Shunta Saito

Sorry for inconvenience, there are some fatal bugs maybe in data processing part. I'm trying to find them now and will update if I could fix them and confirm the...

@HardikChauhanSA Hi, thank you for trying this repo. We've released the cleaned version of Faster R-CNN inference & training codes in ChainerCV: https://github.com/chainer/chainercv . Please check the ChainerCV repo instead...

@wkentaro Great! Thank you for your quite useful PR, I'll check it and will merge it ASAP :)

@yuyu2172 Thanks for the review. I've fixed the points.

Not sure what's blocking this PR, but just resolved conflicts for now.

Oh, I didn’t notice it. I’ll check and update the URL.

Thank you for using my codes. Basically the current prediction script is designed for evaluation and visualization, so it needs to load label data. It calculates mean Euclidean distance between...

@kumasento I haven’t confirmed the reproduction with newer version of ChainerCV code by myself for a long while, so let me check the result using the latest version again. I’ll...

@kumasento I ran the script and got the following result (I removed log lines containing only training error information): ``` $ python calc_weight.py $ MPLBACKEND=Agg python train.py --gpu 0 epoch...

@kumasento OK, thanks for the guide. I'll run the evaluation on the test dataset. Please give me some more time.