vasgaowei

I will write a **README.md** file for **pytorch1.0** branch later. The operations you mentioned **RoiRingpooling, RoIAlign, NMS** are moved to **ops** folder. And before importing these modules, you should complie...

I am sorry, last week I made a update for supporting varied numbers of ROIs for forward operations in case of not enough GPU memory. And you can fix the...

1. You are right. The cls_det_loss/20 is the global entropy loss for global entropy model. And 'refine_loss_1' and 'refine_loss_2' are losses for localization branch 1 and localization branch 2. 2....

For pytorch 1.2 branch, you com compile by command: **bash make_cuda.sh**.

You can try to check if the **.so** file for nms_cpu exists. Also you can use **nms** implementated in **torchvision**.

RoiRingPoolingFunction is similiar with RoiPoolFunction but with a few differences, and I suggest to read the paper 《**[ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization](https://arxiv.org/pdf/1609.04331.pdf)**》to know more about the...

There is an error in **demo.py**. Just modifying `from model.nms_wrapper import` in **demo.py** to `from ops.nms import nms` corrects it. And after you compile nms successfully, is there any error...

The **pytorch1.0** branch supports PyTorch version **1.0~1.4**. Higher versions may encounter errors.

1. My code is based on faster-rcnn. And "bbox_pred" in the faster rcnn code is the regression network's output for each proposal. And a proposal is represented by a tuple...

The **RoiRingPoolFunction** is adopted from another eccv paper, you can read this paper [https://arxiv.org/abs/1609.04331](url) for better understanding.