Initial steps.
This commit is contained in:
25
extras/mmpose/README.md
Normal file
25
extras/mmpose/README.md
Normal file
@ -0,0 +1,25 @@
|
||||
# Finetuning MMPose models
|
||||
|
||||
See: <https://mmpose.readthedocs.io/en/latest/user_guides/train_and_test.html>
|
||||
|
||||
<br>
|
||||
|
||||
```bash
|
||||
docker build --progress=plain -f extras/mmdeploy/dockerfile -t rpt_mmdeploy .
|
||||
|
||||
./extras/mmpose/run_container.sh
|
||||
```
|
||||
|
||||
```bash
|
||||
cd /mmpose/
|
||||
|
||||
pip3 install "albumentations<1.4"
|
||||
|
||||
python3 ./tools/train.py \
|
||||
/mmpose/projects/rtmpose/rtmpose/body_2d_keypoint/rtmpose-m_8xb256-420e_coco-384x288.py \
|
||||
--amp \
|
||||
--cfg-options \
|
||||
load_from=https://download.openmmlab.com/mmpose/v1/projects/rtmposev1/rtmpose-m_simcc-body7_pt-body7_420e-384x288-65e718c4_20230504.pth \
|
||||
train_batch_size=16 val_batch_size=16
|
||||
|
||||
```
|
||||
Reference in New Issue
Block a user