def __init__(self):
goods_dataset = GoodsDataset("dataset-181018.list",
"dataset-181018.labels",
settings.IMAGE_SIZE, settings.train_batch,
settings.valid_batch, settings.multiply,
settings.valid_percentage)
train_set = goods_dataset.get_train_dataset()
valid_set = goods_dataset.get_valid_dataset()
input_tensor = keras.layers.Input(shape=(IMAGE_SIZE[0], IMAGE_SIZE[1],
3))
base_model = InceptionV3(weights='imagenet',
include_top=False,
pooling='avg',
input_tensor=input_tensor)
output_layer_number = 248
intermediate_layer_model = keras.Model(
inputs=base_model.input,
outputs=base_model.layers[output_layer_number].output)
def _intermediate_processing(images, labels):
images = intermediate_layer_model.predict(images, steps=77)
return images, labels
self.train_set = train_set.map(
_intermediate_processing) #, num_parallel_calls=8)
self.valid_set = valid_set.map(
_intermediate_processing) #, num_parallel_calls=8)
predictions = keras.layers.Dense(settings.num_classes,
activation='softmax')(main_model.output)
new_model = keras.Model(inputs=main_model.input, outputs=predictions)
new_model.compile(optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['accuracy', top_6])
session = keras.backend.get_session()
print(new_model.summary())
for i in range(0, len(base_model.layers)):
new_model.layers[i + 248].set_weights(base_model.layers[i].get_weights())
print("new model inputs")
for node in new_model.inputs:
print(node.op.name)
print("new model outputs")
for node in new_model.outputs:
print(node.op.name)
dataset = GoodsDataset("dataset-181018.list", "dataset-181018.labels",
(IMAGE_SIZE[0], IMAGE_SIZE[1]), 32, 32, 5, 0.1)
results = new_model.evaluate(dataset.get_valid_dataset(), steps=77)
print(results)
new_model.save("output/inception_{0}.hdf5".format(model_name))
"./checkpoints/FINE_TUNE_MODEL_4_DIRECT_inceptionv3-181018-{epoch:02d}-{acc:.3f}-{val_acc:.3f}[{val_top_6:.3f}].hdf5",
save_best_only=True,
monitor='val_top_6',
mode='max'),
keras.callbacks.TensorBoard(
log_dir='./tensorboard-incv4',
write_images=True,
)
]
goods_dataset = GoodsDataset("dataset-181018.list", "dataset-181018.labels",
settings.IMAGE_SIZE, settings.train_batch,
settings.valid_batch, settings.multiply,
settings.valid_percentage)
train_dataset = goods_dataset.get_train_dataset()
valid_dataset = goods_dataset.get_valid_dataset()
results = model.evaluate(
goods_dataset.get_images_for_label(94).batch(16).repeat(), steps=6)
print(results)
model.fit(
train_dataset.prefetch(2).repeat(),
callbacks=callbacks,
epochs=30,
steps_per_epoch=1157,
validation_data=valid_dataset.repeat(),
validation_steps=77,
)
"""
1) num_last_trainable_layers = 60
# strategy = tf.contrib.distribute.MirroredStrategy()
# config = tf.estimator.RunConfig(train_distribute=strategy)
# keras_estimator = keras.estimator.model_to_estimator(
# keras_model=model,
# config=config,
# model_dir='/tmp/model_dir')
# keras_estimator.train(input_fn=goods_dataset.get_train_dataset, steps=10)
model.fit(
goods_dataset.get_train_dataset(),
callbacks=callbacks,
epochs=60,
steps_per_epoch=800, # 20 * 21 * 155 = 65100 < 13174 * 5 = 65870
validation_data=goods_dataset.get_valid_dataset().repeat(),
validation_steps=80)
session = keras.backend.get_session()
gr = session.graph.as_graph_def()
# for n in gr.node:
# print(n.name)
# model.save_weights('./checkpoints/{}'.format(OUTPUT_MODEL_NAME))
# for n in keras.backend.get_session().graph.as_graph_def().node:
# print(n.name)
frozen_graph = freeze_session(
keras.backend.get_session(),
output_names=[out.op.name for out in model.outputs])