Hi,
I imported DeeplabV3+(xception) model named 'xception65_coco_voc_trainval'
downloaded from TF model zoo
(https://github.com/tensorflow/models/blob/master/research/deeplab/g3doc/model_zoo.md)
It runs well on CPU but gets some error on GPU.
```
target = tvm.target.cuda()
ctx = tvm.gpu(0)
mo
hi all,
today, following the pipeline PyTorch -> ONNX -> TVM, I met following errors
with cuda error code `CUDA_ERROR_INVALID_PTX`
The same model, 800X800 can work, but 512x512 reports this error
my env:
cuda10.0
torch 1.4.0
Latest co
