-
I am trying to run the docker container on AWS-p2 instance with 1 K80 Tesla Card.
The default config of the instance is
CUDA : 10.1
Driver : 418.67
I tried following the instructions to manua…
-
## 一言でいうと
セグメンテーションのタスクで、色やテクスチャーではなく形状に注目する機構を導入した研究。具体的には、通常の画像を処理するネットワーク(Regular Stream)と並行してAttentionからShape検知を行うShape Streamを導入する。Shapeの学習を行うため、Boundaryに関するlossを組み込んでいる。
: …
-
Hi , Thanks for your codes, when I run the make all -j16 ,I have encountered the following questions and I have no idea how to solver the problems，can you help me? thanks.
make[1]: Is entering the di…
LXWDL updated
7 years ago
-
/bin/sh: 1: ./tools/evaluate: Permission denied
Traceback (most recent call last):
File "main.py", line 143, in
test(model, device, test_loader, args, idx)
File "/home/disk/chengpeisong/p…
cps80 updated
5 years ago
-
I have implemented SCNN using Tensorflow and put the full codes [here](https://github.com/cardwing/Codes-for-Lane-Detection). You can test the code in popular lane detection benchmarks like TuSimple, …
-
The training-finished model can be used for a real-time video?
-
你好，最近我根据您论文中的思路和github代码进行了复现。目前想尝试修改SCNN架构，但是缺少对应的数据集，查阅了相关的代码https://github.com/zwx8981/DBCNN，由于能力有限，没看懂如何生成训练SCNN预训练模型的数据集（包括失真图片和label），您能否提供python版本生成预训练数据集的代码，不胜感激。
还有一个问题，对于DBCNN的优化，您是否有一些思路。
-
Hi, XingangPan. There is a problem when I train SCNN using resnet101_SCNN.prototxt.
I0627 09:18:28.970783 21011 net.cpp:163] Setting up SCNN_D_45/sum
F0627 09:18:28.970795 21011 eltwise_layer.cpp:41…
-
when i pulled the SCNNs in docker, and i entered the scnn directory. when i try to open model.train.py using vim, i found i cannot see the original code. please help!