rw1995

Results 21 comments of rw1995

大佬,我已经在跑这个refinedet_train_test代码了,但是我发现,电脑很卡,16G+2070+8700K,不知道为什么 第二,我想问下大佬,这个100轮怎么设置,我能减少批量输入的图片减少电脑的卡顿吗?

Hi, anjany, thanks for you reply, Now, i know,how to convert the json, I'll summarize your plan in Chinese。 在脊椎分割方案中,对应的质心坐标是在数据集ASL方向得到的结果,所以大家在进行质心训练的时候,请将数据集转换到对应的ASL方向。输入的坐标需要将所有的值除以对应的spacing,然后可以利用itk-snap软件进行查看啦~~~, 请帮我点个赞哦,哈哈哈,看了一个下午的代码才想通的 / emoji

论文中有原话 ![image](https://user-images.githubusercontent.com/37976371/141227595-77d68340-9ad4-47eb-8d72-eb2155626b53.png)

请问为什么需要weight patch

> @DW1HH > The reason that leads to the error is the model file contain the in_place operation, you need trun off the switch of in_place in models/fssd_vgg.py sorry, i...

like this? ` Loading base network... Initializing weights... train.py:98: UserWarning: nn.init.kaiming_normal is now deprecated in favor of nn.init.kaiming_normal_. init.kaiming_normal(m.state_dict()[key], mode='fan_out') Loading Dataset... Training FSSD_VGG on VOC0712 avg_loss_list: [0.0] /home/rw/anaconda3/envs/pytorch0.4.0/lib/python3.5/site-packages/torch/nn/functional.py:2539: UserWarning:...

i replace fssd_vgg.py ` for k, v in enumerate(self.extras): # x = F.relu(v(x), inplace=True) x = F.relu(v(x)) ` and it works ,but found L: nan C: nan S: nan,so i...

左侧为何这么宽?太不舒服了 @cxasm @littzhch

@Kenshin 还 chatgpt貌似又改变啦, 能否重新适配下?