Real-ESRGAN
Real-ESRGAN copied to clipboard
ModuleNotFoundError: No module named 'torchvision.transforms.functional_tensor'
Traceback (most recent call last):
File "/content/Real-ESRGAN/inference_realesrgan.py", line 5, in
go to the file show here "/usr/local/lib/python3.10/dist-packages/basicsr/data/degradations.py" do this change in the code - torchvision.transforms.functional import rgb_to_grayscale you have to replace it every single use
go to the file show here "/usr/local/lib/python3.10/dist-packages/basicsr/data/degradations.py" do this change in the code - torchvision.transforms.functional import rgb_to_grayscale you have to replace it every single use
So does this imply that this repo wont function anymore without explicity changing this? At the same time colab wont work either?
`!nvidia-smi
from PIL import Image import cv2, os, subprocess from google.colab import drive from tqdm import tqdm
!git clone https://github.com/xinntao/Real-ESRGAN.git %cd Real-ESRGAN
with open('requirements.txt', 'w') as arquivo: arquivo.write("basicsr==1.3.5\ngfpgan>=1.3.5\nnumpy\nopencv-python\nPillow\ntorch>=1.7\ntorchvision\ntqdm\n")
!pip install facexlib ffmpeg ffmpeg-python !pip install -r requirements.txt !python setup.py develop
with open('/usr/local/lib/python3.10/dist-packages/basicsr-1.3.5-py3.10.egg/basicsr/data/degradations.py', 'r') as file: file_data = file.read() file_data = file_data.replace('from torchvision.transforms.functional_tensor import rgb_to_grayscale', 'from torchvision.transforms.functional import rgb_to_grayscale') with open('/usr/local/lib/python3.10/dist-packages/basicsr-1.3.5-py3.10.egg/basicsr/data/degradations.py', 'w') as file: file.write(file_data)
mount_drive=False #@param{type:"boolean"}
if mount_drive: drive.mount('/content/gdrive/')`
I don't know why in Colab, whenever something gets updated, it always has to mess up everything else. To solve this problem, you need to execute this command.
!python -m pip install torch==2.0.1 torchvision==0.15.2 --extra-index-url https://download.pytorch.org/whl/cu118
After this, everything should work fine.
go to the file show here "/usr/local/lib/python3.10/dist-packages/basicsr/data/degradations.py" do this change in the code - torchvision.transforms.functional import rgb_to_grayscale you have to replace it every single use
please give a proper video
I don't know why in Colab, whenever something gets updated, it always has to mess up everything else. To solve this problem, you need to execute this command.
!python -m pip install torch==2.0.1 torchvision==0.15.2 --extra-index-url https://download.pytorch.org/whl/cu118
After this, everything should work fine.
Can confirm, this worked for me in colab.
I don't know why in Colab, whenever something gets updated, it always has to mess up everything else. To solve this problem, you need to execute this command.
!python -m pip install torch==2.0.1 torchvision==0.15.2 --extra-index-url https://download.pytorch.org/whl/cu118
After this, everything should work fine.
Can confirm, this worked for me in colab.
ERROR: Could not find a version that satisfies the requirement torch==2.0.1 (from versions: 2.2.0, 2.2.1, 2.2.2) ERROR: No matching distribution found for torch==2.0.1