Leo Chenghui Li

Is there any tricks for training

1

Hi @shicai , I followed Resnet policy for training Densenet-121 yet get 72% for top1, I'd be appreciated if there is any tricks to share to reach the paper acc....

BatchNorm consuming a lot of time

2

Hi shicai, Have you evaluated the time performance of mobilenetv1 & v2? I found that the bn layer and linear layer are very time consuming both in CPU-only and GPU-only...

Not getting a good acc

6

Hi @shicai , I tried your depoly prototxt, yet didn't get a good acc result. I'd be appreciated if you could share your solver prototxt for me to check. thanks!

Local hints render area too small

4

Hi, Your repo is amazing and I have been playing around with it. I am wondering is this normal? I have given a lot of user guided points already. But...

Training schedule

3

Hi @camel007 , ShuffleNet is a great idea and the model size is apparently reduced. Have you ever tried to train it on imagenet? I only got 64% as top1...

CSRMM Not Implemented yet

3

Hi @wenwei202 , After finishing the three steps of Resnet20 baseline, SSL and finetuning, I am having trouble evaluating the performance of finetuned models. I changed the conv mode to...

Not getting a good accuracy

21

Hi @farmingyard , I ran your deploy prototxt on imagenet this weekend yet still got a bad accuracy output. (exactly the same prototxt I'd be appreciated if you could share...

hpp/cpp/cu files compile error

11

Hi @farmingyard , I am new to caffe. I got an error saying like "class caffe::ConvolutionParameter’ has no member named ‘kernel_size_size’" in conv_dw_layer.cpp when I'm trying to compile. Any idea...

Training Accuracy problem

6

Hi @farmingyard , Have you trained with your prototxt and do you reach the paper acc? I followed the resnext training policy yet have 1%~2% difference below the paper acc....

Hi Kuangliu, Nice job on achieving good result on Cifar10. Have you evaluated the speed performance of all the experiment models? It seems Mobilenet v2 cannot achieve significant speed improvement...