# 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

```