UMEI

Thanks for your awesome paper and code! I have a question about IS. I got the result from your code for 10000 images: IS: 4.457951 But the real data IS...

Ony have anchor and pos_sample

5

Thanks for your contribution！ In this code, I only found utilize the anchor and pos_sample as follows: def __getitem__(self, index): path, target = self.samples[index] cam = self.cams[index] # pos_path, neg_path...

Thanks for your sharing. I don't know why I change the input size like 56x56, It is can meet this question. I print the index.shape is torch.Size([8, 32, 28224]). Please...

ValueError: invalid literal for int() with base 10: ' gen_0000'

4

你好，感谢你的分享!有一个问题想向你请教~我已经通过DCGAN生成图像并且放到train_new中，如下图所示:  生成图像的索引如下：  但是在跑train_baseline的时候，却出现了下面的错误， > Traceback (most recent call last): File "/home/meichen/SourceProject/Person-reid-GAN-pytorch-master/train_baseline.py", line 178, in dataloaders['train'] = DataLoader(dcganDataset('train_new',data_transforms['train']), batch_size=opt.batchsize, File "/home/meichen/SourceProject/Person-reid-GAN-pytorch-master/train_baseline.py", line 115, in __init__ self.img_label.append(int(folder)) ValueError:...

Thanks for your sharing! May I know how can I get the test image？ I noted that many papers just only mentioned the training set. 1, Should I randomly change...

Thanks for your sharing your code. It's a wonderful job I think~~ I have one question about the content loss score. I have applied StyTr2 to a dataset of 800...

'builtin_function_or_method' object has no attribute 'grad_fn'

1

Thanks for your sharing! But I meet this question about ` File "/home/meichen/PycharmProjects/CBAM /cbam+resnet/MODELS/model_resnet.py", line 282, in make_dot(output.mean, params=dict(net.named_parameters())) File "/home/meichen/anaconda3/envs/reidbaseline/lib/python3.6/site-packages/torchviz/dot.py", line 37, in make_dot output_nodes = (var.grad_fn,) if not...

Only have positive pairs?

2

Thanks for your sharing! May I have a question about NCELoss? I cannot find how to choose the negative samples in your code. I only found how to choose the...