# Custom Model deployment on deepstream **URL:** \ **Category:** DeepStream SDK\ **Tags:** tensorrt, cuda\ **Created:** [June 4, 2022, 3:28pm UTC](https://forums.developer.nvidia.com/t/custom-model-deployment-on-deepstream/216523 "2022-06-04T15:28:05Z")\ **Posts on this page:** 9\ **Page:** 1
**Author:** ![shivam.mishra](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@shivam.mishra](https://forums.developer.nvidia.com/u/shivam.mishra)\ **Post date:** [June 4, 2022, 3:28pm UTC](https://forums.developer.nvidia.com/t/custom-model-deployment-on-deepstream/216523/1 "2022-06-04T15:28:05Z")
I have converted one tensorrt engine model from pytorch. It is basically a segementation model . Now when I am trying to run it on deepstream I am getting an error like this Opening in BLOCKING MODE WARNING: [TRT]: Using an engine plan file across different models of devices is not recommended and is likely to affect performance or even cause errors. 0:00:08.666316719 26834 0x17631b50 INFO nvinfer gstnvinfer.cpp:638:gst\_nvinfer\_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() \ [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-6.0/sources/deepstream\_python\_apps/apps/deepstream-segmentation/trt\_fp32\_py.engine INFO: [Implicit Engine Info]: layers num: 2 0 INPUT kFLOAT actual\_input 3x64x64 1 OUTPUT kFLOAT output 6x64x64 0:00:08.668154258 26834 0x17631b50 INFO nvinfer gstnvinfer.cpp:638:gst\_nvinfer\_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() \ [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-6.0/sources/deepstream\_python\_apps/apps/deepstream-segmentation/trt\_fp32\_py.engine 0:00:08.712010507 26834 0x17631b50 INFO nvinfer gstnvinfer\_impl.cpp:313:notifyLoadModelStatus: [UID 1]: Load new model:model\_basic.txt sucessfully NvMMLiteBlockCreate : Block : BlockType = 256 [JPEG Decode] BeginSequence Display WidthxHeight 3150x2100 in videoconvert caps = video/x-raw(memory:NVMM), format=(string)RGBA, framerate=(fraction)1/1, width=(int)64, height=(int)64 /dvs/git/dirty/git-master\_linux/nvutils/nvbufsurftransform/nvbufsurftransform.cpp:3885: =\> VIC Configuration failed image scale factor exceeds 16, use GPU for Transformation 0:00:09.333505857 26834 0x7f240035e0 WARN nvinfer gstnvinfer.cpp:1376:convert\_batch\_and\_push\_to\_input\_thread: error: NvBufSurfTransform failed with error -2 while converting buffer Error: gst-stream-error-quark: NvBufSurfTransform failed with error -2 while converting buffer (1): /dvs/git/dirty/git-master\_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(1376): convert\_batch\_and\_push\_to\_input\_thread (): /GstPipeline:pipeline0/GstNvInfer:primary-nvinference-engine [JPEG Decode] NvMMLiteJPEGDecBlockPrivateClose done [JPEG Decode] NvMMLiteJPEGDecBlockClose done My config files are: basic\_deepstream.txt [application] enable-perf-measurement=1 perf-measurement-interval-sec=5 #gie-kitti-output-dir=streamscl [tiled-display] enable=1 rows=1 columns=1 width=1280 height=720 gpu-id=0 #(0): nvbuf-mem-default - Default memory allocated, specific to particular platform #(1): nvbuf-mem-cuda-pinned - Allocate Pinned/Host cuda memory, applicable for Tesla #(2): nvbuf-mem-cuda-device - Allocate Device cuda memory, applicable for Tesla #(3): nvbuf-mem-cuda-unified - Allocate Unified cuda memory, applicable for Tesla #(4): nvbuf-mem-surface-array - Allocate Surface Array memory, applicable for Jetson nvbuf-memory-type=0 [source0] enable=1 #Type - 1=CameraV4L2 2=URI 3=MultiURI 4=RTSP type=3 uri=file://./videoplayback.mp4 num-sources=1 #drop-frame-interval=2 gpu-id=0 # (0): memtype\_device - Memory type Device # (1): memtype\_pinned - Memory type Host Pinned # (2): memtype\_unified - Memory type Unified cudadec-memtype=0 [sink0] enable=1 #Type - 1=FakeSink 2=EglSink 3=File type=5 sync=0 source-id=0 gpu-id=0 qos=0 nvbuf-memory-type=0 overlay-id=1 [sink1] enable=1 type=3 #1=mp4 2=mkv container=1 #1=h264 2=h265 codec=1 #encoder type 0=Hardware 1=Software enc-type=0 sync=0 #iframeinterval=10 bitrate=2000000 #H264 Profile - 0=Baseline 2=Main 4=High #H265 Profile - 0=Main 1=Main10 profile=0 output-file=out4.mp4 source-id=0 [sink2] enable=0 #Type - 1=FakeSink 2=EglSink 3=File 4=RTSPStreaming type=4 #1=h264 2=h265 codec=1 #encoder type 0=Hardware 1=Software enc-type=0 sync=0 bitrate=4000000 #H264 Profile - 0=Baseline 2=Main 4=High #H265 Profile - 0=Main 1=Main10 profile=0 # set below properties in case of RTSPStreaming rtsp-port=8554 udp-port=5400 [osd] enable=1 gpu-id=0 border-width=1 text-size=15 text-color=1;1;1;1; font=Serif show-clock=0 clock-x-offset=800 clock-y-offset=820 clock-text-size=12 clock-color=1;0;0;0 nvbuf-memory-type=0 [streammux] gpu-id=0 ##Boolean property to inform muxer that sources are live live-source=0 batch-size=1 ##time out in usec, to wait after the first buffer is available ##to push the batch even if the complete batch is not formed batched-push-timeout=40000 width=640 height=480 ##enable to maintain aspect ratio wrt source, and allow black borders, works ##along with width, height properties enable-padding=0 nvbuf-memory-type=0 [primary-gie] enable=1 gpu-id=0 batch-size=1 interval=0 model-engine-file=./trt\_fp32\_py.engine nvbuf-memory-type=0 config-file=model\_basic.txt and model\_basic.txt is [property] gpu-id=0 net-scale-factor=1.0 model-color-format=0 model-engine-file=./trt\_fp32\_py.engine infer-dims=3;64;64 #uff-input-order=0 #uff-input-blob-name=data batch-size=1 ## 0=FP32, 1=INT8, 2=FP16 mode network-mode=0 num-detected-classes=6 interval=0 gie-unique-id=1 network-type=2 #output-blob-names=last segmentation-threshold=0.0 ---
**Author:** ![yingliu](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/yingliu/32/136703_2.png) [@yingliu](https://forums.developer.nvidia.com/u/yingliu)\ **Post date:** [June 6, 2022, 2:42am UTC](https://forums.developer.nvidia.com/t/custom-model-deployment-on-deepstream/216523/2 "2022-06-06T02:42:24Z")
Please provide complete information as applicable to your setup. **• Hardware Platform (Jetson / GPU)** **• DeepStream Version** **• JetPack Version (valid for Jetson only)** **• TensorRT Version** **• NVIDIA GPU Driver Version (valid for GPU only)** **• Issue Type( questions, new requirements, bugs)** **• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)** **• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)** **• The pipeline being used** ---
**Author:** ![shivam.mishra](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@shivam.mishra](https://forums.developer.nvidia.com/u/shivam.mishra)\ **Post date:** [June 6, 2022, 6:03am UTC](https://forums.developer.nvidia.com/t/custom-model-deployment-on-deepstream/216523/4 "2022-06-06T06:03:22Z")
- Hardware Platform Jetson Nano 4gb - Deepstream Vesrion 6.0 - JetPack Version 4.6.2 (L4T 32.7.2] - tensorrt==8.2.1.8 - I created a Project Folder inside /opt/nvidia/deepstream/deepstream-6.0/sources/Project/configs and inside it i created two custom file deepstream\_basic.txt and model\_basic.txt(content in these two is given above). I run the command in the folder /opt/nvidia/deepstream/deepstream-6.0/sources/Project$ deepstream-app -c deepstream\_basic.txt and i Got the error mentioned above. I am not using any of the built-in deepstream models. I had my pytoorch model which I converted to ONNX then converted it .engine file. My model is for segmentation. Is there any way to deploy my custom trt engine model and have control over input ? Because in original model for prediction I have to preprocess the input , How can i do it in deepstream? ---
**Author:** ![kesong](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/kesong/32/101255_2.png) [@kesong](https://forums.developer.nvidia.com/u/kesong)\ **Post date:** [June 6, 2022, 11:38am UTC](https://forums.developer.nvidia.com/t/custom-model-deployment-on-deepstream/216523/5 "2022-06-06T11:38:59Z")
> [@shivam.mishra](#): > > /dvs/git/dirty/git-master\_linux/nvutils/nvbufsurftransform/nvbufsurftransform.cpp:3885: =\> VIC Configuration failed image scale factor exceeds 16, use GPU for Transformation Seems there is video resize factor exceeds 16. ---
**Author:** ![shivam.mishra](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@shivam.mishra](https://forums.developer.nvidia.com/u/shivam.mishra)\ **Post date:** [June 6, 2022, 11:48am UTC](https://forums.developer.nvidia.com/t/custom-model-deployment-on-deepstream/216523/6 "2022-06-06T11:48:45Z")
How to resolve it? ---
**Author:** ![kesong](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/kesong/32/101255_2.png) [@kesong](https://forums.developer.nvidia.com/u/kesong)\ **Post date:** [June 7, 2022, 8:41am UTC](https://forums.developer.nvidia.com/t/custom-model-deployment-on-deepstream/216523/7 "2022-06-07T08:41:52Z")
Can you check your pipeline where need resize factor exceeds 16? ---
**Author:** ![shivam.mishra](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@shivam.mishra](https://forums.developer.nvidia.com/u/shivam.mishra)\ **Post date:** [June 14, 2022, 5:36am UTC](https://forums.developer.nvidia.com/t/custom-model-deployment-on-deepstream/216523/8 "2022-06-14T05:36:08Z")
sorry for the late reply, My error got solve by resizing the dimension of image inputs. ---
**Author:** ![kesong](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/kesong/32/101255_2.png) [@kesong](https://forums.developer.nvidia.com/u/kesong)\ **Post date:** [June 14, 2022, 9:25am UTC](https://forums.developer.nvidia.com/t/custom-model-deployment-on-deepstream/216523/9 "2022-06-14T09:25:12Z")
Glad to know the issue resolved. ---
**Author:** ![system](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/system/32/68080_2.png) [@system](https://forums.developer.nvidia.com/u/system)\ **Post date:** [June 28, 2022, 9:25am UTC](https://forums.developer.nvidia.com/t/custom-model-deployment-on-deepstream/216523/10 "2022-06-28T09:25:22Z")
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.