shata-wh

Results 5 comments of shata-wh

自己数据集的实现

I made my own data as Cityscapes Dataset format, but my dataset only has 6 classes labeled 0-5. I change the "self.label_mapping" in lib/datasets/cityscapes.py: self.label_mapping = {0: 0, 1: 1,...

How to deal with the error：AttributeError: SyncBatchNorm is only supported within torch.nn.parallel.DistributedDataParallel

Maybe in bn_helper.py: # BatchNorm2d_class = BatchNorm2d = torch.nn.SyncBatchNorm BatchNorm2d_class = BatchNorm2d = torch.nn.BatchNorm2d

RuntimeError: could not create a primitive descriptor for a matmul primitive

While running inference on the gpt-j model，I also encountered this problem.

Bootstrapping Bazel-6.0.0 from source in QEMU with RISCV image

> Able to build the binaries successfully now. Hence closing the issue. How did you build it successfully? I tried to bootstrap bazel-3.1.0 on riscv, and I also encountered this...

why onnx.load("resnet50_v1.pth") when I use pytorch backend?

> > Hello, has anyone found any solution yet? I was wondering about the same thing > > I am try to use backend_pytorch_native.py and fixed some code,it's look like...