ItsArghya

Hi, An easy fix is: 1. Open `~/.keras/keras.json` file. In Ubuntu do: `vi ~/.keras/keras.json` 2. change your input data format from `channels_last` to `channels_first` 3. save it. 4. Run: `python...

add ``` #ifndf AT_CHECK #define AT_CHECK TORCH_CHECK #endif ``` at the very beginning of: ``` vc_rcnn/csrc/cuda/deform_conv_cuda.cu ``` and ``` vc_rcnn/csrc/cuda/deform_pool_cuda.cu ```

I and my partner had got the same problem. We tried to train the R101 network after uncommenting ```rpn```. It is working (our present iteration number is 31K+). We agree...

Hi, open the dataloader.py file and, add elif dataset == 'AWA': data_loader = DataLoader( datasets.ImageFolder('data/AWA', transform=transform), batch_size=batch_size, shuffle=True) then, open main.py and modify this line: parser.add_argument('--dataset', type=str, default='mnist', choices=[ 'mnist',...

No, I don't think so. Please go ahead and use your dataset.. please reply back, if you encounter any problem related to image size

Got the same problem.. @Luna86 have you solved this issue? ` Using board 0 2048 Traceback (most recent call last): File "display_results.py", line 22, in main() File "display_results.py", line 9,...

Use python 3.6

> > https://github.com/sangyun884/fast-ode/blob/master/EMA.py > > Try this code instead, and let me know if it works. > > Unfortunately with your code I've got `AttributeError: 'EMA' object has no attribute...

No code!

Hi, @tjtorres and @RobGeada have got the similar problem.. My Image size is 300X300 and Gray Scale `fauxtograph train --kl_ratio 0.005 --shape 300 300 /home/dl-box/Arghya/arghya/lasttry/images/ ./models/VAE 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 49/49 [00:00