Paul
Paul
I am getting the same thing with using opencv cv2.dnn.readNetFromONNX using converted custom model to onnx. I wondering if it is missing something else. In the nccn demo, it seems...
I got it working with onnx using onnxruntime
I updated for cuda 10 and latest pytorch if anyone interested. https://github.com/ubergeekNZ/FastFlowNet
Do you see any issue of using https://github.com/jongwook/tfrecord_lite for reading the tfrecords, and create the hub dataset, or does it have to be using tensorflow?
I created a docker, hub, tensorboard, jupyter notebook example based on pytorch MNIST example. Wondering if that is of any use. https://github.com/ubergeekNZ/pytorch_and_hub > @jaivanti hi! thanks for following up. @farizrahman4u...