SingL3

Is the confidence only used for sorting?

4

Hi, I read the evaluation code of wider face dataset and compare it with this repo. As I can see, the confidence is only used for sorting the detection result...

In training phase, we use SoftmaxWithLoss Layer and replace it with Softmax in testing. If I use FocalLoss in training, is it still replaced by Softmax?

Can this OHEM method be used in Faster R-CNN? If yes, how to write the prototxt? Thank you!

Loss keep increasing

2

Hello! I am trying to train on my own dataset, and I got a loss like below: > [Dec21-15-15-54_user-SYS-7048GR-TR_step][FPN_SE_ARP.yml][Step 201 / 150000] loss: 0.041566, lr: 0.002250 time: 1.166229, eta: 2...

Can this implementation handle images without objects?

2

Hello! I want to train a model with some samples that has no objects ( just background ). Can this implementation handle that?

A problem about branch 0.4

2

Hello, I am trying to run SSD_vgg in branch 0.4. > python train_test.py -d VOC -v SSD_vgg -s 512 -b 16 And I got the below error: > Traceback (most...

Can this implementation handle images without objects?

6

Hello! I want to train a model with some samples that has no objects ( just background ). Can this implementation handle that?

TypeError: No to_python (by-value) converter found for C++ type: class caffe::LayerParameter

2

我想在windows下跑Faster RCNN，使用C++调用，使用了py-faster-rcnn的版本，其中的rpn是使用python layer实现的。当我运行的时候，就有以下错误： TypeError: No to_python (by-value) converter found for C++ type: class caffe::LayerParameter 我注意到您提供的caffe版本中有proposal layer，我看了一下源码跟rpn的源码很像，所以我直接在网络文件中将rpn替换成这个proposal layer，但是系统就直接死机了。 我在ubuntu下跑这个C++调用faster-rcnn的程序是没有任何错误的，请问有什么解决办法吗？ 谢谢！

In training phase, we use SoftmaxWithLoss Layer and replace it with Softmax in testing. If I use FocalLoss in training, is it still replaced by Softmax?