Kevin mei

Can I change the environment？I must need python3.6 and tf1.8

1

Can I change the environment？I must need python3.6 and tf1.8

after network-slimming,the size of modell are the same as premodel?

4

after network-slimming,the size of modell are the same as premodel?

Can lsoftmax be transformed into ONNX

1

Can lsoftmax be transformed into ONNX?

No module named 'utils.ssd_mobilenet_utils'

1

No module named 'utils.ssd_mobilenet_utils' it does not work， thanks

fail to load pre-model

1

model = torch.load(‘mbv3_small.pth.tar‘, map_location='cpu') print('Loading base network...') weight = model["state_dict"] base_net = torch.nn.DataParallel(base_net) base_net.load_state_dict(weights) The program has been running, no response

## Env - GPU, Nano - OS, - Cuda version 10.2 - TensorRT version ## About this repo repvgg ## Your problem sudo ./repvgg -s RepVGG-B2 // serialize model to...

if img_ch =3,RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0

1

if img_ch =3,RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0 If img_ch =3 ，sometimes this error occurs. more detail information： batchsize = 1，the code can...

if img_ch =1 ，output with shape doesn't match the broadcast shape

1

if img_ch =1 ，output with shape doesn't match the broadcast shape Input is grayscale image. Thanks!

jetson nano repvgg make failed

1

Env GPU, Nano OS, Cuda version 10.2 TensorRT version About this repo repvgg Your problem sudo ./repvgg -s RepVGG-B2 // serialize model to plan file i.e. 'RepVGG-B2.engine' finished load weights...

组归一化（GroupNormalization）代替批量归一化，会影响预训练权值吗

1

组归一化（GroupNormalization）代替批量归一化，会影响预训练权值吗