Google Colab CUDA error #44
Comments
|
i have same issues |
|
fixed this issues by setting nvcc '-gencode', 'arch=compute_70,code=compute_70' |
|
Yeah we waiting for colab version, Goodluck. |
|
If anyone succeeds with Google Colab, please share working 'notebook' |
|
Mine seems to work just following the instructions: https://colab.research.google.com/drive/1hkPQQNRH1ykKJN6V7tTiGnZOHWm7JRdr They must have updated the code. |
|
@btahir Thanks for sharing this link! Sorry for a lot of off-topic, won't happen again :) |
|
Is there anyone who has used the TPU on the Google Colab to run this program? |
Follow this colab, but Install scipy 1.0.0 and remove the %%%writefile cell. |
|
It really depends which GPU is used by colab in the backend. Anyway if you don't know how to do it, have a look at my fork as an example: |
|
How to use this video for this project？ |
|
@tamu520 - there's a very early version of it packaged as an app here - https://grisk.itch.io/dain-app |
|
@Gunslap Thanks for the answer, but I am referring to how to test my video in a project in Goole Colab |
|
Hi! We've made some progress on this front. The latest version of a working Colab notebook can be found here: https://github.com/AlphaGit/DAIN/blob/master/Colab_DAIN_alpha.ipynb Once we get it updated on the upstream repo (StylerDollar's one), we will submit a PR for this repo. In the meantime, you can upload that notebook manually and change cell 5 so that it uses my repo, which has the latest. |
|
@AlphaGit Thanks for sharing, but sometimes '# Interpolation' will give an error |
|
@AlphaGit And I believe %shell commands don't work locally, any suggestions regarding what I could replace the commands which use %shell, other than the ! symbol. (Also, I'm sorry if this isn't the right place to ask this question) |
|
@tamu520 Kind of depends what the error is. If you're getting that "No module named correlation_cuda", it means you missed running the build cell. @SreeHarshaNelaturu You might be missing the step to build the modules that DAIN has. That's the cell that has the warning about taking long. Yes, using |
|
@AlphaGit Thanks a bunch for sharing! But (like probably everyone here...) I've got a problem. When I try to check the GPU with |
|
In the runtime menu in Google Colab, could you check if the hardware accelerator is set to
GPU. This is what might causing the error.
|
|
@SreeHarshaNelaturu thank you! It wasn't set before, but I just activated it, tried again and it worked. |
|
Sorry to bother again, but...
As a short note, Drive was succesfully mounted at /content/gdrive. |
Are you sure that directory exists? The error seems to imply it didn’t. Make sure you have the variables correctly set up. |
|
Hello! Google Colab has been down for two days now. Endlessly loading the item "Install dependencies". Before that, everything worked. |
|
Yeah I'm getting this error on styler00dollar's Colab now: Running: Gives |
|
Hi @alvisanovari -- that error usually means that the module compiled by the previous cells is not available. Make sure to run them all in order. If you keep receiving those issues, consider restarting the notebook and starting from scratch. |
|
PS: I have been able to verify that with the linked notebook the build process doesn't quite finish. I'll work on it later and submit a PR. I'll provide more info here later. |
|
@alvisanovari @AlphaGit |
|
I also tried creating conda env from environment.yml, but this fails too :( |
|
@alvisanovari I managed to get it working after also getting that error. Im still testing and cleaning up the colab, will share it when I'm done. |
|
It seems Google Collab upgraded to pytorch 1.5, which breaks the modules build. Add this cell and it should work. I still cannot get to submit a right PR, but I was able to give it a try and this, before the build cell, fixes it:
|
|
@AlphaGit Thank you! I can get it to run now! The output video seems to be the same as the input though? The length of the video and the number of frames in the output directory are the same even though the time step was 0.5...shouldn't they have doubled? |
|
im getting some errors, like "resize_hotfix" is not defined and others :/ |
|
@AlphaGit ) Using Tesla P100-PCIE-16GB, 418.67, 16280 MiB, I also get: in [6] # ffmpeg extract in [9] # Interpolation: Recreating error: I'm running the notebook step by step as instructed. |
|
According to the following settings, I successfully used DAIN on Colab today. # Install PyTorch 1.4.0 with CUDA 10.0
!pip install torch==1.4.0+cu100 torchvision==0.5.0+cu100 -f https://download.pytorch.org/whl/torch_stable.html
# Then set the softlink to CUDA 10.0
!sudo ln -snf /usr/local/cuda-10.0 /usr/local/cuda
# After that we can perform a complete compilation.You can also check my repository |
I tried that, and it works, thz :)
:( |
|
Can somebody make a video tutorial on this please -_- |
|
I dunno how, but it works xD, thanks to you all people :) |
|
@Brokensilence Those are warnings, meaning that it doesn't prevent the code from running. I did take a look at that long time ago and I wasn't able to fix it, and also I didn't find an easy way to hide it. I agree it is a bit noisy. @0nepixel I'm glad you got it working. The most difficult part is to understand how to operate a notebook, but then, it's just about reading, modifying variables, and running the cells in order. If you'd like to do the video tutorial, we'd very much appreciate it! |
|
My first language is spanish :/, maybe a tutorial step by step using images. |
|
@0nepixel Also mine! =D I lack video editing skills, but if you need someone to narrate over a video, count me in, I do have audio editing experience. |
|
I am not. If you’d like to continue the conversation you can reach out to me at alphagma@gmail.com — that way we won’t create unnecessary chatter for all other members subscribed to this issue. See ya around! |
|
@Brokensilence |
|
CAN SOMEONE PLEASE HELP ME? When I run it Colab version,
I'm encountering with this error;
|
|
@xstrauss This error ("IndexError: list index out of range" in DAIN.py), seems to be unrelated to the issue being discussed (Google Colab compatibility). Would you mind to open another issue in GitHub for that? If you can, also include the input video and the configuration you're trying to use. If we're able to reproduce, we might get to the underlying problem. /EDIT: Nevermind, I just saw you did. It's preferable to mention people instead of spamming with multiple questions -- that is distracting to the contributors involved. I'll check it out and see if I can help. |
Sorry but I just need answer. |
Yes, it works with pytorch 1.4.0 and cuda 10.0. |
|
I was trying to make a DAIN video when executing this command. Detecting FPS of the input file.`%shell yes | cp -f /content/gdrive/My\ Drive/{INPUT_FILEPATH} /content/DAIN/ import os import cv2 fps = cap.get(cv2.CAP_PROP_FPS) if(fps/TARGET_FPS>0.5): I got an error saying this. I don't know to code at all cp: cannot stat '/content/gdrive/My Drive//content/gdrive/My': No such file or directory
|
Try replacing I think the INPUT_PATH in this case should be the path in your drive, try taking away "/content/gdrive/My Drive" from INPUT_PATH. |
|
GUYS I HAVE THE SOLUTION FOR THIS PROBLEM CODE: Detecting FPS of input file.%shell yes | cp -f /content/gdrive/MyDrive/input.mp4 /content/DAIN/ import os import cv2 fps = cap.get(cv2.CAP_PROP_FPS) if(fps/TARGET_FPS>0.5): |
|
it is showing that : |
and others
Tried to get this running on Colab, but I'm running into cuda issues...
Link to notebook.
Any ideas on how to fix this? Would be great to just have a Colab to experiment!
The text was updated successfully, but these errors were encountered: