GL Li

AttGAN RuntimeERROR:Sizes of tensors must match except in dimension 1

5

Hi, when I use Pytorch-1.7 to train AttGAN from scratch, a RuntimeERROR appears. There are more details: Traceback (most recent call last): File "train.py", line 161, in errD = attgan.trainD(img_a,...

I am puzzled by the results presented in your paper.

12

In your paper, you mentioned that the mean rank of the model is close to 0, but the average correct rate of the model is only about 0.004. But I...

[Feature Support] For Multi-Batch Data Inference Support

10

If you wish to generate descriptions for multiple images at one time. Simply use the following codes: ``` import requests import torch import transformers from PIL import Image from otter.modeling_otter...

Are you still studying this work?

1

I want to refer to the code of the paper.Can you provide it? thx

i find a bug in submit.py hope you can fix it

17

when i use a trained model of FPN,submit.py have an error called `p4_out = torch.add(self.P4_conv1(C4), F.upsample(p5_out, scale_factor=2))` `RuntimeError: The size of tensor a (23) must match the size of tensor...

SG的傻狗guna！

4

艹艹不喜欢！

tf _approxmatch_so cannot be used in higher version tensorflow

1

I am using Tensorflow-gpu=1.14.0, CUDA=10.2. I try to compile the tf_approxmatch_so by myself. However, there is an error when I try to import it. ` tensorflow.python.framework.errors_impl.NotFoundError: /root/AdvPC/latent_3d_points/external/structural_losses/tf_approxmatch_so.so: undefined symbol: _ZN10tensorflow12OpDefBuilder5InputESs...

batch first mode causes some error

6

`if __name__ == '__main__': model = LSTM(50, 100, 2,batch_first=True) x = Variable(Tensor(32,50, 50)) h = model.init_hidden(32) print(model(x, h))` and it will return : `Traceback (most recent call last):' 'File "lstm.py",...