Video-Captioning
Video-Captioning copied to clipboard
Shreyz-max
Video Captioning is an encoder decoder mode based on sequence to sequence learning
Remove inf_decoder_model=None to retains the value assigned by model.inference_model
Hi! Thanks a lot for you project! I have a problem with features extraction (extract_feature.py file). Running prediction on npy file presented in testing_data folder produces different result from applying...
Traceback (most recent call last): File "predict_realtime.py", line 214, in video_caption, file = video_to_text.test() File "predict_realtime.py", line 161, in test sentence_predicted = self.greedy_search(X_test.reshape((-1, 80, 4096))) File "predict_realtime.py", line 45, in...
Hello, I'm using "MSRVTT" dataset to prediction in Colab, but the result is not good... As you can see the output is felt weird... May I ask you how to...
I have faced the time_steps_decoder error which. AttributeError: module 'config' has no attribute 'time_steps_decoder' How can I set this variable?
I can't find the features.py file，Can you provide this file
Removed the created item '.ipynb_checkpoints' created at the beginning of file_list
Metadata
Owner
Metadata
Video Captioning is an encoder decoder mode based on sequence to sequence learning