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 want to make my own dataset to train this model, so how do I make my own dataset step by step?
Hello, thank you for the tutorial! I tried to run your code on PyTorch 1.2.0 and it seems I couldn't produce your scores. The `bleu-4 score` is peaked at epoch...
Did anyone save the model after the training and is willing to share it with the rest of us? I tried running on my machine, and it is too slow....
When I use muti-gpu in training, there is an issue: `Some of weight/gradient/input tensors are located on different GPUs` When I revise the following code, the question is resolved! I...
Hi, Pre trained model file seems to be broken and i am unable to use it. Can you please if possible re share it. Regards, Vinod Krishnan
assert len(references) == len(hypotheses) # Calculate BLEU-4 scores bleu4 = corpus_bleu(references, hypotheses)
Exception in thread Thread-2: Traceback (most recent call last): File "/home/wanglulu/anaconda3/lib/python3.6/threading.py", line 916, in _bootstrap_inner self.run() File "/home/wanglulu/anaconda3/lib/python3.6/threading.py", line 864, in run self._target(*self._args, **self._kwargs) File "/home/wanglulu/anaconda3/lib/python3.6/multiprocessing/resource_sharer.py", line 139, in _serve...
Thanks for you tutorial! I found in [READEME.md](https://github.com/sgrvinod/a-PyTorch-Tutorial-to-Image-Captioning#attention-1) and code: ``` def forward(self, encoder_out, decoder_hidden): """ Forward propagation. :param encoder_out: encoded images, a tensor of dimension (batch_size, num_pixels, encoder_dim) :param...
