You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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
The text was updated successfully, but these errors were encountered:
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
The text was updated successfully, but these errors were encountered: