mirrors
/
ScaledYOLOv4
mirror of https://github.com/WongKinYiu/ScaledYOLOv4.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Update README.md

pull/108/head
Kin-Yiu, Wong 2020-12-21 15:39:16 +08:00 committed by GitHub
parent 9eecfa2a7b
commit bb6ee39944
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
README.md
View File

@ -32,9 +32,9 @@ This is the implementation of "[Scaled-YOLOv4: Scaling Cross Stage Partial Netwo
# create the docker container, you can change the share memory size if you have more.
nvidia-docker run --name yolov4_csp -it -v your_coco_path/:/coco/ -v your_code_path/:/yolo --shm-size=64g nvcr.io/nvidia/pytorch:20.06-py3
# install mish-cuda, if you use different pytorch version, you could try https://github.com/JunnYu/mish-cuda
# install mish-cuda, if you use different pytorch version, you could try https://github.com/thomasbrandon/mish-cuda
cd /
git clone https://github.com/thomasbrandon/mish-cuda
git clone https://github.com/JunnYu/mish-cuda
cd mish-cuda
python setup.py build install
@ -42,27 +42,6 @@ python setup.py build install
cd /yolo
```
For using pre-trained models:
```
cd /yolo
git clone https://github.com/thomasbrandon/mish-cuda mc
cd mc
# change all of name which is mish_cuda to mish_mish and build.
# 1. mc/src/mish_cuda -> mc/src/mish_mish
# 2. mc/csrc/mish_cuda.cpp -> mc/csrc/mish_mish.cpp
# 3. in mc/setup.py
# 3.1 line 5 -> 'csrc/mish_mish.cpp'
# 3.2 line 11 -> name='mish_mish'
# 3.3 line 20 -> 'mish_mish._C'
python setup.py build
# rename mc/build/lib.xxx folder to mc/build/lib
# modify import in models/common.py
# line 7 -> from mc.build.lib.mish_mish import MishCuda as Mish
```
## Testing
```