Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Chapter 5 convert #34

Open
csecht opened this issue Jun 16, 2024 · 0 comments
Open

Chapter 5 convert #34

csecht opened this issue Jun 16, 2024 · 0 comments

Comments

@csecht
Copy link

csecht commented Jun 16, 2024

After downloading the yolov3.weights binary, and placing it in a new made weights directory, running this:
python3 convert.py --weights weights/yolov3.weights --output weights/yolov3.tf
throws this error:
...
File "/home/craig/Desktop//Hands-On-Computer-Vision-with-TensorFlow-2-master/Chapter05/utils.py", line 36, in load_darknet_weights
in_dim = layer.input_shape[-1]
AttributeError: 'Conv2D' object has no attribute 'input_shape'. Did you mean: 'input_dtype'?

Consequently, the .tf file conversion fails.

Any suggestions to resolve the error or updates to the utils modules would be appreciated.

Cheers,
Craig

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Development

No branches or pull requests

1 participant