Hello! Can you provide me with the compatible format of pictures required for srgan implementation as it is showing me an error i.e: RuntimeError: Given groups=1, weight of size [64, 3, 9, 9], expected input[1, 4, 64, 64] to have 3 channels, but got 4 channels instead
Error: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU. As I don't have the GPU so what changes I have to make ??
Thanks a lot bro. Also i noticed that this model works for face (human, animal etc.). I tried it on a blurred image of rose, it didn't work well. Any suggestion?
It only works with the sample images they provide, my own images came out exactly the same as they went in the LR folder, no noticeable difference whatsoever.
when i tried to train i had these; Traceback (most recent call last): File "/content/drive/My Drive/ESRGAN/SRGAN-Super-Resolution-GAN/main.py", line 32, in train(args) File "/content/drive/My Drive/ESRGAN/SRGAN-Super-Resolution-GAN/mode.py", line 21, in train dataset = mydata(GT_path = args.GT_path, LR_path = args.LR_path, in_memory = args.in_memory, transform = transform) File "/content/drive/My Drive/ESRGAN/SRGAN-Super-Resolution-GAN/dataset.py", line 17, in __init__ self.LR_img = sorted(os.listdir(LR_path)) FileNotFoundError: [Errno 2] No such file or directory: 'Data/train_LR' what should i do?
Your way of explaining and implementing is very effective and easy. Thank you bappy! I did search alot for this video but no body hits. Great job!
Thanks man, this is the only method that worked for me :)
the way you explain is just beautiful !! Thanks a Lot bappy !!
Hello! Can you provide me with the compatible format of pictures required for srgan implementation as it is showing me an error i.e:
RuntimeError: Given groups=1, weight of size [64, 3, 9, 9], expected input[1, 4, 64, 64] to have 3 channels, but got 4 channels instead
Can you create end to end implementation using data ingestion to data transformation to training and deployment
Error:
Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.
As I don't have the GPU so what changes I have to make ??
Use google colab
Runtime-use GPU
Thanks a lot bro. Also i noticed that this model works for face (human, animal etc.). I tried it on a blurred image of rose, it didn't work well. Any suggestion?
try with different variant of model
It only works with the sample images they provide, my own images came out exactly the same as they went in the LR folder, no noticeable difference whatsoever.
me also facing the same issue bro
One called REALESRGAN Portable worked though.@@Dinesh-wc8jw
Thanks bhai
Tq❤
❤
Can you please make videos on ML
when i tried to train i had these;
Traceback (most recent call last):
File "/content/drive/My Drive/ESRGAN/SRGAN-Super-Resolution-GAN/main.py", line 32, in
train(args)
File "/content/drive/My Drive/ESRGAN/SRGAN-Super-Resolution-GAN/mode.py", line 21, in train
dataset = mydata(GT_path = args.GT_path, LR_path = args.LR_path, in_memory = args.in_memory, transform = transform)
File "/content/drive/My Drive/ESRGAN/SRGAN-Super-Resolution-GAN/dataset.py", line 17, in __init__
self.LR_img = sorted(os.listdir(LR_path))
FileNotFoundError: [Errno 2] No such file or directory: 'Data/train_LR'
what should i do?
Ok
I was cracking up the entire time
❤