zengxianyu

I thought there should be a '/' before the second '*' in line 50 of file 'create_miniImagenet.py'

1

I thought there should be a '/' before the second '*' in line 50 of file 'create_miniImagenet.py'

How to generate the ground-truth pose parameter?

2

Thank you for the amazing work. I am very interested in it and would like to ask some questions about the details. From the training code it seems that the...

Hi, Cadene, why don't you update the feature extractor when training?

1

Hi, Cadene, Thank you very much for your code, it's very helpful. But it seems that you use resnet as a seperate feature extractor instead of updating it when training...

Out of memory when the meta optimizer updates parameters

3

Hello, I find your code very helpful, but too much memory is consumed when the meta optimizer updates parameters of the model. On my computer, it always raises an error...

Some differences from original FCN

1

Hi, I'm trying to use FCN in pytorch, and your work interests me very much. It really helps me a lot, but I found the segmentation results are not so...

FID on coco for text to image generation

7

I was trying to evaluate the text to image generation results on coco dataset. I computed the FID on 259 samples randomly drawn from the coco validation dataset and got...

error when batchsize=1

1

#4 line 135 in skip-thoughts.torch/pytorch/skipthoughts/skipthoughts.py lengths = list(max_length - input.data.eq(0).sum(1).squeeze()) will raise an error if the batch size is 1, saying ``typeError: iteration over a 0-d tensor''

line 135 in skip-thoughts.torch/pytorch/skipthoughts/skipthoughts.py ```lengths = list(max_length - input.data.eq(0).sum(1).squeeze())``` will raise an error if the batch size is 1, saying ``typeError: iteration over a 0-d tensor''

Why flip weight and add 1 to bias when loading tensorflow pretrained model

1

Thanks to the great work. I noticed that when loading the tensorflow pretrained model you flip "Conv0_up.conv.weight" and add 1 to the "conv.modulation.bias. Is this because of the difference between...

find image files recursively in a folder