lcxsnow

Problem when using

3

Here is a part of my code.  And this is the error.  Here is the data detail. 

cuda error?

1

UserWarning: A NumPy version >=1.16.5 and

device=torch.device('cpu')

1

/home/m11113013/.local/lib/python3.8/site-packages/scipy/__init__.py:138: UserWarning: A NumPy version >=1.16.5 and

我使用作者提供的pretrained model，順著指示操作(bash ./scripts/calc_fid.sh ./cfg/bird.yml)，每次都測得FID score為32.79，請問是出了什麼問題

I want to do some experiences to this project, like changing the model architecture and the loss function. What do I suppose to add or delete or change the code,...

fix text_encoder

3

In the paper, it is mentioned that the text_encoder will be fixed during the image synthesis training. However, in the provided code, the text_encoder is frozen, meaning it won’t be...

What is the loss and recall score when doing the pretrain?

The CUB-200 spoken captions - Part II is same as CUB-200 spoken captions -Part I. Class 101 to 200 are missing. Could you reupload them?

How to calculate Recall@1, Recall@5 between text_encoder and image_encoder?

run in ubuntu

2

when I run the code in ubuntu, which has more than one gpu, it appeared the below error: (pytorch) m11113013@htsc-Server3:~/ProjectCode/MasterProject2$ python -m torch.distributed.run --standalone --nproc_per_node 1 train.py --outdir ./training-runs/ --cfg...