search

TuSimple / TuSimple-DUC

Understanding Convolution for Semantic Segmentation
https://arxiv.org/abs/1702.08502
Apache License 2.0
610 stars 118 forks source link

Questions #30

Closed Youngkl0726 closed 6 years ago

Youngkl0726 commented 6 years ago

Why the num_filter in the "res1_3 = Conv_BN_AC(data=res1_2, num_filter=128, kernel=(3, 3), name='conv1_3_3x3', suffix='conv1_3_3x3', pad=(1, 1), stride=(1, 1))", which is in the resnet.py, is 128? I think it may be 64.

wpqmanu commented 6 years ago

There is no specific reason for setting the number. You can try both.