Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

could not find plugin ScatterND #21

Open
daxiongpro opened this issue Nov 21, 2022 · 1 comment
Open

could not find plugin ScatterND #21

daxiongpro opened this issue Nov 21, 2022 · 1 comment

Comments

@daxiongpro
Copy link

Hi。I can run your tensorrt code sucessfully following your README in tensorrt/samples.
But I cannot get scatterND plugin when I using your code out of the root of tensorrt :

`
Doc string:

input.name():input.1
input.name():indices_input
[01/29/2018-00:52:33] [W] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/onnx2trt_utils.cpp:220: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:107: Parsing node: pfe_MatMul_0 [Conv]
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:129: pfe_MatMul_0 [Conv] inputs: [input.1 -> (1, 10, 30000, 20)], [48 -> (32, 10, 1, 1)],
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:183: pfe_MatMul_0 [Conv] outputs: [16 -> (1, 32, 30000, 20)],
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:107: Parsing node: pfe_BatchNormalization_2 [BatchNormalization]
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:129: pfe_BatchNormalization_2 [BatchNormalization] inputs: [16 -> (1, 32, 30000, 20)], [pfn_layers.0.norm.weight -> (32)], [pfn_layers.0.norm.bias -> (32)], [pfn_layers.0.norm.running_mean -> (32)], [pfn_layers.0.norm.running_var -> (32)],
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:183: pfe_BatchNormalization_2 [BatchNormalization] outputs: [18 -> (1, 32, 30000, 20)],
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:107: Parsing node: pfe_Relu_4 [Relu]
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:129: pfe_Relu_4 [Relu] inputs: [18 -> (1, 32, 30000, 20)],
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:183: pfe_Relu_4 [Relu] outputs: [20 -> (1, 32, 30000, 20)],
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:107: Parsing node: pfe_ReduceMax_5 [MaxPool]
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:129: pfe_ReduceMax_5 [MaxPool] inputs: [20 -> (1, 32, 30000, 20)],
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:183: pfe_ReduceMax_5 [MaxPool] outputs: [21 -> (1, 32, 30000, 1)],
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:107: Parsing node: pfe_Tile_16 [Tile]
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:129: pfe_Tile_16 [Tile] inputs: [21 -> (1, 32, 30000, 1)], [34 -> (4)],
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:183: pfe_Tile_16 [Tile] outputs: [38 -> (1, 32, 30000, 20)],
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:107: Parsing node: pfe_Concat_17 [Concat]
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:129: pfe_Concat_17 [Concat] inputs: [20 -> (1, 32, 30000, 20)], [38 -> (1, 32, 30000, 20)],
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:183: pfe_Concat_17 [Concat] outputs: [39 -> (1, 64, 30000, 20)],
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:107: Parsing node: pfe_MatMul_18 [Conv]
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:129: pfe_MatMul_18 [Conv] inputs: [39 -> (1, 64, 30000, 20)], [53 -> (64, 64, 1, 1)],
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:183: pfe_MatMul_18 [Conv] outputs: [41 -> (1, 64, 30000, 20)],
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:107: Parsing node: pfe_BatchNormalization_20 [BatchNormalization]
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:129: pfe_BatchNormalization_20 [BatchNormalization] inputs: [41 -> (1, 64, 30000, 20)], [pfn_layers.1.norm.weight -> (64)], [pfn_layers.1.norm.bias -> (64)], [pfn_layers.1.norm.running_mean -> (64)], [pfn_layers.1.norm.running_var -> (64)],
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:183: pfe_BatchNormalization_20 [BatchNormalization] outputs: [43 -> (1, 64, 30000, 20)],
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:107: Parsing node: pfe_Relu_22 [Relu]
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:129: pfe_Relu_22 [Relu] inputs: [43 -> (1, 64, 30000, 20)],
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:183: pfe_Relu_22 [Relu] outputs: [45 -> (1, 64, 30000, 20)],
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:107: Parsing node: pfe_ReduceMax_23 [MaxPool]
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:129: pfe_ReduceMax_23 [MaxPool] inputs: [45 -> (1, 64, 30000, 20)],
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:183: pfe_ReduceMax_23 [MaxPool] outputs: [46 -> (1, 64, 30000, 1)],
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:107: Parsing node: pfe_Squeeze_1 [Squeeze]
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:129: pfe_Squeeze_1 [Squeeze] inputs: [46 -> (1, 64, 30000, 1)],
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:183: pfe_Squeeze_1 [Squeeze] outputs: [pfe_squeeze_1 -> (1, 64, 30000)],
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:107: Parsing node: pfe_Transpose_1 [Transpose]
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:129: pfe_Transpose_1 [Transpose] inputs: [pfe_squeeze_1 -> (1, 64, 30000)],
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:183: pfe_Transpose_1 [Transpose] outputs: [pfe_transpose_1 -> (1, 30000, 64)],
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:107: Parsing node: ScatterND_1 [ScatterND]
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:129: ScatterND_1 [ScatterND] inputs: [scatter_data -> (1, 262144, 64)], [indices_input -> (1, 30000, 2)], [pfe_transpose_1 -> (1, 30000, 64)],
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/ModelImporter.cpp:139: No importer registered for op: ScatterND. Attempting to import as plugin.
[01/29/2018-00:52:33] [I] [TRT] /home/ubuntu/work/onnx-tensorrt-v7.0/builtin_op_importers.cpp:3762: Searching for plugin: ScatterND, plugin_version: 1, plugin_namespace:
[01/29/2018-00:52:33] [E] [TRT] INVALID_ARGUMENT: getPluginCreator could not find plugin ScatterND version 1
While parsing node number 187 [ScatterND]:
ERROR: /home/ubuntu/work/onnx-tensorrt-v7.0/builtin_op_importers.cpp:3764 In function importFallbackPluginImporter:
[8] Assertion failed: creator && "Plugin not found, are the plugin name, version, and namespace correct?"
`

My environment is :
platform : jetson AGX xavier
cuda : 10.2
tensorrt: 7.x

can you give me some advance? thank you very much!!!
@realwenpeng
Copy link

realwenpeng commented Nov 28, 2023 •
edited
Loading

tensorrt: 7.x do not support scatterND, try tensorrt: 8.x

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@daxiongpro @realwenpeng