[Python] Increasing the size of the model

Recently I trained two MLP model and saved weights for future work. I develop one module for loading model and use these model in another module.

Load model module contain this code to load models:

def creat_model_extractor(model_path, feature_count):
"""
This function create model and set weights
aram model_path: address of weights files
aram feature_count: Number of nodes in input layer
"""
try:
tf.keras.backend.clear_session()
node_list = [1024, 512, 256, 128, 64, 32]

model = Sequential()
model.add(Input(shape=(feature_count,)))

for node in node_list:
model.add(Dense(node, activation='relu'))
model.add(Dropout(0.2))
model.add(LayerNormalization())

model.add(Dense(16, activation='relu'))
model.add(LayerNormalization())
model.add(Dense(1, activation='sigmoid'))

@tf.function
def inference_step(inputs):
return tf.stop_gradient(model(inputs, training=False))

model.inference_step = inference_step

model.load_weights(model_path)
model.trainable = False
for layer in model.layers:
layer.trainable = False
except Exception as error:
logger.warning(error, exc_info=True)
return None

return model


And this is predict function

SMALL_MODEL = creat_model_extractor(MODEL_PATH_SMALL, small_blocks_count)

(SMALL_MODEL.inference_step(small_blocks_normal) > 0.5).numpy().astype(int)



Problem: After predict label 'SMALL_MODEL' size change. It become bigger and And after a while, the RAM fills up. What should I do to prevent RAM from filling up?

This problem happen even in one module

Continue reading...