def main():
model = create_model()
model.load_weights(WEIGHTS_FILE)
for filename in glob.glob(IMAGES):
unscaled = cv2.imread(filename)
image_height, image_width, _ = unscaled.shape
image = cv2.resize(unscaled, (IMAGE_SIZE, IMAGE_SIZE))
feat_scaled = preprocess_input(np.array(image, dtype=np.float32))
region, class_id = model.predict(x=np.array([image]))
region = region[0]
x0 = int(region[0] * image_width / IMAGE_SIZE)
y0 = int(region[1] * image_height / IMAGE_SIZE)
x1 = int((region[0] + region[2]) * image_width / IMAGE_SIZE)
y1 = int((region[1] + region[3]) * image_height / IMAGE_SIZE)
class_id = np.argmax(class_id, axis=1)[0]
cv2.rectangle(unscaled, (x0, y0), (x1, y1), (0, 0, 255), 1)
cv2.putText(unscaled, "class: {}".format(class_names[class_id]), (x0, y0), cv2.FONT_HERSHEY_SIMPLEX, 1, (255,255,255), 2, cv2.LINE_AA)
cv2.imshow("image", unscaled)
cv2.waitKey(0)
cv2.destroyAllWindows()
def read_model(IMG_SIZE, PATH_TO_MODEL):
# Init model with right architecture
model = create_model(IMG_SIZE, optimizer_param='sgd', depth='dense3')
model.load_weights(PATH_TO_MODEL)
model.compile(loss='categorical_crossentropy',
optimizer='sgd',
metrics=['accuracy'])
return model
def build_mlp(input_size=PATCH_SIZE, phase='TRAIN'):
optimizer_param = 'sgd'
# Create Model
model = create_model(input_size, optimizer_param='sgd', depth='patches')
if phase == 'TEST':
model.add(
Dense(units=8, activation='linear')
) # In test phase we softmax the average output over the image patches
else:
model.add(Dense(units=8, activation='softmax'))
model.compile(loss='categorical_crossentropy',
optimizer=optimizer_param,
metrics=['accuracy'])
return model
from model_definition import create_model
from config import EPOCHS, BATCH_SIZE, keras_model_dir, serving_model_dir
from prepare_data import get_datasets
# GPU settings
gpus = tf.config.experimental.list_physical_devices('GPU')
if gpus:
for gpu in gpus:
tf.config.experimental.set_memory_growth(gpu, True)
train_generator, valid_generator, \
train_num, valid_num, \
class_weights = get_datasets()
# start training
model = create_model()
model.fit_generator(train_generator,
epochs=EPOCHS,
steps_per_epoch=train_num // BATCH_SIZE,
validation_data=valid_generator,
validation_steps=valid_num // BATCH_SIZE,
class_weight=class_weights)
# save the whole keras model
model.save(os.path.join('keras_model', keras_model_dir))
# save saved_model for tensorflow serving
tf.keras.experimental.export_saved_model(
model, os.path.join('saved_model', serving_model_dir))