Why am I getting "AssertionError: Exception encountered when calling layer" while extracting features from frames? - machine-learning

Question

I merged a Vgg model and a Resnet model. The merged model will be used to extract features from frames of videos. The model is merged correctly, but it shows "AssertionError: Exception encountered when calling layer" while extracting features from frames. I am not finding any mistakes.
The code for extracting features from frames of video is mentioned below
def prepare_all_videos(df, root_dir):
num_samples = len(df)
video_paths = df["video_name"].values.tolist()
##take all classlabels from train_df column named 'tag' and store in labels
labels = df["tag"].values
#convert classlabels to label encoding
labels = label_processor(labels[..., None]).numpy()
# `frame_masks` and `frame_features` are what we will feed to our sequence model.
# `frame_masks` will contain a bunch of booleans denoting if a timestep is
# masked with padding or not.
frame_masks = np.zeros(shape=(num_samples, MAX_SEQ_LENGTH), dtype="bool")
frame_features = np.zeros(shape=(num_samples, MAX_SEQ_LENGTH, NUM_FEATURES), dtype="float32")
# For each video.
for idx, path in enumerate(video_paths):
# Gather all its frames and add a batch dimension.
frames = load_video(os.path.join(root_dir, path))
frames = frames[None, ...]
# Initialize placeholders to store the masks and features of the current video.
temp_frame_mask = np.zeros(shape=(1, MAX_SEQ_LENGTH,), dtype="bool")
temp_frame_features = np.zeros(
shape=(1, MAX_SEQ_LENGTH, NUM_FEATURES), dtype="float32"
)
# Extract features from the frames of the current video.
for i, batch in enumerate(frames):
video_length = batch.shape[0]
length = min(MAX_SEQ_LENGTH, video_length)
for j in range(length):
temp_frame_features[i, j, :] = feature_extractor.predict(
batch[None, j, :]
)
temp_frame_mask[i, :length] = 1 # 1 = not masked, 0 = masked
frame_features[idx,] = temp_frame_features.squeeze()
frame_masks[idx,] = temp_frame_mask.squeeze()
return (frame_features, frame_masks), labels
train_data, train_labels = prepare_all_videos(train_df, "train")
test_data, test_labels = prepare_all_videos(test_df, "test")
print(f"Frame features in train set: {train_data[0].shape}")
print(f"Frame masks in train set: {train_data[1].shape}")
print(f"train_labels in train set: {train_labels.shape}")
print(f"test_labels in train set: {test_labels.shape}")
The error shows
AssertionError Traceback (most recent call last)
<ipython-input-86-ae247cc8c7f3> in <module>
43
44
---> 45 train_data, train_labels = prepare_all_videos(train_df, "train")
46 test_data, test_labels = prepare_all_videos(test_df, "test")
47
2 frames
/usr/local/lib/python3.8/dist-packages/keras/engine/training.py in tf__predict_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
AssertionError: in user code:
File "/usr/local/lib/python3.8/dist-packages/keras/engine/training.py", line 2137, in predict_function *
return step_function(self, iterator)
File "/usr/local/lib/python3.8/dist-packages/keras/engine/training.py", line 2123, in step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/usr/local/lib/python3.8/dist-packages/keras/engine/training.py", line 2111, in run_step **
outputs = model.predict_step(data)
File "/usr/local/lib/python3.8/dist-packages/keras/engine/training.py", line 2079, in predict_step
return self(x, training=False)
File "/usr/local/lib/python3.8/dist-packages/keras/utils/traceback_utils.py", line 70, in error_handler
raise e.with_traceback(filtered_tb) from None
File "/usr/local/lib/python3.8/dist-packages/keras/engine/functional.py", line 679, in _run_internal_graph
assert x_id in tensor_dict, "Could not compute output " + str(x)
AssertionError: Exception encountered when calling layer 'merged_model' (type Functional).
Could not compute output KerasTensor(type_spec=TensorSpec(shape=(None, 2049), dtype=tf.float32, name=None), name='concatenated_layer/concat:0', description="created by layer 'concatenated_layer'")
Call arguments received by layer 'merged_model' (type Functional):
• inputs=tf.Tensor(shape=(None, 224, 224, 3), dtype=float32)
• training=False
• mask=None
The main error is in following line
temp_frame_features[i, j, :] = feature_extractor.predict(
batch[None, j, :]
)
Please let me know where am I going wrong? I need a solution as soon as possible.