zx

infogan line 102 when I try to apply it on celebA with size (channel,height,width) as (3,180,180) as the code below, the data from dataloader size is (batch,channel,height,width), but when choose...

MAE公式直接用numpy写是： np.mean ( np.abs ( predict-gt ) ) / len(pictures)，结果和matlab结果不一样，会更低。

我是个初学者, 对音频计算的太困惑了, 基本就没有mfcc算出来一样的

翻译弹出太慢了, 而且段落翻译又失效了只有一句话

2

# 我的浏览器 # 我的插件版本 # 问题描述

At line 220 in [main.py](https://github.com/salesforce/corr_based_prediction/blob/master/main.py), the zero_grad is outside the training stage, the gradients will be accumulated along the training data.

idea没找到自动补全英文的插件, 刚好发现这个库, 但是似乎在.txt .tex这样的文本中都不生效.