Closed qilinli closed 6 years ago
Hi, @qilinli ,
You are right. Because ASPP doesn't exit in ResNet, its weights are initialized default initializer of each layer.
For example, the weights of layers_lib.conv2d
is, I believe, initialized by xavier_initializer(), etc.
@rishizek I see. It seems that nowadays no one explains random initialisation anymore :). BTW, I am also curious about the use of Batch Normalisation (BN) layer.
Hi @qilinli , let me answer your questions as far as I know,
mean or variance of batch x height x width
by each feature. Thus, the size of input image is irrelevant for this model.@rishizek Thanks for sharing your thoughts. I have some different opinions.
Thanks for telling me this. BN parameters are following the same parameter sharing rule of conv layer. I definitely missed this. :(
FYI, the author of deeplab released an official version of deeplabv3+ at https://github.com/tensorflow/models/tree/master/research/deeplab
Hi @qilinli , No problem. Thank you for shareing your thoughts. Let me comment about Q1:
Yes, I'm aware with that even though I don't have sufficient time to investigate their code in detail yet ;)
Hi, @rishizek. Thanks for sharing your code. I am a bit of confusing about the weight initialization of Deeplabv3. As described in the original paper, the backbone of deeplabv3 is ResNet, which is pre-trained with ImageNet. How about the ASPP module? It is not applicable to ImageNet right? How do you initialize ASPP module?