def compile(name,
model: Sequential,
train_samples: pd.DataFrame,
validation_samples: pd.DataFrame,
gen,
type='img'):
# model.add(Reshape((-1, num_classes), name=RESHAPED))
size = 5
steps_per_epoch = len(train_samples) // size
validation_steps = len(validation_samples) // size
train_generator = gen(train_samples, type)(size, infinite=True)
validation_generator = gen(validation_samples, type)(size, infinite=True)
adam = optimizers.Adam(lr=0.0001)
model.compile(loss='categorical_crossentropy', optimizer=adam)
history_object = model.fit_generator(train_generator,
validation_data=validation_generator,
epochs=5,
callbacks=None,
validation_steps=validation_steps,
steps_per_epoch=steps_per_epoch)
model.save_weights(name)
# model.save('fcn_model.h5')
print(history_object.history.keys())
print('Loss')
print(history_object.history['loss'])
print('Validation Loss')
print(history_object.history['val_loss'])
"""
If you need to load weights into a *different* architecture (with some layers in common), for instance for fine-tuning or transfer-learning, you can load weights by *layer name*:
"""
model_yaml.load_weights('to_delete_weights.h5', by_name=True)
# make sure they share the same weights: total 202 parameters
(model_json.get_weights()[0] == model_yaml.get_weights()[0]).sum()
(model_json.get_weights()[1] == model_yaml.get_weights()[1]).sum()
"""
For example
Assume original model looks like this:
"""
model1 = Sequential()
model1.add(Dense(2, input_dim=3, name='dense_1'))
model1.add(Dense(3, name='dense_2'))
model1.save_weights("weights1.h5")
# check out the weights
model1.get_weights()
# new model
model2 = Sequential()
model2.add(Dense(2, input_dim=3, name='dense_1')) # will be loaded
model2.add(Dense(10, name='new_dense')) # will not be loaded
# load weights from first model; will only affect the first layer, dense_1.
model2.load_weights("weights1.h5", by_name=True)
# check out the weights
model2.get_weights()
#validation_split=0.2 - 20% for validation set
predictions = model.predict(X_train)
#convert output data to a single number
predictions = np_utils.categorical_probas_to_classes(predictions)
score = model.evaluate(X_test, y_test, verbose=0)
print('Accurate: ', score[1] * 100)
##############
model = Sequential()
model.add(Dense(800, input_dim=784, init="normal", activation='relu'))
model.add(Dense(10, init="normal", activation='softmax'))
model_json = model.to_json()
json_file = open('model.json', 'w')
json_file.write(model_json)
json_file.close()
model.save_weights("weighst.h5")
json_file = open('model.json', 'r')
loaded_model_json = json_file.read()
json_file.close()
loaded_model = model_from_json(loaded_model_json)
loaded_model.load_weights('weighst.h5')
loaded_model.compile(loss="categorical_crossentropy",
optimizer="SGD",
metrics=["accuracy"])