I am training an image classifier using Large EfficientNet:
base_model = EfficientNetV2L(input_shape = (300, 500, 3),
include_top = False,
weights = 'imagenet',
include_preprocessing = True)
model = tf.keras.Sequential([base_model,
layers.GlobalAveragePooling2D(),
layers.Dropout(0.2),
layers.Dense(128, activation = 'relu'),
layers.Dropout(0.3),
layers.Dense(6, activation = 'softmax')])
base_model.trainable = False
model.compile(optimizer = optimizers.Adam(learning_rate = 0.001),
loss = losses.SparseCategoricalCrossentropy(),
metrics = ['accuracy'])
callback = [callbacks.EarlyStopping(monitor = 'val_loss', patience = 2)]
history = model.fit(ds_train, batch_size = 28, validation_data = ds_val, epochs = 20, verbose = 1, callbacks = callback)
it is working properly.
model summary:
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
efficientnetv2-l (Functiona (None, 10, 16, 1280) 117746848
l)
global_average_pooling2d (G (None, 1280) 0
lobalAveragePooling2D)
dropout (Dropout) (None, 1280) 0
dense (Dense) (None, 128) 163968
dropout_1 (Dropout) (None, 128) 0
dense_1 (Dense) (None, 6) 774
=================================================================
Total params: 117,911,590
Trainable params: 164,742
Non-trainable params: 117,746,848
_________________________________________________________________
output:
Epoch 4/20
179/179 [==============================] - 203s 1s/step - loss: 0.1559 - accuracy: 0.9474 - val_loss: 0.1732 - val_accuracy: 0.9428
But, while fine-tuning it, I am unfreezing some weights:
base_model.trainable = True
fine_tune_at = 900
for layer in base_model.layers[:fine_tune_at]:
layer.trainable = False
model.compile(optimizer = optimizers.Adam(learning_rate = 0.0001),
loss = losses.SparseCategoricalCrossentropy(),
metrics = ['accuracy'])
history = model.fit(ds_train, batch_size = 28, validation_data = ds_val, epochs = 20, verbose = 1, callbacks = callback)
model summary:
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
efficientnetv2-l (Functiona (None, 10, 16, 1280) 117746848
l)
global_average_pooling2d (G (None, 1280) 0
lobalAveragePooling2D)
dropout (Dropout) (None, 1280) 0
dense (Dense) (None, 128) 163968
dropout_1 (Dropout) (None, 128) 0
dense_1 (Dense) (None, 6) 774
=================================================================
Total params: 117,911,590
Trainable params: 44,592,230
Non-trainable params: 73,319,360
_________________________________________________________________
And, it is starting the training all over again. For the first time, when I trained it with freezed weights, the loss decreased to 0.1559, after unfreezing the weights, the model started training again from loss = 0.444. Why is this happening? I think fine tuning should't reset the weights.
