-
Notifications
You must be signed in to change notification settings - Fork 122
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
The example of esp-dl/tools/tensorflow_to_onnx does not support MatMul and Softmax yet (AIV-536) #98
Comments
@Auroragan when can it support more layers like MatMul and Clip in calibrator? These are very common layers and the calibrator is too outdated |
Hi, I was successful in implementing Convolution,MatMul and Softmax check out here. |
@Farzinkh impressive! I sure will try out! |
Is this resolved?? |
Where specifically should I look? The repository you provided is hard to follow, please let me know I am having the same issue and it is frustrating. Thank you. |
Hello were you able to solve this problem? I am running into the same issue any help would be appreciated @QimingLee @Farzinkh |
We complete the example and run the program, but it shows "Generating the quantization table:
MatMul is not supported on esp-dl yet
Softmax is not supported on esp-dl yet"
Traceback (most recent call last):
File "D:/esp-dl-master/esp-dl-master/tools/quantization_tool/examples/example.py", line 39, in
calib.generate_quantization_table(model_proto, calib_dataset, pickle_file_path)
File "calibrator.py", line 333, in calibrator.Calibrator.generate_quantization_table
File "calibrator.py", line 222, in calibrator.Calibrator.generate_output_model
File "calibrator.py", line 217, in calibrator.Calibrator.check_model
ValueError: current model is not supported by esp-dl
The text was updated successfully, but these errors were encountered: