yeyu

Thank you very much for the work of Dashen. The code is easy to understand and saves new entrants a lot of time. One word - 6666. Full 2D-3D-S Dataset...

Why does the loss function ignore the tag of 255.

5

@CoinCheung Why does the loss function ignore the tag of 255. I look at the data. The label of 255 may be various objects, and each image is almost different....

The technique of reproducing the author's accuracy

4

Although this is not the first time for me to hang out with the author, I would like to thank the author again for the code. I've almost reproduced the...

Bisenetv2

19

Bisenetv2 has come out, and my reproduction accuracy is only 66.7%. The author's paper is 73.6%. This bisenetv2 has better real-time performance. Would God be interested in reproducing it?

How to decompress the data after downloading.

1

How to decompress the data after downloading. thank you.

What tools do you use to implement c++ code of roi-pool layer? Is it Qt? thanks！！！

Do you want to train with pytorch or Python interface?Thank you!

Why do I change "VALID" to "SAME"? Why is the effect of network prediction very poor? Are there pixels not aligned? But I did not find this problem.

1

Why do I change "VALID" to "SAME"? Why is the effect of network prediction very poor? Are there pixels not aligned? But I did not find this problem.

error occurs running on gpu when i transplant the code to windows

2

I parse models/resnet/caffenet_train_iter_2000000.caffemodel under the caffe. I only transplant the part of sparse matrix calculations to caffe(for example, the caffe_gpu_sparse_dense2csr function interface),but CUSPARSE_CHECK () reports error when running to the...

error occurs running on gpu when i transplant the code to windows

1

I parse models/resnet/caffenet_train_iter_2000000.caffemodel under the caffe. I only transplant the part of sparse matrix calculations to caffe(for example, the caffe_gpu_sparse_dense2csr function interface),but CUSPARSE_CHECK () reports error when running to the...