zc1616
zc1616
Hi @AnastGerus , I have the same problem when convert torch->onnx->tflite. Have you solved the problem? It seems tensorflow=2.6.0 or tf-nigthtly can convert to tflite but it log error when...
Hi @AnastGerus , Thanks for your reply. I have met the same situation with you. Model can be convert to tflite with tfnightly and log similar error log with you....
Hi @AnastGerus , Is there any suggestion that modify tensorflow.pb model manual? Or redefine the net in the tensorflow(using keras) and load the onnx model? Thanks
Hi @AnastGerus I got the explain from https://github.com/tensorflow/tensorflow/issues/52041.
Hi @AnastGerus , I try set the tensorflow.pb weights manually follow this author https://github.com/onnx/onnx-tensorflow/issues/971#issuecomment-926467939. By the way, do you try another way in onnx-tf which causes TF models work? I...
Hi @AnastGerus , I'm sorry I didn't describe the problem clearly. I can see you can make it work when set the QUANTIZATION = 'None'. However, in my case, When...
Hi @jumelet I have met the similar problem. And I can convert onnx to tensorflow.pb model 'correctly', but can't inference the tensorflow.pb model. Can you inference the model now? Best...
Thanks for your reply! Do you define in tensorflow and retrain Or directly define in Keras and assign onnx weights to tensorflow? Hope you can run it as soon as...
Good luck!
Hi, yanxin! Have you ever met the question that train loss decrease but the dev loss increase? Hope your reply