-
CPN
《Cascaded Pyramid Network for Multi-Person Pose Estimation》
### 简介
- Paper: [CVPR2018](https://arxiv.org/abs/1711.07319)
- Code: [pytorch](https://github.com/GengDavid/pytor…
-
## 🌟 Epic
### Moderation
![image](https://user-images.githubusercontent.com/1238238/55630878-0cfc3e00-57b7-11e9-96d5-6f816a5d4a5e.png)
- [X] List of Reported Users, Posts & Comments
- [x] Reen…
-
Specifically, I am referring to this
```
widerface_640 = {
'num_classes': 2,
#'lr_steps': (80000, 100000, 120000),
#'max_iter': 120000,
'lr_steps': (40000, 50000, 60000),
…
-
## ❓ Questions and Help
Hi Kaihua, thanks for the great work. I have several questions regarding the feature extracting. I found in code that both union feature and roi feature are extracted from FPN…
-
related paper
|摘要|
|---|
|In this work, we revisit atrous convolution, a powerful tool to explicitly adjust filter’s field-of-view as well as control the resolution of feature responses computed …
-
### Motivation for the feature
@valosekj showed interest in trying the method implemented in [Perone et al., 2018](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5899127/). The repo for the code is her…
-
Hi Charles,
Thank you for your interest and implementing Mask R-CNN!
I would like to clarify some descriptions in your Readme (which may suggest misunderstanding of our work):
"The original w…
-
Hi!
Do you plan to provide a tiny version of the network with, for instance, MobileNetv3 as backbone which can be run even on embedded devices?
If not, do you have any hints about how to change …
-
I have dense images, 1024 * 1024 but there are 2000 same objects in every image. There are two strategies I can think of, hope you can give me some suggestion.
1. Train on small patch (128 * 128) a…
-
Hi @waleedka ,
This was one of the posts today in the competition (copied below). it is about a new normalization technique called Group Normalization. The paper reports that it helps to speed up …