I recently posted this post on the TensorRT forums and was referred here. Currently my I think that the problem is due to the different image pre-processing from the PyTorch model and when running on TRT. How do I find the values I use in my spec file for net-scale-factor, offsets or other variables to best replicate the image preprocessing used in the PyTorch program? • Hardware Platform (Jetson / GPU) = Jetson • DeepStream Version = 5.1 • JetPack Version (valid for Jetson only) = jetson-nano-jp451-sd-card-image • TensorRT Version = 7.1.3-1 • Issue Type( questions, new requirements, bugs) = questions Thanks

There is no update from you for a period, assuming this is not an issue any more. Hence we are closing this topic. If need further support, please open a new one. Thanks Hi, Could you share the details about your preprocessing so we can check? Thanks.

Hi, Please find below’s topic for the information: [image] How to set the correct config for a pytorch model in nvinfer? DeepStream SDK Hello, I have trained a Resnet classifier in PyTorch and exported to an ONNX model. The FC layer of Resnet18 is set to: model.fc = nn.Sequential( nn.Linear(model.fc.in_features, args.n_classes, bias=False), nn.Softmax(1), ) These are the normalization values I have used. normalize = transforms.Normalize( mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) The model accuracy goes up to 80%, but when I infer (using nvinfer) on the exact same images used… Thanks.

Hi, Unfortunately, when I try to use those values I get outputs that are much larger than expected and are not normalised as they should be. I am trying to replicate this from torchvision: torchvision.transforms.Compose([torchvision.transforms.ToTensor(), torchvision.transforms.Normalize(mean=[0.43476477, 0.44504763, 0.43252817], std=[0.20490805, 0.19712372, 0.20312176]), torchvision.transforms.Resize(540, 960) ]) # normalize to (-1, 1) Thanks

Replicating PyTorch image pre-processing into TRT DeepStream

Accelerated Computing Intelligent Video Analytics DeepStream SDK

AastaLLL July 23, 2021, 2:56am 3

Hi,

Please find below’s topic for the information:

Thanks.

Topic		Replies	Views
Config file settings for custom pytorch pre-process transform DeepStream SDK dataframes-preprocessing-cudf	6	688	November 6, 2023
How to set the correct config for a pytorch model in nvinfer? DeepStream SDK	3	1761	April 19, 2021
Reflecting Pytorch Normalize transform parameter to Deepstream configuration DeepStream SDK pytorch , inference-server-triton	3	1646	December 9, 2020
Can't configure DeepStream classifier to give the same softmax outputs as the TRT engine it builds DeepStream SDK deepstream , config	23	1582	January 4, 2024
Custom (TF) Model - Which config to set in nvinfer? DeepStream SDK	3	380	March 15, 2024
Scale_factor and channel_offsets DeepStream SDK	1	344	November 9, 2023
Preprocessing steps for dashcamnet TensorRT	1	544	November 19, 2020
Preprocessing steps for dashcamnet DeepStream SDK tensorrt	10	1339	December 8, 2020
DeepStream TRT preprocessing settings DeepStream SDK	1	909	November 4, 2020
Getting incorrect results for classification model DeepStream SDK deepstream61	11	1065	May 23, 2023

Replicating PyTorch image pre-processing into TRT DeepStream

Related topics