崔星星
Hi,all, when I train LSTM network, error appear" Message type "caffe.LayerParameter" has no field named "lstm_param""? I have installed the latest caffe version from the master branch. According to my...
我的也是，因为windows上python3.6还没出现兼容的caffe，依赖的库版本有几个不一样，如protobuf，lmdb，libboost，我还是放弃了，比较折腾，要用就用python2.7，配置方便
@Amanda-Barbara please download windows sdk10.0 from https://developer.microsoft.com/en-us/windows/downloads/windows-10-sdk and install it
I see that you have updated the “thirdparty.rar” file to support cuda9.0, but in turn CUDA 8.0 is compatible? @happynear
@sbeeve， for windows-os example: ```json "matlab.linterConfig": "C:\\Program Files\\Polyspace\\R2021a\\bin\\win64\\mlint.exe", "settingsSync.ignoredSettings": [ "-matlab.linterConfig", "-matlab.matlabpath", "-matlab.mlintpath" ], "matlab.matlabpath": "C:\\Program Files\\Polyspace\\R2021a\\bin\\matlab.exe", "matlab.mlintpath": "C:\\Program Files\\Polyspace\\R2021a\\bin\\win64\\mlint.exe", "files.associations": { "\"*.m\":\"matlab\"": "" } ```
Hope to support custom training in the future and increase flexibility!
hi, @eltabbal The [segment anything model](https://www.mathworks.com/help/images/getting-started-with-segment-anything-model.html) is now integrated in the R2024a.
> @mystao Have you solved the problem about "out of memory" ? I want to train by myself, but my GPU is 1050, could you give me some advice ?...
> @AlexeyAB thank you! In fact, I am using [resnet18](https://github.com/pjreddie/darknet/blob/master/cfg/resnet18.cfg) as backbone, and download the weights from [this page](https://pjreddie.com/darknet/yolo/) and this [link](https://pjreddie.com/media/files/resnet18.weights) The tail of my modified cfg looks like...