alitor
alitor
> Our code require a GPU to run, please install cuda and I doubt that a VM can do this. 老铁，我的代码跑到中间断了，百度mxnet版本有问题，修复之后怎么继续接着跑呢？ python experiments/dff_rfcn/dff_rfcn_end2end_train_test.py --cfg experiments/dff_rfcn/cfgs/resnet_v1_101_flownet_imagenet_vid_rfcn_end2end_ohem.yaml 正在跑这个代码
l use only 1 gpu and get the mAP=0.6699
@ParanoidW @1292765944 l get the mAp=0.6699 with only 1 gpu ? can you send me about your result log ? thank your very much ? my email: [email protected] thank you!
> @1292765944 I have the same situation,two gpus and got [[email protected]](mailto:[email protected]) did you solve this question? can you send me about your result log ? thank you very much !...
> Ok how about your mAP? my mAP = 0.6699 ,l also don't achieve the claimed result can you contact me with qq my qq 1069919773 thank you !
> I read the R-FCN paper. > > After the Resnet101 they append a randomly initialized 1024-d 1x1 convolution layer to reducing dimension. > However, your implementation append the a...
楼上都是中国老铁吧？这个问题好像是mxnet版本和论文使用的版本不一致。 我也遇到了这个问题，我是按照mxnet的官网安装的 没有cuDNN加速，模型跑起来特别慢。 最后我建立了一个qq群，希望真心研究学习的小伙伴能加入。964957091
do you known why?