GuoxingYan

项目商用

3

请问您这个项目可以商用吗？

[https://github.com/CSAILVision/semantic-segmentation-pytorch/blob/master/test.py](url) 82 line pred = as_numpy(pred.squeeze(0).cpu()) .cpu()is very slow

请问可以商用吗？ https://github.com/jjprincess/PMTD

resnet_v1_101-0000.params

10

Resnet_v1_101-0000.params Can't access, can upload a copy to BaiDu Yun?

(nil) (unknown) Aborted (core dumped)

3

When I try to run you training script to train a **resnet101** cascade faster rcnn, I encounter a error like this: F0530 22:30:27.787274 1077 syncedmem.cpp:71] Check failed: error == cudaSuccess...

Does your program have a detection file like py-faster-rcnn/tools/demo.py?

为什么prune.py跑出的map和之前train顺便跑出来的不一样？

4

train里的精度  prune显示的精度，p下降了好多。  +------------+----------+----------+ | Metric | Before | After | +------------+----------+----------+ | mAP | 0.882270 | 0.881940 | | Parameters | 61523734 | 7517869 | | Inference |...