facedetection

June 5, 2024

1 1. Setup and Get Data

1.0.1 1.1 Install Dependencies and Setup

[1]: !pip install labelme tensorflow tensorflow-gpu opencv-python matplotlib␣

↪albumentations

Collecting labelme
Downloading labelme-5.4.1.tar.gz (1.4 MB)
---------------------------------------- 0.0/1.4 MB ? eta -:--:--
--------------------------------------- 0.0/1.4 MB 660.6 kB/s eta 0:00:03
- -------------------------------------- 0.1/1.4 MB 1.1 MB/s eta 0:00:02
------- -------------------------------- 0.3/1.4 MB 2.1 MB/s eta 0:00:01
----------- ---------------------------- 0.4/1.4 MB 2.3 MB/s eta 0:00:01
-------------- ------------------------- 0.5/1.4 MB 2.4 MB/s eta 0:00:01
---------------- ----------------------- 0.6/1.4 MB 2.3 MB/s eta 0:00:01
------------------ --------------------- 0.7/1.4 MB 2.2 MB/s eta 0:00:01
-------------------- ------------------- 0.7/1.4 MB 2.1 MB/s eta 0:00:01
----------------------- ---------------- 0.8/1.4 MB 2.1 MB/s eta 0:00:01
-------------------------- ------------- 0.9/1.4 MB 2.1 MB/s eta 0:00:01
----------------------------- ---------- 1.0/1.4 MB 2.1 MB/s eta 0:00:01
-------------------------------- ------- 1.2/1.4 MB 2.2 MB/s eta 0:00:01
---------------------------------- ----- 1.2/1.4 MB 2.2 MB/s eta 0:00:01
------------------------------------- -- 1.3/1.4 MB 2.1 MB/s eta 0:00:01
---------------------------------------- 1.4/1.4 MB 2.2 MB/s eta 0:00:00
Installing build dependencies: started
Installing build dependencies: finished with status 'done'
Getting requirements to build wheel: started
Getting requirements to build wheel: finished with status 'done'
Installing backend dependencies: started
Installing backend dependencies: finished with status 'done'
Preparing metadata (pyproject.toml): started
Preparing metadata (pyproject.toml): finished with status 'done'
Collecting tensorflow
Downloading tensorflow-2.16.1-cp311-cp311-win_amd64.whl.metadata (3.5 kB)
Collecting tensorflow-gpu
Downloading tensorflow-gpu-2.12.0.tar.gz (2.6 kB)
Installing build dependencies: started

1
 Installing build dependencies: finished with status 'done'
Getting requirements to build wheel: started
Getting requirements to build wheel: finished with status 'error'
error: subprocess-exited-with-error

× Getting requirements to build wheel did not run successfully.

� exit code: 1
��> [58 lines of output]
Traceback (most recent call last):
File "C:\Users\asus\AppData\Local\Temp\pip-build-env-
lugze6ke\overlay\Lib\site-
packages\setuptools\_vendor\packaging\requirements.py", line 35, in __init__
parsed = _parse_requirement(requirement_string)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\asus\AppData\Local\Temp\pip-build-env-
lugze6ke\overlay\Lib\site-packages\setuptools\_vendor\packaging\_parser.py",
line 64, in parse_requirement
return _parse_requirement(Tokenizer(source, rules=DEFAULT_RULES))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\asus\AppData\Local\Temp\pip-build-env-
lugze6ke\overlay\Lib\site-packages\setuptools\_vendor\packaging\_parser.py",
line 82, in _parse_requirement
url, specifier, marker = _parse_requirement_details(tokenizer)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\asus\AppData\Local\Temp\pip-build-env-
lugze6ke\overlay\Lib\site-packages\setuptools\_vendor\packaging\_parser.py",
line 126, in _parse_requirement_details
marker = _parse_requirement_marker(
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\asus\AppData\Local\Temp\pip-build-env-
lugze6ke\overlay\Lib\site-packages\setuptools\_vendor\packaging\_parser.py",
line 147, in _parse_requirement_marker
tokenizer.raise_syntax_error(
File "C:\Users\asus\AppData\Local\Temp\pip-build-env-
lugze6ke\overlay\Lib\site-packages\setuptools\_vendor\packaging\_tokenizer.py",
line 165, in raise_syntax_error
raise ParserSyntaxError(
setuptools.extern.packaging._tokenizer.ParserSyntaxError: Expected end or
semicolon (after name and no valid version specifier)
python_version>"3.7"
^

The above exception was the direct cause of the following exception:

Traceback (most recent call last):

File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.11_
3.11.2544.0_x64__qbz5n2kfra8p0\Lib\site-

2
packages\pip\_vendor\pyproject_hooks\_in_process\_in_process.py", line 353, in
<module>
main()
File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.11_
3.11.2544.0_x64__qbz5n2kfra8p0\Lib\site-
packages\pip\_vendor\pyproject_hooks\_in_process\_in_process.py", line 335, in
main
json_out['return_val'] = hook(**hook_input['kwargs'])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.11_
3.11.2544.0_x64__qbz5n2kfra8p0\Lib\site-
packages\pip\_vendor\pyproject_hooks\_in_process\_in_process.py", line 118, in
get_requires_for_build_wheel
return hook(config_settings)
^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\asus\AppData\Local\Temp\pip-build-env-
lugze6ke\overlay\Lib\site-packages\setuptools\build_meta.py", line 325, in
get_requires_for_build_wheel
return self._get_build_requires(config_settings,
requirements=['wheel'])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\asus\AppData\Local\Temp\pip-build-env-
lugze6ke\overlay\Lib\site-packages\setuptools\build_meta.py", line 295, in
_get_build_requires
self.run_setup()
File "C:\Users\asus\AppData\Local\Temp\pip-build-env-
lugze6ke\overlay\Lib\site-packages\setuptools\build_meta.py", line 487, in
run_setup
super().run_setup(setup_script=setup_script)
File "C:\Users\asus\AppData\Local\Temp\pip-build-env-
lugze6ke\overlay\Lib\site-packages\setuptools\build_meta.py", line 311, in
run_setup
exec(code, locals())
File "<string>", line 40, in <module>
File "C:\Users\asus\AppData\Local\Temp\pip-build-env-
lugze6ke\overlay\Lib\site-packages\setuptools\__init__.py", line 102, in setup
_install_setup_requires(attrs)
File "C:\Users\asus\AppData\Local\Temp\pip-build-env-
lugze6ke\overlay\Lib\site-packages\setuptools\__init__.py", line 73, in
_install_setup_requires
dist.parse_config_files(ignore_option_errors=True)
File "C:\Users\asus\AppData\Local\Temp\pip-build-env-
lugze6ke\overlay\Lib\site-packages\setuptools\dist.py", line 634, in
parse_config_files
self._finalize_requires()
File "C:\Users\asus\AppData\Local\Temp\pip-build-env-
lugze6ke\overlay\Lib\site-packages\setuptools\dist.py", line 368, in
_finalize_requires

3
 self._normalize_requires()
File "C:\Users\asus\AppData\Local\Temp\pip-build-env-
lugze6ke\overlay\Lib\site-packages\setuptools\dist.py", line 383, in
_normalize_requires
self.install_requires = list(map(str, _reqs.parse(install_requires)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\asus\AppData\Local\Temp\pip-build-env-
lugze6ke\overlay\Lib\site-
packages\setuptools\_vendor\packaging\requirements.py", line 37, in __init__
raise InvalidRequirement(str(e)) from e
setuptools.extern.packaging.requirements.InvalidRequirement: Expected end
or semicolon (after name and no valid version specifier)
python_version>"3.7"
^
[end of output]

note: This error originates from a subprocess, and is likely not a problem
with pip.
error: subprocess-exited-with-error

× Getting requirements to build wheel did not run successfully.

� exit code: 1
��> See above for output.

note: This error originates from a subprocess, and is likely not a problem with
pip.

1.0.2 1.2 Collect Images Using OpenCV

[ ]: import os
import time
import uuid
import cv2

[ ]: IMAGES_PATH = os.path.join('data','images')
number_images = 30

[ ]: cap = cv2.VideoCapture(1)
for imgnum in range(number_images):
print('Collecting image {}'.format(imgnum))
ret, frame = cap.read()
imgname = os.path.join(IMAGES_PATH,f'{str(uuid.uuid1())}.jpg')
cv2.imwrite(imgname, frame)
cv2.imshow('frame', frame)
time.sleep(0.5)

if cv2.waitKey(1) & 0xFF == ord('q'):

4
 break
cap.release()
cv2.destroyAllWindows()

1.0.3 1.3 Annotate Images with LabelMe

[ ]: !labelme

2 2. Review Dataset and Build Image Loading Function

2.0.1 2.1 Import TF and Deps

[ ]: import tensorflow as tf
import json
import numpy as np
from matplotlib import pyplot as plt

2.0.2 2.2 Limit GPU Memory Growth

[ ]: # Avoid OOM errors by setting GPU Memory Consumption Growth

gpus = tf.config.experimental.list_physical_devices('GPU')
for gpu in gpus:
tf.config.experimental.set_memory_growth(gpu, True)

[ ]: tf.config.list_physical_devices('GPU')

2.0.3 2.3 Load Image into TF Data Pipeline

[ ]: images = tf.data.Dataset.list_files('data\\images\\*.jpg')

[ ]: images.as_numpy_iterator().next()

[ ]: def load_image(x):
byte_img = tf.io.read_file(x)
img = tf.io.decode_jpeg(byte_img)
return img

[ ]: images = images.map(load_image)

[ ]: images.as_numpy_iterator().next()

[ ]: type(images)

5
 2.0.4 2.4 View Raw Images with Matplotlib

[ ]: image_generator = images.batch(4).as_numpy_iterator()

[ ]: plot_images = image_generator.next()

[ ]: fig, ax = plt.subplots(ncols=4, figsize=(20,20))

for idx, image in enumerate(plot_images):
ax[idx].imshow(image)
plt.show()

3 3. Partition Unaugmented Data

3.0.1 3.1 MANUALLY SPLT DATA INTO TRAIN TEST AND VAL
[ ]: 90*.7 # 63 to train

[ ]: 90*.15 # 14 and 13 to test and val

3.0.2 3.2 Move the Matching Labels

[ ]: for folder in ['train','test','val']:

for file in os.listdir(os.path.join('data', folder, 'images')):

filename = file.split('.')[0]+'.json'
existing_filepath = os.path.join('data','labels', filename)
if os.path.exists(existing_filepath):
new_filepath = os.path.join('data',folder,'labels',filename)
os.replace(existing_filepath, new_filepath)

4 4. Apply Image Augmentation on Images and Labels using Al-

bumentations
4.0.1 4.1 Setup Albumentations Transform Pipeline

[ ]: import albumentations as alb

[ ]: augmentor = alb.Compose([alb.RandomCrop(width=450, height=450),

alb.HorizontalFlip(p=0.5),
alb.RandomBrightnessContrast(p=0.2),
alb.RandomGamma(p=0.2),
alb.RGBShift(p=0.2),
alb.VerticalFlip(p=0.5)],
bbox_params=alb.BboxParams(format='albumentations',
␣
↪label_fields=['class_labels']))

6
 4.0.2 4.2 Load a Test Image and Annotation with OpenCV and JSON

[ ]: img = cv2.imread(os.path.join('data','train',␣
↪'images','ffd85fc5-cc1a-11ec-bfb8-a0cec8d2d278.jpg'))

[ ]: with open(os.path.join('data', 'train', 'labels',␣

↪'ffd85fc5-cc1a-11ec-bfb8-a0cec8d2d278.json'), 'r') as f:

label = json.load(f)

[ ]: label['shapes'][0]['points']

4.0.3 4.3 Extract Coordinates and Rescale to Match Image Resolution

[ ]: coords = [0,0,0,0]
coords[0] = label['shapes'][0]['points'][0][0]
coords[1] = label['shapes'][0]['points'][0][1]
coords[2] = label['shapes'][0]['points'][1][0]
coords[3] = label['shapes'][0]['points'][1][1]

[ ]: coords

[ ]: coords = list(np.divide(coords, [640,480,640,480]))

[ ]: coords

4.0.4 4.4 Apply Augmentations and View Results

[ ]: augmented = augmentor(image=img, bboxes=[coords], class_labels=['face'])

[ ]: augmented['bboxes'][0][2:]

[ ]: augmented['bboxes']

[ ]: cv2.rectangle(augmented['image'],
tuple(np.multiply(augmented['bboxes'][0][:2], [450,450]).
↪astype(int)),

tuple(np.multiply(augmented['bboxes'][0][2:], [450,450]).
↪astype(int)),

(255,0,0), 2)

plt.imshow(augmented['image'])

7
 5 5. Build and Run Augmentation Pipeline
5.0.1 5.1 Run Augmentation Pipeline
[ ]: for partition in ['train','test','val']:
for image in os.listdir(os.path.join('data', partition, 'images')):
img = cv2.imread(os.path.join('data', partition, 'images', image))

coords = [0,0,0.00001,0.00001]
label_path = os.path.join('data', partition, 'labels', f'{image.split(".
↪")[0]}.json')

if os.path.exists(label_path):
with open(label_path, 'r') as f:
label = json.load(f)

coords[0] = label['shapes'][0]['points'][0][0]
coords[1] = label['shapes'][0]['points'][0][1]
coords[2] = label['shapes'][0]['points'][1][0]
coords[3] = label['shapes'][0]['points'][1][1]
coords = list(np.divide(coords, [640,480,640,480]))

try:
for x in range(60):
augmented = augmentor(image=img, bboxes=[coords],␣
↪class_labels=['face'])

cv2.imwrite(os.path.join('aug_data', partition, 'images',␣

↪f'{image.split(".")[0]}.{x}.jpg'), augmented['image'])

annotation = {}
annotation['image'] = image

if os.path.exists(label_path):
if len(augmented['bboxes']) == 0:
annotation['bbox'] = [0,0,0,0]
annotation['class'] = 0
else:
annotation['bbox'] = augmented['bboxes'][0]
annotation['class'] = 1
else:
annotation['bbox'] = [0,0,0,0]
annotation['class'] = 0

with open(os.path.join('aug_data', partition, 'labels',␣

↪f'{image.split(".")[0]}.{x}.json'), 'w') as f:
json.dump(annotation, f)

8
 except Exception as e:
print(e)

5.0.2 5.2 Load Augmented Images to Tensorflow Dataset

[ ]: train_images = tf.data.Dataset.list_files('aug_data\\train\\images\\*.jpg',␣
↪shuffle=False)

train_images = train_images.map(load_image)
train_images = train_images.map(lambda x: tf.image.resize(x, (120,120)))
train_images = train_images.map(lambda x: x/255)

[ ]: test_images = tf.data.Dataset.list_files('aug_data\\test\\images\\*.jpg',␣
↪shuffle=False)

test_images = test_images.map(load_image)
test_images = test_images.map(lambda x: tf.image.resize(x, (120,120)))
test_images = test_images.map(lambda x: x/255)

[ ]: val_images = tf.data.Dataset.list_files('aug_data\\val\\images\\*.jpg',␣
↪shuffle=False)

val_images = val_images.map(load_image)
val_images = val_images.map(lambda x: tf.image.resize(x, (120,120)))
val_images = val_images.map(lambda x: x/255)

[ ]: train_images.as_numpy_iterator().next()

6 6. Prepare Labels
6.0.1 6.1 Build Label Loading Function

[ ]: def load_labels(label_path):
with open(label_path.numpy(), 'r', encoding = "utf-8") as f:
label = json.load(f)

return [label['class']], label['bbox']

6.0.2 6.2 Load Labels to Tensorflow Dataset

[ ]: train_labels = tf.data.Dataset.list_files('aug_data\\train\\labels\\*.json',␣
↪shuffle=False)

train_labels = train_labels.map(lambda x: tf.py_function(load_labels, [x], [tf.

↪uint8, tf.float16]))

[ ]: test_labels = tf.data.Dataset.list_files('aug_data\\test\\labels\\*.json',␣
↪shuffle=False)

9
 test_labels = test_labels.map(lambda x: tf.py_function(load_labels, [x], [tf.
↪uint8, tf.float16]))

[ ]: val_labels = tf.data.Dataset.list_files('aug_data\\val\\labels\\*.json',␣
↪shuffle=False)

val_labels = val_labels.map(lambda x: tf.py_function(load_labels, [x], [tf.

↪uint8, tf.float16]))

[ ]: train_labels.as_numpy_iterator().next()

7 7. Combine Label and Image Samples

7.0.1 7.1 Check Partition Lengths

[ ]: len(train_images), len(train_labels), len(test_images), len(test_labels),␣

↪len(val_images), len(val_labels)

7.0.2 7.2 Create Final Datasets (Images/Labels)

[ ]: train = tf.data.Dataset.zip((train_images, train_labels))

train = train.shuffle(5000)
train = train.batch(8)
train = train.prefetch(4)

[ ]: test = tf.data.Dataset.zip((test_images, test_labels))

test = test.shuffle(1300)
test = test.batch(8)
test = test.prefetch(4)

[ ]: val = tf.data.Dataset.zip((val_images, val_labels))

val = val.shuffle(1000)
val = val.batch(8)
val = val.prefetch(4)

[ ]: train.as_numpy_iterator().next()[1]

7.0.3 7.3 View Images and Annotations

[ ]: data_samples = train.as_numpy_iterator()

[ ]: res = data_samples.next()

[ ]: fig, ax = plt.subplots(ncols=4, figsize=(20,20))

for idx in range(4):
sample_image = res[0][idx]

10
 sample_coords = res[1][1][idx]

cv2.rectangle(sample_image,
tuple(np.multiply(sample_coords[:2], [120,120]).astype(int)),
tuple(np.multiply(sample_coords[2:], [120,120]).astype(int)),
(255,0,0), 2)

ax[idx].imshow(sample_image)

8 8. Build Deep Learning using the Functional API

8.0.1 8.1 Import Layers and Base Network

[ ]: from tensorflow.keras.models import Model

from tensorflow.keras.layers import Input, Conv2D, Dense, GlobalMaxPooling2D
from tensorflow.keras.applications import VGG16

8.0.2 8.2 Download VGG16

[ ]: vgg = VGG16(include_top=False)

[ ]: vgg.summary()

8.0.3 8.3 Build instance of Network

[ ]: def build_model():
input_layer = Input(shape=(120,120,3))

vgg = VGG16(include_top=False)(input_layer)

# Classification Model
f1 = GlobalMaxPooling2D()(vgg)
class1 = Dense(2048, activation='relu')(f1)
class2 = Dense(1, activation='sigmoid')(class1)

# Bounding box model

f2 = GlobalMaxPooling2D()(vgg)
regress1 = Dense(2048, activation='relu')(f2)
regress2 = Dense(4, activation='sigmoid')(regress1)

facetracker = Model(inputs=input_layer, outputs=[class2, regress2])

return facetracker

11
 8.0.4 8.4 Test out Neural Network
[ ]: facetracker = build_model()

[ ]: facetracker.summary()

[ ]: X, y = train.as_numpy_iterator().next()

[ ]: X.shape

[ ]: classes, coords = facetracker.predict(X)

[ ]: classes, coords

9 9. Define Losses and Optimizers

9.0.1 9.1 Define Optimizer and LR

[ ]: batches_per_epoch = len(train)
lr_decay = (1./0.75 -1)/batches_per_epoch

[ ]: opt = tf.keras.optimizers.Adam(learning_rate=0.0001, decay=lr_decay)

9.0.2 9.2 Create Localization Loss and Classification Loss

[ ]: def localization_loss(y_true, yhat):
delta_coord = tf.reduce_sum(tf.square(y_true[:,:2] - yhat[:,:2]))

h_true = y_true[:,3] - y_true[:,1]

w_true = y_true[:,2] - y_true[:,0]

h_pred = yhat[:,3] - yhat[:,1]

w_pred = yhat[:,2] - yhat[:,0]

delta_size = tf.reduce_sum(tf.square(w_true - w_pred) + tf.

↪square(h_true-h_pred))

return delta_coord + delta_size

[ ]: classloss = tf.keras.losses.BinaryCrossentropy()
regressloss = localization_loss

9.0.3 9.3 Test out Loss Metrics

[ ]: localization_loss(y[1], coords)

12
[ ]: classloss(y[0], classes)

[ ]: regressloss(y[1], coords)

10 10. Train Neural Network

10.0.1 10.1 Create Custom Model Class
[ ]: class FaceTracker(Model):
def __init__(self, eyetracker, **kwargs):
super().__init__(**kwargs)
self.model = eyetracker

def compile(self, opt, classloss, localizationloss, **kwargs):

super().compile(**kwargs)
self.closs = classloss
self.lloss = localizationloss
self.opt = opt

def train_step(self, batch, **kwargs):

X, y = batch

with tf.GradientTape() as tape:

classes, coords = self.model(X, training=True)

batch_classloss = self.closs(y[0], classes)

batch_localizationloss = self.lloss(tf.cast(y[1], tf.float32),␣
↪coords)

total_loss = batch_localizationloss+0.5*batch_classloss

grad = tape.gradient(total_loss, self.model.trainable_variables)

opt.apply_gradients(zip(grad, self.model.trainable_variables))

return {"total_loss":total_loss, "class_loss":batch_classloss,␣

↪"regress_loss":batch_localizationloss}

def test_step(self, batch, **kwargs):

X, y = batch

classes, coords = self.model(X, training=False)

batch_classloss = self.closs(y[0], classes)

batch_localizationloss = self.lloss(tf.cast(y[1], tf.float32), coords)

13
 total_loss = batch_localizationloss+0.5*batch_classloss

return {"total_loss":total_loss, "class_loss":batch_classloss,␣

↪"regress_loss":batch_localizationloss}

def call(self, X, **kwargs):

return self.model(X, **kwargs)

[ ]: model = FaceTracker(facetracker)

[ ]: model.compile(opt, classloss, regressloss)

10.0.2 10.2 Train

[ ]: logdir='logs'

[ ]: tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=logdir)

[ ]: hist = model.fit(train, epochs=10, validation_data=val,␣

↪callbacks=[tensorboard_callback])

10.0.3 10.3 Plot Performance

[ ]: hist.history

[ ]: fig, ax = plt.subplots(ncols=3, figsize=(20,5))

ax[0].plot(hist.history['total_loss'], color='teal', label='loss')

ax[0].plot(hist.history['val_total_loss'], color='orange', label='val loss')
ax[0].title.set_text('Loss')
ax[0].legend()

ax[1].plot(hist.history['class_loss'], color='teal', label='class loss')

ax[1].plot(hist.history['val_class_loss'], color='orange', label='val class␣
↪loss')

ax[1].title.set_text('Classification Loss')
ax[1].legend()

ax[2].plot(hist.history['regress_loss'], color='teal', label='regress loss')

ax[2].plot(hist.history['val_regress_loss'], color='orange', label='val regress␣
↪loss')

ax[2].title.set_text('Regression Loss')
ax[2].legend()

plt.show()

14
 11 11. Make Predictions
11.0.1 11.1 Make Predictions on Test Set
[ ]: test_data = test.as_numpy_iterator()

[ ]: test_sample = test_data.next()

[ ]: yhat = facetracker.predict(test_sample[0])

[ ]: fig, ax = plt.subplots(ncols=4, figsize=(20,20))

for idx in range(4):
sample_image = test_sample[0][idx]
sample_coords = yhat[1][idx]

if yhat[0][idx] > 0.9:

cv2.rectangle(sample_image,
tuple(np.multiply(sample_coords[:2], [120,120]).
↪astype(int)),

tuple(np.multiply(sample_coords[2:], [120,120]).
↪astype(int)),

(255,0,0), 2)

ax[idx].imshow(sample_image)

11.0.2 11.2 Save the Model

[ ]: from tensorflow.keras.models import load_model

[ ]: facetracker.save('facetracker.h5')

[ ]: facetracker = load_model('facetracker.h5')

11.0.3 11.3 Real Time Detection

[ ]: cap = cv2.VideoCapture(1)
while cap.isOpened():
_ , frame = cap.read()
frame = frame[50:500, 50:500,:]

rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)

resized = tf.image.resize(rgb, (120,120))

yhat = facetracker.predict(np.expand_dims(resized/255,0))
sample_coords = yhat[1][0]

if yhat[0] > 0.5:

15
 # Controls the main rectangle
cv2.rectangle(frame,
tuple(np.multiply(sample_coords[:2], [450,450]).
↪astype(int)),

tuple(np.multiply(sample_coords[2:], [450,450]).
↪astype(int)),

(255,0,0), 2)
# Controls the label rectangle
cv2.rectangle(frame,
tuple(np.add(np.multiply(sample_coords[:2], [450,450]).
↪astype(int),

[0,-30])),
tuple(np.add(np.multiply(sample_coords[:2], [450,450]).
↪astype(int),

[80,0])),
(255,0,0), -1)

# Controls the text rendered

cv2.putText(frame, 'face', tuple(np.add(np.multiply(sample_coords[:2],␣
↪[450,450]).astype(int),

[0,-5])),
cv2.FONT_HERSHEY_SIMPLEX, 1, (255,255,255), 2, cv2.LINE_AA)

cv2.imshow('EyeTrack', frame)

if cv2.waitKey(1) & 0xFF == ord('q'):

break
cap.release()
cv2.destroyAllWindows()

[ ]:

16