I am trying to build a machine learning model using pre-trained VGG16 with tensorflow, but I keep getting the same problem with the shape of the input. Compared to other public codes, the only difference is that I use a tf.data.dataset to share the data, instead of the DirectoryIterator of tf.image
Here is my code:
zip_ref = ZipFile(zip_file, 'r')
zip_ref.extractall(repository_dir)
zip_ref.close()
train_dir = os.path.join(repository_dir, "seg_train", "seg_train")
test_dir = os.path.join(repository_dir, "seg_test", "seg_test")
os.system(f"rm -r {os.path.join(repository_dir, 'seg_pred')}")
# load variables
validation_percentage = 0.2
label_mode = "int"
# for our model purposes
img_size = (224, 224)
color_mode='rgb'
data_train, data_val = image_dataset_from_directory(
train_dir,
batch_size=None,
label_mode=label_mode,
color_mode=color_mode,
image_size=img_size,
validation_split=validation_percentage,
subset="both",
seed=123,
)
data_test = image_dataset_from_directory(
test_dir,
batch_size=None,
label_mode=label_mode,
color_mode=color_mode,
image_size=img_size,
)
classes = data_train.class_names
print(classes)
scale = 1.0/255
normalization_layer = tf.keras.layers.Rescaling(scale)
data_train_norm = data_train.map(lambda x,y: (normalization_layer(x), y))
data_val_norm = data_val.map(lambda x,y: (normalization_layer(x), y))
data_test_norm = data_test.map(lambda x,y: (normalization_layer(x), y))
input_size = None
for img, label in data_train_norm.take(1).as_numpy_iterator():
input_size = img.shape
print(input_size)
base_model = VGG16(
input_shape=input_size, # Shape of our images
include_top = False, # Leave out the last fully connected layer
weights = 'imagenet'
)
# we do not train the parameters
for layer in base_model.layers:
layer.trainable = False
# Flatten the output layer to 1 dimension
x = layers.Flatten()(base_model.output)
# https://medium.com/analytics-vidhya/car-brand-classification-using-vgg16-transfer-learning-f219a0f09765
# FC layer very simple and with a softmax activation unit
x = layers.Dense(len(classes), activation="softmax")(x)
landscapeModel01 = Model(inputs=base_model.input, outputs=x, name="landscapeModel01")
loss = "sparse_categorical_crossentropy"
optimizer = "adam"
landscapeModel01.compile(
optimizer=optimizer,
loss=loss,
metrics=["loss","accuracy"]
)
#fit data
shuffle=True # variable
epochs=50 # variable, according if it is able to converge
batch_size = 200
print(landscapeModel01.input)
landscapeModel01.fit(
data_train_norm,
validation_data=data_val_norm,
epochs=epochs,
shuffle=shuffle,
batch_size=batch_size
)
and this is the error:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
Cell In [10], line 8
4 batch_size = 200
6 print(landscapeModel01.input)
----> 8 landscapeModel01.fit(
9 data_train_norm,
10 validation_data=data_val_norm,
11 epochs=epochs,
12 shuffle=shuffle,
13 batch_size=batch_size
14 )
File ~/anaconda3/envs/faa/lib/python3.10/site-packages/keras/utils/traceback_utils.py:70, in filter_traceback.<locals>.error_handler(*args, **kwargs)
67 filtered_tb = _process_traceback_frames(e.__traceback__)
68 # To get the full stack trace, call:
69 # `tf.debugging.disable_traceback_filtering()`
---> 70 raise e.with_traceback(filtered_tb) from None
71 finally:
72 del filtered_tb
File /tmp/__autograph_generated_file8y_bf523.py:15, in outer_factory.<locals>.inner_factory.<locals>.tf__train_function(iterator)
13 try:
14 do_return = True
---> 15 retval_ = ag__.converted_call(ag__.ld(step_function), (ag__.ld(self), ag__.ld(iterator)), None, fscope)
16 except:
17 do_return = False
ValueError: in user code:
File "/home/renan/anaconda3/envs/faa/lib/python3.10/site-packages/keras/engine/training.py", line 1160, in train_function *
return step_function(self, iterator)
File "/home/renan/anaconda3/envs/faa/lib/python3.10/site-packages/keras/engine/training.py", line 1146, in step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/home/renan/anaconda3/envs/faa/lib/python3.10/site-packages/keras/engine/training.py", line 1135, in run_step **
outputs = model.train_step(data)
File "/home/renan/anaconda3/envs/faa/lib/python3.10/site-packages/keras/engine/training.py", line 993, in train_step
y_pred = self(x, training=True)
File "/home/renan/anaconda3/envs/faa/lib/python3.10/site-packages/keras/utils/traceback_utils.py", line 70, in error_handler
raise e.with_traceback(filtered_tb) from None
File "/home/renan/anaconda3/envs/faa/lib/python3.10/site-packages/keras/engine/input_spec.py", line 295, in assert_input_compatibility
raise ValueError(
ValueError: Input 0 of layer "landscapeModel01" is incompatible with the layer: expected shape=(None, 224, 224, 3), found shape=(224, 224, 3)
What can I fix to make the code work?
versions: tensorflow==2.10.0
#EDIT
I just found the solution: I was loading images with a batch size equals none, but the trained model demanded that the images had one, even if it was 1.
Solution
I just needed to load images in the image_dataset_from_directory with a batch_size parameter different from None. Considering my investigation did not consider data augmentation in the beginning, I chose 1.