Katsuya Hyodo

I think you have misunderstood something, `pre_explicit_broadcast` is irrelevant. The value corresponding to `bias (onnx:C)` is already processed as a scalar inside onnx2tf. However, when the model is converted to...

It's too strange... It will take some time to do a little research. I can only guess at this point, but it is possible that the tflite optimizer is doing...

Try it. Fixes: https://github.com/PINTO0309/onnx2tf/releases/tag/1.19.10

I understood. However, I am skeptical that we really need to automatically support that pattern in onnx2tf. I understand that a clean conversion would be great for everyone, but the...

>why pre_explicit_broadcast needs to do that? It's an easier change compared to pattern matching change. The `pre_explicit_broadcast` is not necessary if you want to adapt it to the convenience of...

- TensorFlow v2.15.0, v2.16.1, v2.17.0 ``` ERROR: The option `experimental_image_format` is disabled in OSS. Traceback (most recent call last): File "/home/b920405/git/onnx2tf/onnx2tf/onnx2tf.py", line 1173, in convert tf.saved_model.save(model, output_folder_path, options=tf.saved_model.SaveOptions(experimental_image_format=True)) File "/home/b920405/.local/lib/python3.10/site-packages/tensorflow/python/saved_model/save_options.py",...

Hello,　@anguoyang When a clear answer is required, please write at least the full text of the error message. I can not read what is going on. Also please write...

@keldrom below. #11

@keldrom https://ncsforum.movidius.com/discussion/comment/2241/ [POINT] Check the environment variable path.

@keldrom Please try below. `sudo apt install caffe-cpu`