Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising (TIP, 2017)
1.42k
stars
534
forks
source link
The Wrong when I using the \DnCNN\TrainingCodes\DnCNN_TrainingCodes_v1.1\Demo_Train_model_64_25_Res_Bnorm_Adam.m #100
Open
yihaodong1 opened 9 months ago
以下是报错 错误使用 vl_nnconv FILTERS are larger than the DATA (including padding). 出错 vl_simplenn (第 97 行) res(i+1).x = vl_nnconv(res(i).x, l.weights{1}, l.weights{2}, ... 出错 DnCNN_train>process_epoch (第 182 行) res = vl_simplenn(net, inputs, dzdy, res, ... 出错 DnCNN_train (第 111 行) [net, state] = process_epoch(net, state, imdb, opts, 'train'); 出错 Demo_Train_model_64_25_Res_Bnorm_Adam (第 41 行) [net, info] = DnCNN_train(net, ...
我debug了一下,好像是因为在vl_simplenn.m的第95-117行对层的种类判断的时候没有对bnorm层处理,不知道是我哪里运行错了吗