faithfulnguyen

Results 4 comments of faithfulnguyen

Output Node

here is index of output node name, when you freeze graph you will see 30 variable convert to const, file freeze graph had weight is 35Mb, hope it help you....

Output Node

You need feed data for this: https://github.com/da03/Attention-OCR/blob/88cff37cad09fd85b5178662130595821d7fe0a2/src/model/model.py#L101 https://github.com/da03/Attention-OCR/blob/88cff37cad09fd85b5178662130595821d7fe0a2/src/model/model.py#L104 https://github.com/da03/Attention-OCR/blob/88cff37cad09fd85b5178662130595821d7fe0a2/src/model/model.py#L106 or you hard code in your inference graph, decoder:0 - > decoder:35 (maybe more, sorry I don't remember) value feed can...

when i running the testing code. i am getting the below error

because you using old version, you need convert name node, here code to convert name node: https://github.com/tensorflow/tensorflow/tree/master/tensorflow/contrib/rnn/python/tools, or you can remove tensorflow and install new version. hope it help you.

converted ONNX to trt failed( Internal Error (Assertion weights.type() == DataType::kINT32 failed)

I got the same issue as you: Here is the version I use: - onnx=1.9.0 - tf2onnx=1.8.1 - tensorflow=2.6 - tensorrt=8.2.1.8 I use this command to convert TensorFlow to ONNX:...