Fly-dream12
Fly-dream12
Yeah, i have got the json output result and just don't know how to dispaly.
你好，用骨干网络res50训练出来的效果较差，请问提供其他的骨干网络的配置吗？@CPFLAME
@CPFLAME 请问这个项目里面有添加feature loss吗？ 好像没看到，是否能提供一个实例呢
I have made the requires_grad_ as True, but i still can not get the gradient. Can you give some suggestions? @julyxia1992
What codes have you modified? I can not open the image, can you list them? thanks @ddshan
在detectron2架构上的centernet进行grad_cam实现时候总是获取不到梯度,是否在score.backward()可以成功运行时候才会执行_register_hook里面的_get_grads_hook呢? 我这里score是个常量无法反传.望博主指点 @yizt
@yizt centerX 我在提供的detectron2 faster_rcnn中也尝试了,也获取不到梯度.
你好 我发邮箱了 @yizt
有改动 按照你提示的改的. 在 2021-05-26 10:21:58，"mick.yi" ***@***.***> 写道： @Fly-dream12 测试的图片麻烦提供下，faster_rcnn是否有改动，测试命令麻烦提供下，麻烦尽量信息到能够复现问题的粒度 — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.
恩恩 是这样的 但是为什么获取不到梯度呢 At 2021-05-26 11:50:25, "mick.yi" ***@***.***> wrote: @Fly-dream12 感谢您的反馈，我实现的是faster r-cnn，只需要知道第几个proposal就可以了;您用的faster_rcnn_R_101_FPN_base属于FPN，FPN还需要定位proposal是哪一层feature map生成的；faster r-cnn目前直接用的最后一层feature map — You are receiving this because you were mentioned. Reply to this email directly, view...