Larry
@semchan I set groups=1, and the size of the weight file changed from ～30m to ～900m. It is unacceptable. @lukemelas The TensorRT engine file form onnx still slow than the...
@fzyzcjy Great idea, i'd like to work with you, but i don't have time in workday. You can fork my repository and write your code firstly, i will do it...
@fzyzcjy I don't have a pre-train model in imagenet. You can test the performance of mobilenetV3 in imagenet and it will be helpful in segmentation task.
@fzyzcjy I add the code of Lite R-ASPP Semantic Segmentation head and you can check if i have a correct understanding of the description in the paper.
Unfortunately, due to limited computational power, I only experimented on the cifar dataset and did not use imagenet.
扩展因子t的大小跟上述条件均没有关系，每一层inverted_residual_block的t的大小由作者在论文中的网络结构参数表给出。
@momo1986 是不是因为OpenCV版本的问题，这个代码是基于OpenCV 3.2的。
@ywb1016 用vpn。
I did not have this problem in the local test, whether you are using the old code?
@emily19941102 你好，没有接触过3D CNN的模型，不太清楚这方面的技术。