Q-engineering

In that case, I really don't know what causes your issue. I'm very sorry not able to help you.

Dear @Thanushan1997, Every Jetson Nano boots default from SD. It doesn't matter if you are using jetpack 4.5 or 4.6. If the file structure on the SD card is correct...

The image is downloaded and used by many people, targeted to the 'average' user. PPS is quite an 'advanced' subject. It requires quite a bit of technical knowledge. I'm afraid...

Good idea. I will make one. However it will take some time. Please be a little patience.

I've tried to fix the issue. Tested with CUDA 10.2.89 and cuDNN 8.0.0.180. Works like charm. [Q-engineering](https://github.com/Qengineering/caffe)

Dear @4everZard, I've got the same problem with Caffe and cuDNN version 8. As of version 8, NVIDIA has dropped the cudnnGetConvolutionBackwardFilterAlgorithm. The other two obsolete API calls, cudnnGetConvolutionForwardAlgorithm and...

@torta24x Which CUDA and cuDNN version are you using? I've tested it with CUDA 10.2 and cuDNN 8.0.0.180.

@faithmaker, Where did you get the information about mobilenet_v1_1.0_224_quant.tflite from? Which repo?

Try ``` $ python3 >>> import tensorrt as trt >>> trt.__version__ '8.0.1.6' ```

@AINacster, Just flashed a new SD card with the original image. There is nothing wrong with TensorRT. Please check the command below. You should have the same output. ![Screenshot from...