search

behzadshomali / Image-Describe-Pipe

This app outputs the name, coordinations, sentiment of each extracted face, and besides a brief description of the scene's context for each input image.
2 stars 0 forks source link

Can you run main.py without problem? #11

Closed behzadshomali closed 3 years ago

behzadshomali commented 3 years ago

I ran the same code in the Colab notebook but as our IPs are restricted by Tensorflow, I had some issues installing the required dependencies. Now I want to ensure that main.py can be executed successfully.

@behroozomidvar would you please test this? By the way in case everything was ok, please close this issue. To test, you only need to install dependencies placed in requirements.txt and just run main.py

behroozomidvar commented 3 years ago

In the following line faces = RetinaFace.detect_faces('./Test/people.jpg', 0.95), there is an error that the pre-trained weights (retinaface.h5) could not be loaded! Any solution @behzadshomali ?

behroozomidvar commented 3 years ago

The error in details:

retinaface.h5 will be downloaded from the url https://drive.google.com/uc?id=1K3Eq2k1b9dpKkucZjPAiCCnNzfCMosK4 Access denied with the following error:

Too many users have viewed or downloaded this file recently. Please try accessing the file again later. If the file you are trying to access is particularly large or is shared with many people, it may take up to 24 hours to be able to view or download the file. If you still can't access a file after 24 hours, contact your domain administrator.

You may still be able to access the file from the browser:

https://drive.google.com/uc?id=1K3Eq2k1b9dpKkucZjPAiCCnNzfCMosK4

behzadshomali commented 3 years ago

I fixed the issue by downloading the pre-trained weights. But due to the GitHub limits I can't upload the weights to this repository. All you should do to fix the issue is:

  1. download facenet_weights.hp
  2. download retinaface.hp
  3. pull the repository
  4. put the downloaded files beside main.py file
  5. run main.py

@behroozomidvar would you please try these steps and see whether the problem persists?

behroozomidvar commented 3 years ago

After squandering around 2 hours of time, TF still doesn't work on my M1-chip machine: zsh: illegal hardware instruction So check everything, and if they work for you, go ahead and close this issue.

behzadshomali commented 3 years ago

@behroozomidvar thanks for yout effort to run the program on your machine! Yeah I checked everything and it is working without any bug/problem for me.