yehao

Hello, can i get your contact information

1

I want to contact you with more implementation details, can you post your email or other contact information? Thank you in advance!

How to use model to detect objects?

3

Hi，you link provides *.caffemodel, but I do not find solver.prototxt in root directory(like faster_rcnc_test.pt in py-faster-rcnn). By the way, Should I use tools/demo.py(like py-faster-rcnn) to detect objects?

关于训练

4

你好，有几个问题请教下： １.首先使用在imagenet训练好的mobilenet v3分类模型来做分类finetune，这部分新添加的分类数据和检测数据有关联吗？假如有关联，都是５个类别，是需要分别收集这５个类别对应的分类数据和检测数据吗？

train VGG-SSD from scratch get a better result

1

Hi, I follow your experiment setting, train VGG-SSD from scratch(no pretraining, no BN in the backbone, no BN in the head), use the following hyper param(caffe): - train batch size:...

I modify main.cpp to support for video detection, it has the error: `runtime.cpp (16) - Cuda Error in allocate: 2 terminate called after throwing an instance of 'nvinfer1::CudaError' ` I...

why not use lr_mult, decay_mult like {1, 1, 2, 0}?

3

In alexnet network, it uses lr_mult/decay_mult param {1, 1, 2, 0}, In squeezenet, it doesn't set param, so caffe uses its default value, lr_mult and decay_mult is default set to...

Problems about training dataset

1

Hi, @chuanqi305 In README.md, you say > with pretrained weights on VOC0712 and mAP=0.643 I found that this sentence is similar to the one in mobilenet-ssd, In mobilenet-ssd's README.md, it...

why solver.prototxt is divided into solver_train.prototxt and solver_test.prototxt?

3

I am confused about solver_train.prototxt and solver_test.prototxt. - different base_lr set, lr=0.0001 in solver_train.prototxt and lr=0.001 in solver_test.prototxt - different gamma set, gamma=0.5 in solver_train.prototxt and gamma=0.1 in solver_test.prototxt -...

报错

1

ImportError: No module named flask.ext.sqlalchemy 还要requirements.txt里面什么都没有啊

Can you share pelee classification newwork on imagenet?

6

Hi @Robert-JunWang, I want to train pelee classification network, I am confused about solver.prototxt, Can you provide your train file including train.prototxt, test.prototxt and solver.prototxt? Thank you in advance!