.window_size = 3
+params.use_high_order_features = True
+params.use_BIO_model = True
+# This is the common SVM C parameter. Larger values encourage the trainer to
+# attempt to fit the data exactly but might overfit. In general, you determine
+# this parameter by cross-validation.
+params.C = 10
+
+# Train a model. The model object is responsible for predicting the locations
+# of names in new sentences.
+model = dlib.train_sequence_segmenter(training_sequences, segments, params)
+
+# Let's print out the things the model thinks are names. The output is a set
+# of ranges which are predicted to contain names. If you run this example
+# program you will see that it gets them all correct.
+for i, s in enumerate(sentences):
+ print_segment(s, model(training_sequences[i]))
+
+# Let's also try segmenting a new sentence. This will print out "Bob Bucket".
+# Note that we need to remember to use the same vector representation as we used
+# during training.
+test_sentence = "There once was a man from Nantucket " \
+ "whose name rhymed with Bob Bucket"
+if use_sparse_vects:
+ print_segment(test_sentence,
+ model(sentence_to_sparse_vectors(test_sentence)))
+else:
+ print_segment(test_sentence, model(sentence_to_vectors(test_sentence)))
+
+# We can also measure the accuracy of a model relative to some labeled data.
+# This statement prints the precision, recall, and F1-score of the model
+# relative to the data in training_sequences/segments.
+print("Test on training data: {}".format(
+ dlib.test_sequence_segmenter(model, training_sequences, segments)))
+
+# We can also do 5-fold cross-validation and print the resulting precision,
+# recall, and F1-score.
+print("Cross validation: {}".format(
+ dlib.cross_validate_sequence_segmenter(training_sequences, segments, 5,
+ params)))
diff --git a/ml/dlib/python_examples/svm_binary_classifier.py b/ml/dlib/python_examples/svm_binary_classifier.py
new file mode 100755
index 00000000..d114c815
--- /dev/null
+++ b/ml/dlib/python_examples/svm_binary_classifier.py
@@ -0,0 +1,68 @@
+#!/usr/bin/python
+# The contents of this file are in the public domain. See LICENSE_FOR_EXAMPLE_PROGRAMS.txt
+#
+#
+# This is an example illustrating the use of a binary SVM classifier tool from
+# the dlib C++ Library. In this example, we will create a simple test dataset
+# and show how to learn a classifier from it.
+#
+#
+# COMPILING/INSTALLING THE DLIB PYTHON INTERFACE
+# You can install dlib using the command:
+# pip install dlib
+#
+# Alternatively, if you want to compile dlib yourself then go into the dlib
+# root folder and run:
+# python setup.py install
+# or
+# python setup.py install --yes USE_AVX_INSTRUCTIONS
+# if you have a CPU that supports AVX instructions, since this makes some
+# things run faster.
+#
+# Compiling dlib should work on any operating system so long as you have
+# CMake installed. On Ubuntu, this can be done easily by running the
+# command:
+# sudo apt-get install cmake
+#
+
+import dlib
+try:
+ import cPickle as pickle
+except ImportError:
+ import pickle
+
+x = dlib.vectors()
+y = dlib.array()
+
+# Make a training dataset. Here we have just two training examples. Normally
+# you would use a much larger training dataset, but for the purpose of example
+# this is plenty. For binary classification, the y labels should all be either +1 or -1.
+x.append(dlib.vector([1, 2, 3, -1, -2, -3]))
+y.append(+1)
+
+x.append(dlib.vector([-1, -2, -3, 1, 2, 3]))
+y.append(-1)
+
+
+# Now make a training object. This object is responsible for turning a
+# training dataset into a prediction model. This one here is a SVM trainer
+# that uses a linear kernel. If you wanted to use a RBF kernel or histogram
+# intersection kernel you could change it to one of these lines:
+# svm = dlib.svm_c_trainer_histogram_intersection()
+# svm = dlib.svm_c_trainer_radial_basis()
+svm = dlib.svm_c_trainer_linear()
+svm.be_verbose()
+svm.set_c(10)
+
+# Now train the model. The return value is the trained model capable of making predictions.
+classifier = svm.train(x, y)
+
+# Now run the model on our data and look at the results.
+print("prediction for first sample: {}".format(classifier(x[0])))
+print("prediction for second sample: {}".format(classifier(x[1])))
+
+
+# classifier models can also be pickled in the same was as any other python object.
+with open('saved_model.pickle', 'wb') as handle:
+ pickle.dump(classifier, handle, 2)
+
diff --git a/ml/dlib/python_examples/svm_rank.py b/ml/dlib/python_examples/svm_rank.py
new file mode 100755
index 00000000..dad64227
--- /dev/null
+++ b/ml/dlib/python_examples/svm_rank.py
@@ -0,0 +1,155 @@
+#!/usr/bin/python
+# The contents of this file are in the public domain. See LICENSE_FOR_EXAMPLE_PROGRAMS.txt
+#
+#
+# This is an example illustrating the use of the SVM-Rank tool from the dlib C++
+# Library. This is a tool useful for learning to rank objects. For example,
+# you might use it to learn to rank web pages in response to a user's query.
+# The idea being to rank the most relevant pages higher than non-relevant pages.
+#
+# In this example, we will create a simple test dataset and show how to learn a
+# ranking function from it. The purpose of the function will be to give
+# "relevant" objects higher scores than "non-relevant" objects. The idea is
+# that you use this score to order the objects so that the most relevant objects
+# come to the top of the ranked list.
+#
+#
+# COMPILING/INSTALLING THE DLIB PYTHON INTERFACE
+# You can install dlib using the command:
+# pip install dlib
+#
+# Alternatively, if you want to compile dlib yourself then go into the dlib
+# root folder and run:
+# python setup.py install
+# or
+# python setup.py install --yes USE_AVX_INSTRUCTIONS
+# if you have a CPU that supports AVX instructions, since this makes some
+# things run faster.
+#
+# Compiling dlib should work on any operating system so long as you have
+# CMake installed. On Ubuntu, this can be done easily by running the
+# command:
+# sudo apt-get install cmake
+#
+
+import dlib
+
+
+# Now let's make some testing data. To make it really simple, let's suppose
+# that we are ranking 2D vectors and that vectors with positive values in the
+# first dimension should rank higher than other vectors. So what we do is make
+# examples of relevant (i.e. high ranking) and non-relevant (i.e. low ranking)
+# vectors and store them into a ranking_pair object like so:
+data = dlib.ranking_pair()
+# Here we add two examples. In real applications, you would want lots of
+# examples of relevant and non-relevant vectors.
+data.relevant.append(dlib.vector([1, 0]))
+data.nonrelevant.append(dlib.vector([0, 1]))
+
+# Now that we have some data, we can use a machine learning method to learn a
+# function that will give high scores to the relevant vectors and low scores to
+# the non-relevant vectors.
+trainer = dlib.svm_rank_trainer()
+# Note that the trainer object has some parameters that control how it behaves.
+# For example, since this is the SVM-Rank algorithm it has a C parameter that
+# controls the trade-off between trying to fit the training data exactly or
+# selecting a "simpler" solution which might generalize better.
+trainer.c = 10
+
+# So let's do the training.
+rank = trainer.train(data)
+
+# Now if you call rank on a vector it will output a ranking score. In
+# particular, the ranking score for relevant vectors should be larger than the
+# score for non-relevant vectors.
+print("Ranking score for a relevant vector: {}".format(
+ rank(data.relevant[0])))
+print("Ranking score for a non-relevant vector: {}".format(
+ rank(data.nonrelevant[0])))
+# The output is the following:
+# ranking score for a relevant vector: 0.5
+# ranking score for a non-relevant vector: -0.5
+
+
+# If we want an overall measure of ranking accuracy we can compute the ordering
+# accuracy and mean average precision values by calling test_ranking_function().
+# In this case, the ordering accuracy tells us how often a non-relevant vector
+# was ranked ahead of a relevant vector. In this case, it returns 1 for both
+# metrics, indicating that the rank function outputs a perfect ranking.
+print(dlib.test_ranking_function(rank, data))
+
+# The ranking scores are computed by taking the dot product between a learned
+# weight vector and a data vector. If you want to see the learned weight vector
+# you can display it like so:
+print("Weights: {}".format(rank.weights))
+# In this case the weights are:
+# 0.5
+# -0.5
+
+# In the above example, our data contains just two sets of objects. The
+# relevant set and non-relevant set. The trainer is attempting to find a
+# ranking function that gives every relevant vector a higher score than every
+# non-relevant vector. Sometimes what you want to do is a little more complex
+# than this.
+#
+# For example, in the web page ranking example we have to rank pages based on a
+# user's query. In this case, each query will have its own set of relevant and
+# non-relevant documents. What might be relevant to one query may well be
+# non-relevant to another. So in this case we don't have a single global set of
+# relevant web pages and another set of non-relevant web pages.
+#
+# To handle cases like this, we can simply give multiple ranking_pair instances
+# to the trainer. Therefore, each ranking_pair would represent the
+# relevant/non-relevant sets for a particular query. An example is shown below
+# (for simplicity, we reuse our data from above to make 4 identical "queries").
+queries = dlib.ranking_pairs()
+queries.append(data)
+queries.append(data)
+queries.append(data)
+queries.append(data)
+
+# We can train just as before.
+rank = trainer.train(queries)
+
+# Now that we have multiple ranking_pair instances, we can also use
+# cross_validate_ranking_trainer(). This performs cross-validation by splitting
+# the queries up into folds. That is, it lets the trainer train on a subset of
+# ranking_pair instances and tests on the rest. It does this over 4 different
+# splits and returns the overall ranking accuracy based on the held out data.
+# Just like test_ranking_function(), it reports both the ordering accuracy and
+# mean average precision.
+print("Cross validation results: {}".format(
+ dlib.cross_validate_ranking_trainer(trainer, queries, 4)))
+
+# Finally, note that the ranking tools also support the use of sparse vectors in
+# addition to dense vectors (which we used above). So if we wanted to do
+# exactly what we did in the first part of the example program above but using
+# sparse vectors we would do it like so:
+
+data = dlib.sparse_ranking_pair()
+samp = dlib.sparse_vector()
+
+# Make samp represent the same vector as dlib.vector([1, 0]). In dlib, a sparse
+# vector is just an array of pair objects. Each pair stores an index and a
+# value. Moreover, the svm-ranking tools require sparse vectors to be sorted
+# and to have unique indices. This means that the indices are listed in
+# increasing order and no index value shows up more than once. If necessary,
+# you can use the dlib.make_sparse_vector() routine to make a sparse vector
+# object properly sorted and contain unique indices.
+samp.append(dlib.pair(0, 1))
+data.relevant.append(samp)
+
+# Now make samp represent the same vector as dlib.vector([0, 1])
+samp.clear()
+samp.append(dlib.pair(1, 1))
+data.nonrelevant.append(samp)
+
+trainer = dlib.svm_rank_trainer_sparse()
+rank = trainer.train(data)
+print("Ranking score for a relevant vector: {}".format(
+ rank(data.relevant[0])))
+print("Ranking score for a non-relevant vector: {}".format(
+ rank(data.nonrelevant[0])))
+# Just as before, the output is the following:
+# ranking score for a relevant vector: 0.5
+# ranking score for a non-relevant vector: -0.5
diff --git a/ml/dlib/python_examples/svm_struct.py b/ml/dlib/python_examples/svm_struct.py
new file mode 100755
index 00000000..7f0004cc
--- /dev/null
+++ b/ml/dlib/python_examples/svm_struct.py
@@ -0,0 +1,343 @@
+#!/usr/bin/python
+# The contents of this file are in the public domain. See LICENSE_FOR_EXAMPLE_PROGRAMS.txt
+#
+# This is an example illustrating the use of the structural SVM solver from
+# the dlib C++ Library. Therefore, this example teaches you the central ideas
+# needed to setup a structural SVM model for your machine learning problems. To
+# illustrate the process, we use dlib's structural SVM solver to learn the
+# parameters of a simple multi-class classifier. We first discuss the
+# multi-class classifier model and then walk through using the structural SVM
+# tools to find the parameters of this classification model. As an aside,
+# dlib's C++ interface to the structural SVM solver is threaded. So on a
+# multi-core computer it is significantly faster than using the python
+# interface. So consider using the C++ interface instead if you find that
+# running it in python is slow.
+#
+#
+# COMPILING/INSTALLING THE DLIB PYTHON INTERFACE
+# You can install dlib using the command:
+# pip install dlib
+#
+# Alternatively, if you want to compile dlib yourself then go into the dlib
+# root folder and run:
+# python setup.py install
+# or
+# python setup.py install --yes USE_AVX_INSTRUCTIONS
+# if you have a CPU that supports AVX instructions, since this makes some
+# things run faster.
+#
+# Compiling dlib should work on any operating system so long as you have
+# CMake installed. On Ubuntu, this can be done easily by running the
+# command:
+# sudo apt-get install cmake
+#
+
+import dlib
+
+
+def main():
+ # In this example, we have three types of samples: class 0, 1, or 2. That
+ # is, each of our sample vectors falls into one of three classes. To keep
+ # this example very simple, each sample vector is zero everywhere except at
+ # one place. The non-zero dimension of each vector determines the class of
+ # the vector. So for example, the first element of samples has a class of 1
+ # because samples[0][1] is the only non-zero element of samples[0].
+ samples = [[0, 2, 0], [1, 0, 0], [0, 4, 0], [0, 0, 3]]
+ # Since we want to use a machine learning method to learn a 3-class
+ # classifier we need to record the labels of our samples. Here samples[i]
+ # has a class label of labels[i].
+ labels = [1, 0, 1, 2]
+
+ # Now that we have some training data we can tell the structural SVM to
+ # learn the parameters of our 3-class classifier model. The details of this
+ # will be explained later. For now, just note that it finds the weights
+ # (i.e. a vector of real valued parameters) such that predict_label(weights,
+ # sample) always returns the correct label for a sample vector.
+ problem = ThreeClassClassifierProblem(samples, labels)
+ weights = dlib.solve_structural_svm_problem(problem)
+
+ # Print the weights and then evaluate predict_label() on each of our
+ # training samples. Note that the correct label is predicted for each
+ # sample.
+ print(weights)
+ for k, s in enumerate(samples):
+ print("Predicted label for sample[{0}]: {1}".format(
+ k, predict_label(weights, s)))
+
+
+def predict_label(weights, sample):
+ """Given the 9-dimensional weight vector which defines a 3 class classifier,
+ predict the class of the given 3-dimensional sample vector. Therefore, the
+ output of this function is either 0, 1, or 2 (i.e. one of the three possible
+ labels)."""
+
+ # Our 3-class classifier model can be thought of as containing 3 separate
+ # linear classifiers. So to predict the class of a sample vector we
+ # evaluate each of these three classifiers and then whatever classifier has
+ # the largest output "wins" and predicts the label of the sample. This is
+ # the popular one-vs-all multi-class classifier model.
+ # Keeping this in mind, the code below simply pulls the three separate
+ # weight vectors out of weights and then evaluates each against sample. The
+ # individual classifier scores are stored in scores and the highest scoring
+ # index is returned as the label.
+ w0 = weights[0:3]
+ w1 = weights[3:6]
+ w2 = weights[6:9]
+ scores = [dot(w0, sample), dot(w1, sample), dot(w2, sample)]
+ max_scoring_label = scores.index(max(scores))
+ return max_scoring_label
+
+
+def dot(a, b):
+ """Compute the dot product between the two vectors a and b."""
+ return sum(i * j for i, j in zip(a, b))
+
+
+################################################################################
+
+
+class ThreeClassClassifierProblem:
+ # Now we arrive at the meat of this example program. To use the
+ # dlib.solve_structural_svm_problem() routine you need to define an object
+ # which tells the structural SVM solver what to do for your problem. In
+ # this example, this is done by defining the ThreeClassClassifierProblem
+ # object. Before we get into the details, we first discuss some background
+ # information on structural SVMs.
+ #
+ # A structural SVM is a supervised machine learning method for learning to
+ # predict complex outputs. This is contrasted with a binary classifier
+ # which makes only simple yes/no predictions. A structural SVM, on the
+ # other hand, can learn to predict complex outputs such as entire parse
+ # trees or DNA sequence alignments. To do this, it learns a function F(x,y)
+ # which measures how well a particular data sample x matches a label y,
+ # where a label is potentially a complex thing like a parse tree. However,
+ # to keep this example program simple we use only a 3 category label output.
+ #
+ # At test time, the best label for a new x is given by the y which
+ # maximizes F(x,y). To put this into the context of the current example,
+ # F(x,y) computes the score for a given sample and class label. The
+ # predicted class label is therefore whatever value of y which makes F(x,y)
+ # the biggest. This is exactly what predict_label() does. That is, it
+ # computes F(x,0), F(x,1), and F(x,2) and then reports which label has the
+ # biggest value.
+ #
+ # At a high level, a structural SVM can be thought of as searching the
+ # parameter space of F(x,y) for the set of parameters that make the
+ # following inequality true as often as possible:
+ # F(x_i,y_i) > max{over all incorrect labels of x_i} F(x_i, y_incorrect)
+ # That is, it seeks to find the parameter vector such that F(x,y) always
+ # gives the highest score to the correct output. To define the structural
+ # SVM optimization problem precisely, we first introduce some notation:
+ # - let PSI(x,y) == the joint feature vector for input x and a label y
+ # - let F(x,y|w) == dot(w,PSI(x,y)).
+ # (we use the | notation to emphasize that F() has the parameter vector
+ # of weights called w)
+ # - let LOSS(idx,y) == the loss incurred for predicting that the
+ # idx-th training sample has a label of y. Note that LOSS()
+ # should always be >= 0 and should become exactly 0 when y is the
+ # correct label for the idx-th sample. Moreover, it should notionally
+ # indicate how bad it is to predict y for the idx'th sample.
+ # - let x_i == the i-th training sample.
+ # - let y_i == the correct label for the i-th training sample.
+ # - The number of data samples is N.
+ #
+ # Then the optimization problem solved by a structural SVM using
+ # dlib.solve_structural_svm_problem() is the following:
+ # Minimize: h(w) == 0.5*dot(w,w) + C*R(w)
+ #
+ # Where R(w) == sum from i=1 to N: 1/N * sample_risk(i,w) and
+ # sample_risk(i,w) == max over all
+ # Y: LOSS(i,Y) + F(x_i,Y|w) - F(x_i,y_i|w) and C > 0
+ #
+ # You can think of the sample_risk(i,w) as measuring the degree of error
+ # you would make when predicting the label of the i-th sample using
+ # parameters w. That is, it is zero only when the correct label would be
+ # predicted and grows larger the more "wrong" the predicted output becomes.
+ # Therefore, the objective function is minimizing a balance between making
+ # the weights small (typically this reduces overfitting) and fitting the
+ # training data. The degree to which you try to fit the data is controlled
+ # by the C parameter.
+ #
+ # For a more detailed introduction to structured support vector machines
+ # you should consult the following paper:
+ # Predicting Structured Objects with Support Vector Machines by
+ # Thorsten Joachims, Thomas Hofmann, Yisong Yue, and Chun-nam Yu
+ #
+
+ # Finally, we come back to the code. To use
+ # dlib.solve_structural_svm_problem() you need to provide the things
+ # discussed above. This is the value of C, the number of training samples,
+ # the dimensionality of PSI(), as well as methods for calculating the loss
+ # values and PSI() vectors. You will also need to write code that can
+ # compute:
+ # max over all Y: LOSS(i,Y) + F(x_i,Y|w). To summarize, the
+ # ThreeClassClassifierProblem class is required to have the following
+ # fields:
+ # - C
+ # - num_samples
+ # - num_dimensions
+ # - get_truth_joint_feature_vector()
+ # - separation_oracle()
+
+ C = 1
+
+ # There are also a number of optional arguments:
+ # epsilon is the stopping tolerance. The optimizer will run until R(w) is
+ # within epsilon of its optimal value. If you don't set this then it
+ # defaults to 0.001.
+ # epsilon = 1e-13
+
+ # Uncomment this and the optimizer will print its progress to standard
+ # out. You will be able to see things like the current risk gap. The
+ # optimizer continues until the
+ # risk gap is below epsilon.
+ # be_verbose = True
+
+ # If you want to require that the learned weights are all non-negative
+ # then set this field to True.
+ # learns_nonnegative_weights = True
+
+ # The optimizer uses an internal cache to avoid unnecessary calls to your
+ # separation_oracle() routine. This parameter controls the size of that
+ # cache. Bigger values use more RAM and might make the optimizer run
+ # faster. You can also disable it by setting it to 0 which is good to do
+ # when your separation_oracle is very fast. If If you don't call this
+ # function it defaults to a value of 5.
+ # max_cache_size = 20
+
+ def __init__(self, samples, labels):
+ # dlib.solve_structural_svm_problem() expects the class to have
+ # num_samples and num_dimensions fields. These fields should contain
+ # the number of training samples and the dimensionality of the PSI
+ # feature vector respectively.
+ self.num_samples = len(samples)
+ self.num_dimensions = len(samples[0])*3
+
+ self.samples = samples
+ self.labels = labels
+
+ def make_psi(self, x, label):
+ """Compute PSI(x,label)."""
+ # All we are doing here is taking x, which is a 3 dimensional sample
+ # vector in this example program, and putting it into one of 3 places in
+ # a 9 dimensional PSI vector, which we then return. So this function
+ # returns PSI(x,label). To see why we setup PSI like this, recall how
+ # predict_label() works. It takes in a 9 dimensional weight vector and
+ # breaks the vector into 3 pieces. Each piece then defines a different
+ # classifier and we use them in a one-vs-all manner to predict the
+ # label. So now that we are in the structural SVM code we have to
+ # define the PSI vector to correspond to this usage. That is, we need
+ # to setup PSI so that argmax_y dot(weights,PSI(x,y)) ==
+ # predict_label(weights,x). This is how we tell the structural SVM
+ # solver what kind of problem we are trying to solve.
+ #
+ # It's worth emphasizing that the single biggest step in using a
+ # structural SVM is deciding how you want to represent PSI(x,label). It
+ # is always a vector, but deciding what to put into it to solve your
+ # problem is often not a trivial task. Part of the difficulty is that
+ # you need an efficient method for finding the label that makes
+ # dot(w,PSI(x,label)) the biggest. Sometimes this is easy, but often
+ # finding the max scoring label turns into a difficult combinatorial
+ # optimization problem. So you need to pick a PSI that doesn't make the
+ # label maximization step intractable but also still well models your
+ # problem.
+ #
+ # Create a dense vector object (note that you can also use unsorted
+ # sparse vectors (i.e. dlib.sparse_vector objects) to represent your
+ # PSI vector. This is useful if you have very high dimensional PSI
+ # vectors that are mostly zeros. In the context of this example, you
+ # would simply return a dlib.sparse_vector at the end of make_psi() and
+ # the rest of the example would still work properly. ).
+ psi = dlib.vector()
+ # Set it to have 9 dimensions. Note that the elements of the vector
+ # are 0 initialized.
+ psi.resize(self.num_dimensions)
+ dims = len(x)
+ if label == 0:
+ for i in range(0, dims):
+ psi[i] = x[i]
+ elif label == 1:
+ for i in range(dims, 2 * dims):
+ psi[i] = x[i - dims]
+ else: # the label must be 2
+ for i in range(2 * dims, 3 * dims):
+ psi[i] = x[i - 2 * dims]
+ return psi
+
+ # Now we get to the two member functions that are directly called by
+ # dlib.solve_structural_svm_problem().
+ #
+ # In get_truth_joint_feature_vector(), all you have to do is return the
+ # PSI() vector for the idx-th training sample when it has its true label.
+ # So here it returns
+ # PSI(self.samples[idx], self.labels[idx]).
+ def get_truth_joint_feature_vector(self, idx):
+ return self.make_psi(self.samples[idx], self.labels[idx])
+
+ # separation_oracle() is more interesting.
+ # dlib.solve_structural_svm_problem() will call separation_oracle() many
+ # times during the optimization. Each time it will give it the current
+ # value of the parameter weights and the separation_oracle() is supposed to
+ # find the label that most violates the structural SVM objective function
+ # for the idx-th sample. Then the separation oracle reports the
+ # corresponding PSI vector and loss value. To state this more precisely,
+ # the separation_oracle() member function has the following contract:
+ # requires
+ # - 0 <= idx < self.num_samples
+ # - len(current_solution) == self.num_dimensions
+ # ensures
+ # - runs the separation oracle on the idx-th sample.
+ # We define this as follows:
+ # - let X == the idx-th training sample.
+ # - let PSI(X,y) == the joint feature vector for input X
+ # and an arbitrary label y.
+ # - let F(X,y) == dot(current_solution,PSI(X,y)).
+ # - let LOSS(idx,y) == the loss incurred for predicting that the
+ # idx-th sample has a label of y. Note that LOSS()
+ # should always be >= 0 and should become exactly 0 when y is the
+ # correct label for the idx-th sample.
+ #
+ # Then the separation oracle finds a Y such that:
+ # Y = argmax over all y: LOSS(idx,y) + F(X,y)
+ # (i.e. It finds the label which maximizes the above expression.)
+ #
+ # Finally, separation_oracle() returns LOSS(idx,Y),PSI(X,Y)
+ def separation_oracle(self, idx, current_solution):
+ samp = self.samples[idx]
+ dims = len(samp)
+ scores = [0, 0, 0]
+ # compute scores for each of the three classifiers
+ scores[0] = dot(current_solution[0:dims], samp)
+ scores[1] = dot(current_solution[dims:2*dims], samp)
+ scores[2] = dot(current_solution[2*dims:3*dims], samp)
+
+ # Add in the loss-augmentation. Recall that we maximize
+ # LOSS(idx,y) + F(X,y) in the separate oracle, not just F(X,y) as we
+ # normally would in predict_label(). Therefore, we must add in this
+ # extra amount to account for the loss-augmentation. For our simple
+ # multi-class classifier, we incur a loss of 1 if we don't predict the
+ # correct label and a loss of 0 if we get the right label.
+ if self.labels[idx] != 0:
+ scores[0] += 1
+ if self.labels[idx] != 1:
+ scores[1] += 1
+ if self.labels[idx] != 2:
+ scores[2] += 1
+
+ # Now figure out which classifier has the largest loss-augmented score.
+ max_scoring_label = scores.index(max(scores))
+ # And finally record the loss that was associated with that predicted
+ # label. Again, the loss is 1 if the label is incorrect and 0 otherwise.
+ if max_scoring_label == self.labels[idx]:
+ loss = 0
+ else:
+ loss = 1
+
+ # Finally, return the loss and PSI vector corresponding to the label
+ # we just found.
+ psi = self.make_psi(samp, max_scoring_label)
+ return loss, psi
+
+
+if __name__ == "__main__":
+ main()
diff --git a/ml/dlib/python_examples/train_object_detector.py b/ml/dlib/python_examples/train_object_detector.py
new file mode 100755
index 00000000..aef3fe16
--- /dev/null
+++ b/ml/dlib/python_examples/train_object_detector.py
@@ -0,0 +1,183 @@
+#!/usr/bin/python
+# The contents of this file are in the public domain. See LICENSE_FOR_EXAMPLE_PROGRAMS.txt
+#
+# This example program shows how you can use dlib to make a HOG based object
+# detector for things like faces, pedestrians, and any other semi-rigid
+# object. In particular, we go though the steps to train the kind of sliding
+# window object detector first published by Dalal and Triggs in 2005 in the
+# paper Histograms of Oriented Gradients for Human Detection.
+#
+#
+# COMPILING/INSTALLING THE DLIB PYTHON INTERFACE
+# You can install dlib using the command:
+# pip install dlib
+#
+# Alternatively, if you want to compile dlib yourself then go into the dlib
+# root folder and run:
+# python setup.py install
+# or
+# python setup.py install --yes USE_AVX_INSTRUCTIONS
+# if you have a CPU that supports AVX instructions, since this makes some
+# things run faster.
+#
+# Compiling dlib should work on any operating system so long as you have
+# CMake installed. On Ubuntu, this can be done easily by running the
+# command:
+# sudo apt-get install cmake
+#
+# Also note that this example requires scikit-image which can be installed
+# via the command:
+# pip install scikit-image
+# Or downloaded from http://scikit-image.org/download.html.
+
+import os
+import sys
+import glob
+
+import dlib
+from skimage import io
+
+
+# In this example we are going to train a face detector based on the small
+# faces dataset in the examples/faces directory. This means you need to supply
+# the path to this faces folder as a command line argument so we will know
+# where it is.
+if len(sys.argv) != 2:
+ print(
+ "Give the path to the examples/faces directory as the argument to this "
+ "program. For example, if you are in the python_examples folder then "
+ "execute this program by running:\n"
+ " ./train_object_detector.py ../examples/faces")
+ exit()
+faces_folder = sys.argv[1]
+
+
+# Now let's do the training. The train_simple_object_detector() function has a
+# bunch of options, all of which come with reasonable default values. The next
+# few lines goes over some of these options.
+options = dlib.simple_object_detector_training_options()
+# Since faces are left/right symmetric we can tell the trainer to train a
+# symmetric detector. This helps it get the most value out of the training
+# data.
+options.add_left_right_image_flips = True
+# The trainer is a kind of support vector machine and therefore has the usual
+# SVM C parameter. In general, a bigger C encourages it to fit the training
+# data better but might lead to overfitting. You must find the best C value
+# empirically by checking how well the trained detector works on a test set of
+# images you haven't trained on. Don't just leave the value set at 5. Try a
+# few different C values and see what works best for your data.
+options.C = 5
+# Tell the code how many CPU cores your computer has for the fastest training.
+options.num_threads = 4
+options.be_verbose = True
+
+
+training_xml_path = os.path.join(faces_folder, "training.xml")
+testing_xml_path = os.path.join(faces_folder, "testing.xml")
+# This function does the actual training. It will save the final detector to
+# detector.svm. The input is an XML file that lists the images in the training
+# dataset and also contains the positions of the face boxes. To create your
+# own XML files you can use the imglab tool which can be found in the
+# tools/imglab folder. It is a simple graphical tool for labeling objects in
+# images with boxes. To see how to use it read the tools/imglab/README.txt
+# file. But for this example, we just use the training.xml file included with
+# dlib.
+dlib.train_simple_object_detector(training_xml_path, "detector.svm", options)
+
+
+
+# Now that we have a face detector we can test it. The first statement tests
+# it on the training data. It will print(the precision, recall, and then)
+# average precision.
+print("") # Print blank line to create gap from previous output
+print("Training accuracy: {}".format(
+ dlib.test_simple_object_detector(training_xml_path, "detector.svm")))
+# However, to get an idea if it really worked without overfitting we need to
+# run it on images it wasn't trained on. The next line does this. Happily, we
+# see that the object detector works perfectly on the testing images.
+print("Testing accuracy: {}".format(
+ dlib.test_simple_object_detector(testing_xml_path, "detector.svm")))
+
+
+
+
+
+# Now let's use the detector as you would in a normal application. First we
+# will load it from disk.
+detector = dlib.simple_object_detector("detector.svm")
+
+# We can look at the HOG filter we learned. It should look like a face. Neat!
+win_det = dlib.image_window()
+win_det.set_image(detector)
+
+# Now let's run the detector over the images in the faces folder and display the
+# results.
+print("Showing detections on the images in the faces folder...")
+win = dlib.image_window()
+for f in glob.glob(os.path.join(faces_folder, "*.jpg")):
+ print("Processing file: {}".format(f))
+ img = io.imread(f)
+ dets = detector(img)
+ print("Number of faces detected: {}".format(len(dets)))
+ for k, d in enumerate(dets):
+ print("Detection {}: Left: {} Top: {} Right: {} Bottom: {}".format(
+ k, d.left(), d.top(), d.right(), d.bottom()))
+
+ win.clear_overlay()
+ win.set_image(img)
+ win.add_overlay(dets)
+ dlib.hit_enter_to_continue()
+
+
+
+
+# Next, suppose you have trained multiple detectors and you want to run them
+# efficiently as a group. You can do this as follows:
+detector1 = dlib.fhog_object_detector("detector.svm")
+# In this example we load detector.svm again since it's the only one we have on
+# hand. But in general it would be a different detector.
+detector2 = dlib.fhog_object_detector("detector.svm")
+# make a list of all the detectors you wan to run. Here we have 2, but you
+# could have any number.
+detectors = [detector1, detector2]
+image = io.imread(faces_folder + '/2008_002506.jpg');
+[boxes, confidences, detector_idxs] = dlib.fhog_object_detector.run_multiple(detectors, image, upsample_num_times=1, adjust_threshold=0.0)
+for i in range(len(boxes)):
+ print("detector {} found box {} with confidence {}.".format(detector_idxs[i], boxes[i], confidences[i]))
+
+
+
+
+# Finally, note that you don't have to use the XML based input to
+# train_simple_object_detector(). If you have already loaded your training
+# images and bounding boxes for the objects then you can call it as shown
+# below.
+
+# You just need to put your images into a list.
+images = [io.imread(faces_folder + '/2008_002506.jpg'),
+ io.imread(faces_folder + '/2009_004587.jpg')]
+# Then for each image you make a list of rectangles which give the pixel
+# locations of the edges of the boxes.
+boxes_img1 = ([dlib.rectangle(left=329, top=78, right=437, bottom=186),
+ dlib.rectangle(left=224, top=95, right=314, bottom=185),
+ dlib.rectangle(left=125, top=65, right=214, bottom=155)])
+boxes_img2 = ([dlib.rectangle(left=154, top=46, right=228, bottom=121),
+ dlib.rectangle(left=266, top=280, right=328, bottom=342)])
+# And then you aggregate those lists of boxes into one big list and then call
+# train_simple_object_detector().
+boxes = [boxes_img1, boxes_img2]
+
+detector2 = dlib.train_simple_object_detector(images, boxes, options)
+# We could save this detector to disk by uncommenting the following.
+#detector2.save('detector2.svm')
+
+# Now let's look at its HOG filter!
+win_det.set_image(detector2)
+dlib.hit_enter_to_continue()
+
+# Note that you don't have to use the XML based input to
+# test_simple_object_detector(). If you have already loaded your training
+# images and bounding boxes for the objects then you can call it as shown
+# below.
+print("\nTraining accuracy: {}".format(
+ dlib.test_simple_object_detector(images, boxes, detector2)))
diff --git a/ml/dlib/python_examples/train_shape_predictor.py b/ml/dlib/python_examples/train_shape_predictor.py
new file mode 100755
index 00000000..23758b2c
--- /dev/null
+++ b/ml/dlib/python_examples/train_shape_predictor.py
@@ -0,0 +1,135 @@
+#!/usr/bin/python
+# The contents of this file are in the public domain. See LICENSE_FOR_EXAMPLE_PROGRAMS.txt
+#
+# This example program shows how to use dlib's implementation of the paper:
+# One Millisecond Face Alignment with an Ensemble of Regression Trees by
+# Vahid Kazemi and Josephine Sullivan, CVPR 2014
+#
+# In particular, we will train a face landmarking model based on a small
+# dataset and then evaluate it. If you want to visualize the output of the
+# trained model on some images then you can run the
+# face_landmark_detection.py example program with predictor.dat as the input
+# model.
+#
+# It should also be noted that this kind of model, while often used for face
+# landmarking, is quite general and can be used for a variety of shape
+# prediction tasks. But here we demonstrate it only on a simple face
+# landmarking task.
+#
+# COMPILING/INSTALLING THE DLIB PYTHON INTERFACE
+# You can install dlib using the command:
+# pip install dlib
+#
+# Alternatively, if you want to compile dlib yourself then go into the dlib
+# root folder and run:
+# python setup.py install
+# or
+# python setup.py install --yes USE_AVX_INSTRUCTIONS
+# if you have a CPU that supports AVX instructions, since this makes some
+# things run faster.
+#
+# Compiling dlib should work on any operating system so long as you have
+# CMake installed. On Ubuntu, this can be done easily by running the
+# command:
+# sudo apt-get install cmake
+#
+# Also note that this example requires scikit-image which can be installed
+# via the command:
+# pip install scikit-image
+# Or downloaded from http://scikit-image.org/download.html.
+
+import os
+import sys
+import glob
+
+import dlib
+from skimage import io
+
+
+# In this example we are going to train a face detector based on the small
+# faces dataset in the examples/faces directory. This means you need to supply
+# the path to this faces folder as a command line argument so we will know
+# where it is.
+if len(sys.argv) != 2:
+ print(
+ "Give the path to the examples/faces directory as the argument to this "
+ "program. For example, if you are in the python_examples folder then "
+ "execute this program by running:\n"
+ " ./train_shape_predictor.py ../examples/faces")
+ exit()
+faces_folder = sys.argv[1]
+
+options = dlib.shape_predictor_training_options()
+# Now make the object responsible for training the model.
+# This algorithm has a bunch of parameters you can mess with. The
+# documentation for the shape_predictor_trainer explains all of them.
+# You should also read Kazemi's paper which explains all the parameters
+# in great detail. However, here I'm just setting three of them
+# differently than their default values. I'm doing this because we
+# have a very small dataset. In particular, setting the oversampling
+# to a high amount (300) effectively boosts the training set size, so
+# that helps this example.
+options.oversampling_amount = 300
+# I'm also reducing the capacity of the model by explicitly increasing
+# the regularization (making nu smaller) and by using trees with
+# smaller depths.
+options.nu = 0.05
+options.tree_depth = 2
+options.be_verbose = True
+
+# dlib.train_shape_predictor() does the actual training. It will save the
+# final predictor to predictor.dat. The input is an XML file that lists the
+# images in the training dataset and also contains the positions of the face
+# parts.
+training_xml_path = os.path.join(faces_folder, "training_with_face_landmarks.xml")
+dlib.train_shape_predictor(training_xml_path, "predictor.dat", options)
+
+# Now that we have a model we can test it. dlib.test_shape_predictor()
+# measures the average distance between a face landmark output by the
+# shape_predictor and where it should be according to the truth data.
+print("\nTraining accuracy: {}".format(
+ dlib.test_shape_predictor(training_xml_path, "predictor.dat")))
+# The real test is to see how well it does on data it wasn't trained on. We
+# trained it on a very small dataset so the accuracy is not extremely high, but
+# it's still doing quite good. Moreover, if you train it on one of the large
+# face landmarking datasets you will obtain state-of-the-art results, as shown
+# in the Kazemi paper.
+testing_xml_path = os.path.join(faces_folder, "testing_with_face_landmarks.xml")
+print("Testing accuracy: {}".format(
+ dlib.test_shape_predictor(testing_xml_path, "predictor.dat")))
+
+# Now let's use it as you would in a normal application. First we will load it
+# from disk. We also need to load a face detector to provide the initial
+# estimate of the facial location.
+predictor = dlib.shape_predictor("predictor.dat")
+detector = dlib.get_frontal_face_detector()
+
+# Now let's run the detector and shape_predictor over the images in the faces
+# folder and display the results.
+print("Showing detections and predictions on the images in the faces folder...")
+win = dlib.image_window()
+for f in glob.glob(os.path.join(faces_folder, "*.jpg")):
+ print("Processing file: {}".format(f))
+ img = io.imread(f)
+
+ win.clear_overlay()
+ win.set_image(img)
+
+ # Ask the detector to find the bounding boxes of each face. The 1 in the
+ # second argument indicates that we should upsample the image 1 time. This
+ # will make everything bigger and allow us to detect more faces.
+ dets = detector(img, 1)
+ print("Number of faces detected: {}".format(len(dets)))
+ for k, d in enumerate(dets):
+ print("Detection {}: Left: {} Top: {} Right: {} Bottom: {}".format(
+ k, d.left(), d.top(), d.right(), d.bottom()))
+ # Get the landmarks/parts for the face in box d.
+ shape = predictor(img, d)
+ print("Part 0: {}, Part 1: {} ...".format(shape.part(0),
+ shape.part(1)))
+ # Draw the face landmarks on the screen.
+ win.add_overlay(shape)
+
+ win.add_overlay(dets)
+ dlib.hit_enter_to_continue()
+