Isaac Ge

How do you train DRN-D-22?

3

I trained it with `python3 segment.py train -d -c -s 896 --arch drn_d_22 --batch-size 14 --epochs 250 --lr 0.001 --momentum 0.99 --step 100`, and multi-scale test only get 66.49. It...

What GPU do you use to train?

1

> If you use 8 GPUs for 16 crops per batch, the memory for each GPU is more than 12GB. My GTX 1080Ti has only 11171MiB even.

I find if train with `CUDA_LAUNCH_BLOCKING=1`, then the `segment.py` will stuck like below:  I google and google again, no one compains he will stuck when use `CUDA_LAUNCH_BLOCKING=1`.

The code just averaging the vars from all GPUs, not computing the total var in all GPUs.

Feature right prompt

9

I add a simple `build_rprompt` function and two rprompt about user and host. I think `RPROMPT` is suitable to place user and host these **stable** information while the `PROMPT` hold...

I am glad that #24 is solved, however I find the lastest version is 0.5 which does not contain this fix...

Reproduce failed.

2

I write resnet.symbol by myself and use it as pretrained model to train TuSimple-DUC, and keep cfg consistent with the paper except cropped size. See my [fork](https://github.com/acgtyrant/TuSimple-DUC/tree/tyrant). However, train_IoU is...

我猜这代理可以绕过 Steam 对国区 IP 留言的限制。 ``` ~ 欢迎使用AnotherSteamCommunityFix v1.2.2 ~ Author: Makazeu [ Steam: Makazeu | Weibo: @Makazeu ] main.go:46: 正在获取IP地址，请稍候~ lookup.go:26: 使用OpenDNS_2解析域名成功，耗时: 264.793076ms main.go:53: 域名解析成功： 23.14.169.3 程序已启动，请不要关闭该窗口！ 对于Mac和Linux用户，使用nohup命令运行程序可使其在后台运行。 └─...

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation says: > Finally, please note that to encourage reproduction of our results we release the Caffe implementation of all the variants...