qinxianyuzi

reduce time not obviously

1

Hi, thank you for your meaningful job. I change the model in benchmark.py and set batch size 64. device = "cuda" # model = nn.Sequential(*[nn.Linear(128, 128) for i in range(100)]).to(device)...

您好，我想要您的超高精度模型,谢谢。我的邮箱是[email protected]

删除残差连接后，速度没有发生变化

1

你好，这是很棒的工作。 我删除残差连接后，速度没有发生变化（甚至稍微慢些，但网络输出值是相同的），请问能分享一下测试代码吗？谢谢！

the deploy.prototxt of LargeMargin_Softmax_Loss

5

After finished training. How can I use LargeMargin_Softmax_Loss in the deploy.prototxt? thank you!

[Windows 10] [C LIBRARY] : PNG decoding is slower than OpenCV

16

Hello, thanks for helping: I try to use wuffs to open png files within a c++ project. I use vs2017 to compile this code, but PNG decoding is slower than...

内存溢出

3

各位，在卷积中添加group参数后（比如resnext网络），训练过程中内存无法释放，有人遇到类似问题吗？

model_name should be one of

1

Then I ran the following commands: bash mnext_efficient_s.sh 1 ValueError: model_name should be one of: efficientnet_b0, efficientnet_b1, efficientnet_b2, efficientnet_b3, efficientnet_b4, efficientnet_b5, efficientnet_b6, efficientnet_b7, i2rnet_b0, i2rnet_b1, i2rnet_b2, i2rnet_b3, i2rnet_b4, i2rnet_b5, i2rnet_b6,...

106个关键点的仿射目标点

7

@zuoqing1988 您好，我发现您代码中对齐仿射CropImage时用5个关键点的，请问能告知106关键点的对应的关键点是多少？谢谢

How to config the exploration

1

Thanks for your help. How to config the exploration in training codes. 

smu能转成tensorrt吗

1

你好，很棒的工作。请问smu能转成tensorrt吗？谢谢