This is a documentation bug. The parameter of API mxnet.test_utils.check_numeric_gradient is not consistent between signature and Parameter section. There is a parameter check_eps in the Parameter section, but it is not in the signature.
MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.
There are many links in Kinetics that have expired. As as result, everyone might not be using the same Kinetics dataset. As a reference, the statistics of the Kinetics dataset used in PySlowFast can be found here, https://github.com/facebookresearch/video-nonlocal-net/blob/master/DATASET.md. However, I cannot seem to find similar information for gluoncv. Will you guys be sharing the statistics and
I have the same hardware envs, same network, but I could not get the result as you, almost half as you. Any best practices and experience? thanks very much! for bytePS with 1 instance and 8 GPU, I have similar testing result.