Description I introduce a custion model developed by python into deepstream gst-infer, but the output value of the gst-infer isn’t the same as python code： cap = cv2.VideoCapture(“output1.mp4”) #cv2 getting the camera rval, frame = cap.read() if rval == False: break img = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)# image to RGB img_ = Image.fromarray(img) img_transforms = transforms.Compose([ transforms.Resize((288, 800)), transforms.ToTensor(), transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225)), ]) imgs = img_transforms(img_) imgs = imgs.unsqueeze(0) imgs = imgs.cuda() with torch.no_grad(): out = module_net(imgs) Environment I think, maybe the imgs input into “module_net(imgs)” isn’t the same as gst-pipeline, so, should I add a pre-processor for the input image in gst-infer as img_transforms? If yes, how?

Hi, This looks like a Deepstream related issue. We will move this post to the Deepstream forum. Thanks!

Custom Model applied on Deepstream

zhaochong December 30, 2022, 6:36am 4

Topic		Replies	Views
Custom Model applied on Deepstream DeepStream SDK gstreamer	4	618	January 2, 2023
Custom Secondary Network DeepStream SDK	15	1502	August 23, 2022
Input frame to Nvinfer in a pipeline is wrong DeepStream SDK	3	505	December 28, 2021
Custom ONNX model, TensorRT Engine with PyCUDA in Deepstream DeepStream SDK	16	1767	April 20, 2023
Custom Model deployment on deepstream DeepStream SDK tensorrt , cuda	7	886	June 14, 2022
Difference between predictions of exported TensorRT engine and PyTorch pth models DeepStream SDK	22	2921	March 14, 2023
How to debug gstnvinfer with custom model？ DeepStream SDK tensorrt	23	2620	June 11, 2021
Inference with custom model DeepStream SDK opencv , gstreamer , python , deepstream61	4	816	August 26, 2022
Issues running custom model in deepstream DeepStream SDK	1	601	February 17, 2021
Secondary-GIE result in DeepStream messed, python tensorrt api works fine DeepStream SDK tensorrt	5	1130	August 23, 2021