search

oyam / Semantic-Segmentation-using-Adversarial-Networks

Chainer Implementation of Semantic Segmentation using Adversarial Networks
https://arxiv.org/abs/1611.08408
MIT License
103 stars 41 forks source link

How to choose model? #8

Open ldhl103 opened 5 years ago

ldhl103 commented 5 years ago

Hello Oyam,

You said you used FCN-VGG16. However, there is " n_class=1000 " in your models/vgg16.py code. It should use ImageNet with 1000 classes.

If I add "-s fcn32s" in command, I always got the shape error " ValueError: could not broadcast input array from shape (4096,25088) into shape (4096,512,7,7)"

Do I need to reshape the input data?