iTom
- version: brokenaxes 0.5.0 I'm using `clip_on=False` when plotting like this: ```python import matplotlib.pyplot as plt from brokenaxes import brokenaxes import numpy as np fig = plt.figure(figsize=(6,4)) baxes = brokenaxes(ylims=((0,30000),(75000,85000)),...
Hi, I wonder, why the missing rate is halved [here](https://github.com/XLearning-SCU/2021-CVPR-Completer/blob/main/get_mask.py#L17)?
Hi, I have run you codes of **CMHH** on flickr of 64-bit hash, with data & CNN-F weights provided by you, and it's stuck at: - `max MAP: MAP(i->t): 0.7970,...
Hi, I ran your code and it can re-produce the performance on flickr, but fails on nus-wide. Did you use different parameters ? can you provide them? thanks
When I run an toy example in my computer with PyTorch 1.9.0, while giving the right answer, it also gives me the following warning: ```shell C:\Users\iTom\Desktop\pytorch-lasso\lasso\linear\utils.py:36: UserWarning: torch.cholesky is deprecated...
Hi, I want to extract the doc2vec features of those sentences in MS COCO. But I'm not quite sure how the preprocessing is performed. It's said that the articles are...
I found a bug in your code of calculating mAP, which lies in the function [get_AP](https://github.com/kunhe/TALR/blob/master/%2Beval/AP.m#L57), originating from [the wrong construction of the recall difference list](https://github.com/kunhe/TALR/blob/master/%2Beval/AP.m#L65). I advise to change...
with the [lambda expansion expressions used in AngleLayer](https://github.com/Joyako/SphereFace-pytorch/blob/master/module/sphere_face.py#L70), error occurs when saving the model: *Can't pickle local object 'AngleLayer.\_\_init\_\_\.\'*
Flow model 笔记中的 Eq (8) 第二个等号，分子是不是应该将 $f^{-1}$ 改成 $f$？由 [1] 的介绍： > 可逆函数的雅可比矩阵的逆矩阵即为该函数的反函数的雅可比矩阵 所以 Eq (8) 中 $\frac{\partial f^{-1}(X)}{\partial X}$ 是与 $\frac{\partial f(Z)}{\partial Z}$（而不是 $\frac{\partial f^{-1}(Z)}{\partial Z}$）互为逆矩阵，它们的行列式互为倒数。 --- 1. [雅可比矩阵](https://baike.baidu.com/item/%E9%9B%85%E5%8F%AF%E6%AF%94%E7%9F%A9%E9%98%B5/10753754)
Hi, I'm running your code and find that the performance (i.e. hamming loss) is slightly worse than that stated in the paper. By checking the code I find some, I...