Skip to content

[Enhancement] Add a visualize script for inference result comparation. #2013

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 5 commits into from

Conversation

IRONICBo
Copy link

Motivation

  1. add a visualization script to visualize the backend inference results, refer to the visualization section in tools/deploy.py
  2. script parameters include deployment config, model config, backend model path, image list, pytorch model (ckpt, optional), visualization result save path, etc.
  3. require that when the pytorch model is passed in, the back-end results and the pytorch results graph are concatenated for comparison

Modification

tools/visualize.py

Use cases (Optional)

Run command:

python mmdeploy/tools/visualize.py \
    --deploy-cfg mmdeploy/configs/mmdet/detection/detection_onnxruntime_dynamic.py \
    --model-cfg mmdetection/configs/faster_rcnn/faster-rcnn_r50_fpn_1x_coco.py \
    --deploy-path mmdeploy_model/faster-rcnn/end2end.onnx \
    --checkpoint checkpoints/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth \
    --test-img mmdetection/demo/demo.jpg mmdetection/demo/demo2.jpg \
    --save-dir mmdeploy_model/faster-rcnn \
    --device cuda

Inference result:
image

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant