Yusuke Niitani

With this weight ~https://drive.google.com/open?id=1UJ5LMwiyK-k1g-bv-4dmiSKej7LA_2NV~, demo works https://drive.google.com/open?id=1UJ5LMwiyK-k1g-bv-4dmiSKej7LA_2NV ```bash $ python3 demo.py --gpu 0 --model mask_rcnn_fpn_resnet50 --pretrained-model chainercv_point_rcnn_fpn_resnet50_coco_converted.npz --mode keypoint IMG_PATH.jpg ``` ### Evaluation converted (bilinear interpolation with kernel size 2):...

TODOs - [x] Use balanced sampling to include negative samples for keypoint head loss - [x] use within_bbox to decide invalid boxes - [x] multi scale training

Transition is working at least for inference. ``` mmAP (all): 0.639657 mmAP (large): 0.73500156 mmAP (medium): 0.58247757 ```

`python3 eval_keypoint_detection.py --model keypoint_rcnn_fpn_resnet50 --pretrained-model coco --gpu 0 ` mmAP (all): 0.6396571 mmAP (large): 0.73500156 mmAP (medium): 0.58247715 このときと https://github.com/chainer/chainercv/pull/810#issuecomment-473249333 同じ

Thanks!

I remember extracting label names from that text file. (also in csv format https://github.com/CSAILVision/semantic-segmentation-pytorch/blob/master/data/object150_info.csv) I should have been more carefully with parsing names.

Nice PR. Please delete `lsp` files. Also, add a link to the documentation.

Please wait until https://github.com/chainer/chainercv/pull/787 is merged

I made a simpler benchmark script to measure time to load images with crop. ```python from PIL import Image import numpy as np from chainercv.utils import write_image import time import...

Yes. That is my conclusion too. I am guessing that most of the time is spent decoding `jpg` image, and it seems that `cv2` has a better decoder.