Tao Zhong

Results 6 comments of Tao Zhong

Training on cityscapes dataset

I'm having the same problem... Loss went down but the mIoU is only 2%. Have you succeeded in training from scratch? Thanks! > Hi > > Did you get success...

I cannot compress the model

> Hey @dannadori, sorry for the delay, I've been super busy. I can try to check it this weekend, I think `v1.15` had introduced a new version of TF variables....

feat(pointpainting multiframe): add multi-sweep pointpainting

@yukkysaito 一旦待ち状態です。社内データで学習し直してアップロードするになるかもしれません。

ops test core dump

I'm using 1.13. Not sure if is the same problem but I also met FATAL ERROR when using py.test to run the test. ``` test/ops_test.py FFatal Python error: Aborted Current...

Always converges to nearly 22dB

Hi, @MKFMIKU , @lhwcv Have you managed solve the colorful sky problem?

Unable to reproduce the results in Table 1 of the paper

I found the ood_dataset and checkpoint here: https://drive.google.com/drive/folders/1jfMgVTzvlYg5qTF_iEKj0M_ZuJH3ETC9?usp=drive_link But I still cannot reproduce the results using this one.