zijunwei

patch_embed related questions.

1

Hi, Thanks for providing the code! I have a couple of questions regarding patch_embedding. 1. in https://github.com/whai362/PVT/blob/v2/segmentation/pvt.py#L148, the last layer you added one more embed feature than the num_patches but...

Model NOT working on watermark removal examples out of specified test data

1

Hi, thanks for sharing this code. I was impressed by the watermark removal results provided by this model. However, when I was trying this model (I didn't do any modifications,...

bug in resnet.py

1

line 283 of resnet.py , should it be `weight_decay=FC_WEIGHT_DECAY)` ? Also, it might be better for each variable_scope, for example: `with tf.variable_scope('scale1'): ` add resue flag at the end `with...

Correct me if I'm wrong: the model declared here is different from the original Caffe model from the [author](https://github.com/KaimingHe/deep-residual-networks/blob/master/prototxt/ResNet-152-deploy.prototxt) The shortcut layer in this model is added with a non-identity...

random loading data sequence

1

Technically this is not an issue, but I feel more stable if this can be fixed. The possible problem lies in 'dataset.lua' around line 105. When function `dir.getdirectories(path)` seems to...