HsuTzuJen

Hi, I received a data "10.H264" by jQuery, but nothing happened on the canvas after p.decode(data). No error happened in the console. I can play the 10.H264, and it is...

the number of weights for logit is 85164*512. It's about 43.6M! But we do not need the logit after training right? I am wondering if it is possible that we...

Hi, I use the network "tensorflow/tensorflow/contrib/slim/python/slim/nets/resnet_v2.py" instead, and it works! The model size is down to 630M for MS1M and 330M for VGGface2. And I can train the network with...

I did not read the paper yet, but I will do it after reading it. I am now interested in implement NASNet and training with your code.

Hi, I added the same numbers of PRelu and Batch_norm layers to resnet_v2.py. The model size is 640MB with MS1M dataset. Differences: 1.It seems that there is no gamma in...

Hi, I just found that the first conv and bn should be followed by a 3x3 stride2 pooling layer, but it is not in L_Resnet_E_IR.py. After adding the pooling layer,...

@TengliEd I am using ResNetV2, and I achieve acc 0.995 test on lfw now. I think L_ResnetE_IR is improved from ResNet, but I have not tried to train it more...

@TengliEd I think you can read the paper about ResNet first"https://arxiv.org/abs/1512.03385". There are net models in "https://github.com/tensorflow/tensorflow/tree/master/tensorflow/contrib/slim/python/slim/nets", and you can try to revise the code. It's more simple to implement...

@TengliEd Since each unit bottleneck is modified, the number of units should be too. They count layers by the number of convolution layer. There are 2 conv in each unit...

I just compared the two models: ResNetV2(50 layers): 16 3x3 convs and 32 1x1 convs in 4 blocks. L_Resnet_E_IR(50 layers): 48 3x3 convs in 4 blocks. The size of one...