yolo2_light
yolo2_light copied to clipboard
AlexeyAB
Error int8 support for jetson tx2
Error: CUDNN_STATUS_ARCH_MISMATCH - This GPU doesn't support DP4A (INT8 weights and input)
cudnnstat = 6
So jetson tx2 not support for quantized?
It seems yes, jetson tx2 doesn't support INT8-quantization (DP4A). This is strange, because jetson tx2 is Pascal architecture and compute capability (CC) = 6.2 that is higher than 6.0: https://en.wikipedia.org/wiki/CUDA#GPUs_supported
What CUDA, cuDNN do you use?
Can you show output of command nvidia-smi?
nvidia-smi don't support jetson tx2? cuda 9.0 cudnn 7.1.5 Is there any way to make jetson tx2 support for fp16?
nvidia-smi don't support jetson tx2?
Any desktop GPU supports nvidia-smi.
Is there any way to make jetson tx2 support for fp16?
jetson tx2 supports fp16, but it doesn't have Tensor Cores, so fp16 will not be faster than fp32 on jetson tx2.
jetson tx2 really not support nvidia-smi it is not a dependent gpu. Its gpu memory shares with cpu memory.
oh yeah nvidia-smi doesn't work on tegra (jetson tx2)
so I think it doesn't support DP4A (INT8).
You can only try to use XNOR (1-bit) quantization by training these models:
- yolov2-tiny xnor: https://github.com/AlexeyAB/darknet/blob/master/cfg/tiny-yolo_xnor.cfg
- yolov3-tiny xnor: https://github.com/AlexeyAB/darknet/blob/master/cfg/yolov3-tiny_xnor.cfg
I met the same issue, it can compile successfully with GPU, but when do the INT8 inference, it complains about the mismatch. I also use cuda 9.0 and cudnn 7.1.5 on TX2. In TX2, I use "sudo ~/tegrastats" to monitor the GPU usage since nvidia-smi is not working.
oh yeah
nvidia-smidoesn't work on tegra (jetson tx2)so I think it doesn't support DP4A (INT8).
You can only try to use XNOR (1-bit) quantization by training these models:
- yolov2-tiny xnor: https://github.com/AlexeyAB/darknet/blob/master/cfg/tiny-yolo_xnor.cfg
- yolov3-tiny xnor: https://github.com/AlexeyAB/darknet/blob/master/cfg/yolov3-tiny_xnor.cfg
@AlexeyAB will you share models trained with XNOR quantization with us?
