Open yswang1717 opened 4 years ago
Sorry for the late reply. Those three models have actually not been released since we trained these models in our earlier stage with Tensorflow. However, since they were trained from scratch, you can just modify the code to reproduce them, but it will be inefficient for Cityscapes because they are designed for lower resolution such as CamVid
Hello, I appreciate for your kind responses for every questions! now I'm working on the implementations of all hardnet models, but I couldn't find the details of the "first_channel" and "ch_list" on your repo for FC-HarDNet 68,76,84. your paper only describes on BLK depth, Growth rate, m in table 3.
For example, you specified first_ch = [32, 64] / ch_list = [ 128, 256, 320, 640, 1024] for HarDNet68. first_ch = [16,24,32,48] / ch_list = [ 64, 96, 160, 224, 320] for FC-HarDNet70.
Could you please tell me the how many convolution layers are in front of FC-HarDNet and ch_list?