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

python_demo.py can work, but export_tflite.py and export_pb.py have some problem #399

Open
wmy10128 opened this issue Feb 5, 2024 · 0 comments

Comments

@wmy10128
Copy link

wmy10128 commented Feb 5, 2024

Traceback (most recent call last):
File "D:\codefiled\py\human_pose\HyperPose-master\export_tflite.py", line 14, in
model.load_weights(model_weight_path)
File "D:\Programs\anaconda\envs\hypose\lib\site-packages\tensorlayer\models\core.py", line 958, in load_weights
utils.load_and_assign_npz(filepath, self)
File "D:\Programs\anaconda\envs\hypose\lib\site-packages\tensorlayer\files\utils.py", line 2046, in load_and_assign_npz
assign_weights(weights, network)
File "D:\Programs\anaconda\envs\hypose\lib\site-packages\tensorlayer\files\utils.py", line 2019, in assign_weights
ops.append(network.all_weights[i].assign(d[network.all_weights[i].name]))
File "D:\Programs\anaconda\envs\hypose\lib\site-packages\tensorflow\python\ops\resource_variable_ops.py", line 891, in assign
(tensor_name, self_shape, value_tensor.shape)
valueError: Cannot assign to variable conv2d_1/filters:0 due to variable shape (3,3,3,32) and value shape (1,1,384,128)are incompatible.

numpy:1.19.4
tensorflow-gpu:2.4.0
tensorlayer:2.2.3
cuda:11.4

And i download the newest model weights here
please help me, thanks

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

No branches or pull requests

1 participant