a-PyTorch-Tutorial-to-Image-Captioning
a-PyTorch-Tutorial-to-Image-Captioning copied to clipboard
sgrvinod
Show, Attend, and Tell | a PyTorch Tutorial to Image Captioning
I have tried making the encoder part process batch image by passing multiple image as np array and later converting it in tensorfloat and stacking images together , but i...
I use the COCO.api and change the eval.py a little to achieve evaluation using CIDEr, METEOR, ROUGE and BLEU. The packages of all the evaluation methods are in the folder:...
Thanks for your work first! learned a lot. In the forward function of DecoderWithAttention, I see at each output turn, the LSTMcell need an embedded encoded_captions, which is a supervised...
TypeError: iter() returned non-iterator of type 'int' How to solve this problem!help！
The error can be avoided by set num_worker as 0 or 1 in data loader. However, I have to use more than one worker to load my dataset (One process...
I am not clear with this code in model.py ``` for t in range(max(decode_lengths)): batch_size_t = sum([l > t for l in decode_lengths]) attention_weighted_encoding, alpha = self.attention(encoder_out[:batch_size_t], h[:batch_size_t]) gate =...
import scipy.special as special will cause error "module 'scipy' has no attribute 'special' ". But import scipy.special was ok. Sometimes it may also causes error "module 'scipy' has no attribute...
Thank you so much for this tutorial. I have a question about beam search decoding. I saw in this course https://youtu.be/XXtpJxZBa2c?t=2407 that the scores should be normalized by length at...
Hi I have used the authors' WORDMAP and checkpoint files but after running the eval.py on these files with correct filepaths, I received a BLEU-4 score @ beam size of...
