Tong He

Add 'middle' value for legend

8

Hi, I am using your script to visualize the difference of the stock price. I want to use `'red'` to represent decreasing and `'green'` to represent increasing. But the HCL...

Questions regarding training parameters

11

First of all thank you for providing the training script and parameters about MobileNetV2 (the first repo I've ever seen). I'm reproducing it for [GluonCV](http://gluon-cv.mxnet.io/) thus have a couple of...

Re-Implementation in GluonCV

4

Hi, We have re-implemented the estimation model in [GluonCV](https://gluon-cv.mxnet.io/). We also achieve slightly higher AP by using pre-trained ResNet with higher accuracy: https://gluon-cv.mxnet.io/model_zoo/pose.html Besides, you mentioned in https://github.com/Microsoft/human-pose-estimation.pytorch/issues/2 that the...

出现了一首歌还没放完就开始播出下一首歌的情况。

2

放着Blue的`You Make Me Wanna`的结尾，突然就响起了`世界が終るまでは…`的前奏……混声了几秒钟才结束。

Pretrained model with global_average_pool=True?

1

Hi, Since `global_average_pool` is an additional option comparing to OpenAI's CLIP implementation, I'm wondering if there'll be any pretrained model released with `global_average_pool=True`? Thanks!

XGBoost 0.81.0.1 breaks MIBayesOpt's tests

5

Hello @ymattu , This is Tong maintaining XGBoost R-package. Recently we are planning to submit version 0.81.0.1 to CRAN. However in the process CRAN alerts that our update breaks your...

Training script release

1

Hi, Thanks for releasing code for this interesting work! Since the loss design and training strategy forms a crucial part of the paper, will there be plan to release the...