# Difference between revisions of "TensorRT/ONNX"

(→TRT Inference with explicit batch onnx model) |
(→Introduce some use cases of onnx-graphsurgeon) |
||

(36 intermediate revisions by 2 users not shown) | |||

Line 1: | Line 1: | ||

'''This page intends to share some guidance regarding how to do inference with onnx model, how to convert onnx model and some common FAQ about parsing onnx model''' | '''This page intends to share some guidance regarding how to do inference with onnx model, how to convert onnx model and some common FAQ about parsing onnx model''' | ||

+ | |||

+ | ---- | ||

+ | === TRT Compatibility === | ||

+ | ONNX Operators: https://github.com/onnx/onnx-tensorrt/blob/master/docs/operators.md (e.g. TensorRT 7.2 supports operators up to Opset 11)<br> | ||

+ | cuDNN/TF/Pytorch/ONNX: "Compatibility" section in TensorRT release note - https://docs.nvidia.com/deeplearning/tensorrt/release-notes/index.html <br> | ||

+ | Protobuf: https://github.com/onnx/onnx-tensorrt#dependencies (e.g. Protobuf >= 3.0.x) | ||

=== TRT Inference with explicit batch onnx model === | === TRT Inference with explicit batch onnx model === | ||

Since TensorRT 6.0 released and the ONNX parser only supports networks with an explicit batch dimension, this part will introduce how to do inference with onnx model, which has a fixed shape or dynamic shape.<br> | Since TensorRT 6.0 released and the ONNX parser only supports networks with an explicit batch dimension, this part will introduce how to do inference with onnx model, which has a fixed shape or dynamic shape.<br> | ||

− | + | 1. '''Fixed shape model'''<br> | |

− | + | ||

+ | If your explicit batch network has fixed shape(N, C, H, W >= 1), then you should be able to just specific explicit batch flag and use executeV2() similar to how you used execute() in previous TensorRT versions.<br> | ||

If you got below warning log when you’re trying to do inference with onnx model.<br> | If you got below warning log when you’re trying to do inference with onnx model.<br> | ||

− | [W] [TRT] Explicit batch network detected and batch size specified, use | + | [W] [TRT] Explicit batch network detected and batch size specified, use execute without batch size instead. |

− | + | ||

+ | as the log said, your onnx model is explicit batch network, you need to specific the EXPLICIT_BATCH flag like this line: https://github.com/NVIDIA/TensorRT/blob/f5e8b8c55060447c4d3a45e7379bc25374edc93f/samples/opensource/sampleDynamicReshape/sampleDynamicReshape.cpp#L126 <br> | ||

+ | |||

+ | and TRT use "without batch size instead", it means that setting batch size with TRT API will be ignored, TRT will always execute inference with the explicit batch size of the network. <br> | ||

− | + | 2. '''Dynamic shape model'''<br> | |

− | |||

− | |||

− | |||

If your explicit batch network has dynamic shape(one of the dims == -1), then you should create an optimization profile for it. Then you set this optimization profile for your execution context. But also before doing inference, you’ll need to specify the shape at inference time based on the input.<br> | If your explicit batch network has dynamic shape(one of the dims == -1), then you should create an optimization profile for it. Then you set this optimization profile for your execution context. But also before doing inference, you’ll need to specify the shape at inference time based on the input.<br> | ||

See a sample here:(https://github.com/lynettez/SampleONNX) <br> | See a sample here:(https://github.com/lynettez/SampleONNX) <br> | ||

+ | |||

+ | ---- | ||

+ | |||

+ | === How to convert your model to onnx? === | ||

+ | 1. Convert Pytorch model, you can use torch.onnx API, sample codes:<br> | ||

+ | https://gist.github.com/rmccorm4/b72abac18aed6be4c1725db18eba4930 | ||

+ | 2. Convert Tensorflow model, using tf2onnx tool: <br> | ||

+ | https://github.com/onnx/tensorflow-onnx | ||

+ | 3. Convert Caffe model, using caffe2onnx tool, it supports less operators than others:<br> | ||

+ | https://github.com/htshinichi/caffe-onnx | ||

+ | |||

+ | ---- | ||

+ | === How to modify the model to replace batch dimension with dynamic dim? === | ||

+ | If you’re not willing to regenerate the onnx model, you can just set input dimension after parsing. | ||

+ | auto input = network->getInput(0); | ||

+ | input->setDimensions(Dims4{-1, 3, 224, 224}); | ||

+ | Or using onnx API: | ||

+ | import onnx | ||

+ | |||

+ | model = onnx.load('alexnet_fixed.onnx') | ||

+ | model.graph.input[0].type.tensor_type.shape.dim[0].dim_param = '?' | ||

+ | onnx.save(model, 'dynamic_alexnet.onnx') | ||

+ | onnx.checker.check_model(model) | ||

+ | |||

+ | If you still got below error after you modified the dimensions, that means you have to regenerate your onnx model with dynamic input shape. This error happened when you use dynamic shape for some model with static tensor, TRT 7.1 will support this case so that you don’t regenerate your model, refer to the below introduction of Onnx-GraghSurgeon<br> | ||

+ | INTERNAL_ERROR: Assertion failed: mg.nodes[mg.regionIndices[outputRegion]].size == mg.nodes[mg.regionIndices[inputRegion]].size | ||

+ | ../builder/cudnnBuilderBlockChooser.cpp:136 | ||

+ | Aborting… | ||

+ | |||

+ | ---- | ||

+ | |||

+ | === How to use trtexec to run inference with dynamic shape? === | ||

+ | trtexec --explicitBatch --onnx=mobilenet_dynamic.onnx \ | ||

+ | --minShapes=data:1x3x224x224 \ # kMIN shape | ||

+ | --optShapes=data:3x3x224x224 \ # kOPT shape | ||

+ | --maxShapes=data:5x3x224x224 \ # kMAX shape | ||

+ | --shapes=data:3x3x224x224 \ # Inference shape - this is like context->setBindingDimensions() | ||

+ | --saveEngine=mobilenet_dynamic.engine | ||

+ | |||

+ | If you have onnx exported from TF with input “x:0”, you also could run with<br> | ||

+ | trtexec … --shapes=\'x:0\':5x3x224x224 … | ||

+ | |||

+ | ---- | ||

+ | |||

+ | === How to convert onnx model to a tensorrt engine? === | ||

+ | Use OnnxParser to parse the onnx model, and then build engine as usual, if you’re not familiar with onnxParser and building engine, please refer to https://github.com/NVIDIA/TensorRT/blob/master/samples/opensource/sampleOnnxMNIST/sampleOnnxMNIST.cpp<br> | ||

+ | |||

+ | You also could use trtexec to do the same thing with below cmd: | ||

+ | trtexec --explicitBatch --onnx=your_model.onnx | ||

+ | |||

+ | ---- | ||

+ | === If you met some error during converting onnx to engine === | ||

+ | If you met some error during parsing, please add “--verbose” into trtexec cmd line to see if there is anything wrong with parsing some node, and check below two things:<br> | ||

+ | 1. Check ONNX model using checker function and see if it passes? | ||

+ | import onnx | ||

+ | model = onnx.load("model.onnx") | ||

+ | onnx.checker.check_model(model) | ||

+ | 2. If (1) passes, maybe try onnx-simplifier on it. https://github.com/daquexian/onnx-simplifier<br> | ||

+ | 3. If (2) doesn’t work, there could be some unsupported operator casung the parsing error. Please check the OnnxParser supported operators list here, https://github.com/onnx/onnx-tensorrt/blob/84b5be1d6fc03564f2c0dba85a2ee75bad242c2e/operators.md. Or you need to see if anything looks off in Netron when viewing the failing nodes. You also could try with newer onnx opset during the converting of onnx model. | ||

+ | |||

+ | Tips: | ||

+ | If you’re converting tf model to onnx, you might have a try with: | ||

+ | onnx_graph = tf2onnx.optimizer.optimize_graph(onnx_graph) | ||

+ | This will help to avoid some converting error | ||

+ | |||

+ | ---- | ||

+ | |||

+ | === Some performance tests about dynamic shape with onnx model === | ||

+ | Test environment<br> | ||

+ | GPU: T4<br> | ||

+ | TensorRT: 7.0 <br> | ||

+ | CUDA: 10.2<br> | ||

+ | |||

+ | {| class="wikitable" | ||

+ | |- | ||

+ | ! MobilenetV2 !! OptimizationProfile !! Engine size(bit) | ||

+ | |- | ||

+ | | Fixed shape [1, 3, 224 ,224] || - || 14487087 | ||

+ | |- | ||

+ | | rowspan="4"| Dynamic shape [-1, 3, 224, 224] || Not setting, default to [1, 3, 224 ,224] || 14487537 | ||

+ | |- | ||

+ | | --minShapes=data:1x3x224x224 --optShapes=data:5x3x224x224 --maxShapes=data:10x3x224x224 || 14595945 | ||

+ | |- | ||

+ | | --minShapes=data:10x3x224x224 --optShapes=data:15x3x224x224 --maxShapes=data:20x3x224x224 || 14601941 | ||

+ | |- | ||

+ | | --minShapes=data:1x3x224x224 --optShapes=data:16x3x224x224 --maxShapes=data:32x3x224x224 || 14604501 | ||

+ | |} | ||

+ | |||

+ | {| class="wikitable" | ||

+ | |- | ||

+ | ! MobilenetV2 !! Inference Batch !! Execution time(ms) | ||

+ | |- | ||

+ | | Fixed shape [1, 3, 224 ,224] || 1 || 1.01 | ||

+ | |- | ||

+ | | rowspan="3"| Dynamic shape [-1, 3, 224, 224] --minShapes=data:1x3x224x224 --optShapes=data:8x3x224x224 --maxShapes=data:16x3x224x224 || 1 || 1.36 | ||

+ | |- | ||

+ | | 8 || 4.47 | ||

+ | |- | ||

+ | | 16 || 8.76 | ||

+ | |- | ||

+ | | rowspan="4"| Dynamic shape [-1, 3, 224, 224] --minShapes=data:1x3x224x224 --optShapes=data:16x3x224x224 --maxShapes=data:32x3x224x224 || 1 || 1.44 | ||

+ | |- | ||

+ | | 8 || 4.56 | ||

+ | |- | ||

+ | | 16 || 8.23 | ||

+ | |- | ||

+ | | 32 || 16.21 | ||

+ | |} | ||

+ | As the test results showed,<br> | ||

+ | 1. The engine size will increase if it is built with dynamic shape and OptimizationProfile, the bigger shape you set, the bigger engine size. but it will not increase much.<br> | ||

+ | 2. The performance will be the best when the inference shape is the same as the optShape you set.<br> | ||

+ | |||

+ | ---- | ||

+ | === Introduce some use cases of onnx-graphsurgeon === | ||

+ | ONNX GraphSurgeon(Onnx-GS) is a tool that allows you to easily generate new ONNX graphs, or modify existing ones. It was released with [https://github.com/NVIDIA/TensorRT/tree/master/tools/onnx-graphsurgeon TensorRT OSS]. You may follow the readme to install it. | ||

+ | This section will introduce some use cases modifying the onnx model using Onnx-GS. | ||

+ | ==== 1. Make dynamic ==== | ||

+ | Since TRT 6.0 released, it only support explicit batch onnx model. So some users have to make the model input dynamic, below sample is showing how to use onnx-GS to modify the input without regenerating the onnx model in the training framework. | ||

+ | |||

+ | Here is the sample to make the model input dynamic: | ||

+ | import onnx_graphsurgeon as gs | ||

+ | import onnx | ||

+ | graph1 = gs.import_onnx(onnx.load("resnet10.onnx")) | ||

+ | tensors = graph1.tensors() | ||

+ | tensors["input"].shape[0] = gs.Tensor.DYNAMIC | ||

+ | tensors["Layer7_cov_Y"].shape[0] = gs.Tensor.DYNAMIC | ||

+ | tensors["Layer7_bbox_Y"].shape[0] = gs.Tensor.DYNAMIC | ||

+ | onnx.save(gs.export_onnx(graph1.cleanup().toposort()), "resnet10_dynamic.onnx") | ||

+ | If you still got error during building the engine, you may find the node which has static dims, let's say it's node named "OC2_DUMMY_1", then you need to change its first dims like this. | ||

+ | # Array is not writeable, need to copy it first. | ||

+ | tensors["OC2_DUMMY_1"].values = np.array(tensors["OC2_DUMMY_1"].values) | ||

+ | tensors["OC2_DUMMY_1"].values[0] = gs.Tensor.DYNAMIC | ||

+ | |||

+ | ==== 2. Change node's name ==== | ||

+ | Here is the sample changing input and output names. | ||

+ | tensors["input"].name = "data" | ||

+ | tensors["Layer7_cov_Y"].name = "Layer7_cov" | ||

+ | tensors["Layer7_bbox_Y"].name = "Layer7_bbox" | ||

+ | |||

+ | ==== 3. Prune the model with a certain output layer ==== | ||

+ | Sometimes we need to prune the model for narrowing down some issue, we could use the below script to specifically set the output tensor as you want: | ||

+ | import onnx_graphsurgeon as gs | ||

+ | import numpy as np | ||

+ | import sys | ||

+ | import onnx | ||

+ | |||

+ | # Cut the model to generate the model ended to the test node | ||

+ | print("cut model: ", sys.argv[1], " to end with node ", sys.argv[2]) | ||

+ | graph = gs.import_onnx(onnx.load(sys.argv[1])) | ||

+ | tensors = graph.tensors() | ||

+ | graph.outputs = [tensors[str(sys.argv[2])].to_variable(dtype=np.float32)] | ||

+ | |||

+ | # removing any unnecessary nodes or tensors, so that we are left with only the subgraph. | ||

+ | graph.cleanup() | ||

+ | |||

+ | om=str(sys.argv[1]) | ||

+ | new_onnx_model_name=om[:om.rfind(".")]+"_ended_node_"+sys.argv[2]+".onnx" | ||

+ | |||

+ | onnx.save(gs.export_onnx(graph), new_onnx_model_name) | ||

+ | |||

+ | ==== 4. Add your Plugin ==== | ||

+ | Onnx-GS also can be used for modifying the model with the custom plugin. <br> | ||

+ | Download this [https://elinux.org/images/e/e6/Insert_dcn_plugin.zip sample].<br> | ||

+ | Note that this sample only shows how to apply the layer params to the plugin layer and replace the original node with the plugin node. <br> | ||

+ | We can see what the sample did as below, it replace the "DCNv2" with the plugin named "DCNv2_SS":<br> | ||

+ | [[File:Ori_model.jpeg|400px|thumb|left| original graph]]<br> | ||

+ | [[File:Inserted_plugin_model.jpeg|400px|thumb|left|new graph]] |

## Revision as of 21:02, 23 June 2021

**This page intends to share some guidance regarding how to do inference with onnx model, how to convert onnx model and some common FAQ about parsing onnx model**

## Contents

- 1 TRT Compatibility
- 2 TRT Inference with explicit batch onnx model
- 3 How to convert your model to onnx?
- 4 How to modify the model to replace batch dimension with dynamic dim?
- 5 How to use trtexec to run inference with dynamic shape?
- 6 How to convert onnx model to a tensorrt engine?
- 7 If you met some error during converting onnx to engine
- 8 Some performance tests about dynamic shape with onnx model
- 9 Introduce some use cases of onnx-graphsurgeon

### TRT Compatibility

ONNX Operators: https://github.com/onnx/onnx-tensorrt/blob/master/docs/operators.md (e.g. TensorRT 7.2 supports operators up to Opset 11)

cuDNN/TF/Pytorch/ONNX: "Compatibility" section in TensorRT release note - https://docs.nvidia.com/deeplearning/tensorrt/release-notes/index.html

Protobuf: https://github.com/onnx/onnx-tensorrt#dependencies (e.g. Protobuf >= 3.0.x)

### TRT Inference with explicit batch onnx model

Since TensorRT 6.0 released and the ONNX parser only supports networks with an explicit batch dimension, this part will introduce how to do inference with onnx model, which has a fixed shape or dynamic shape.

1. **Fixed shape model**

If your explicit batch network has fixed shape(N, C, H, W >= 1), then you should be able to just specific explicit batch flag and use executeV2() similar to how you used execute() in previous TensorRT versions.

If you got below warning log when you’re trying to do inference with onnx model.

[W] [TRT] Explicit batch network detected and batch size specified, use execute without batch size instead.

as the log said, your onnx model is explicit batch network, you need to specific the EXPLICIT_BATCH flag like this line: https://github.com/NVIDIA/TensorRT/blob/f5e8b8c55060447c4d3a45e7379bc25374edc93f/samples/opensource/sampleDynamicReshape/sampleDynamicReshape.cpp#L126

and TRT use "without batch size instead", it means that setting batch size with TRT API will be ignored, TRT will always execute inference with the explicit batch size of the network.

2. **Dynamic shape model**

If your explicit batch network has dynamic shape(one of the dims == -1), then you should create an optimization profile for it. Then you set this optimization profile for your execution context. But also before doing inference, you’ll need to specify the shape at inference time based on the input.

See a sample here:(https://github.com/lynettez/SampleONNX)

### How to convert your model to onnx?

1. Convert Pytorch model, you can use torch.onnx API, sample codes:

https://gist.github.com/rmccorm4/b72abac18aed6be4c1725db18eba4930

2. Convert Tensorflow model, using tf2onnx tool:

https://github.com/onnx/tensorflow-onnx

3. Convert Caffe model, using caffe2onnx tool, it supports less operators than others:

https://github.com/htshinichi/caffe-onnx

### How to modify the model to replace batch dimension with dynamic dim?

If you’re not willing to regenerate the onnx model, you can just set input dimension after parsing.

auto input = network->getInput(0); input->setDimensions(Dims4{-1, 3, 224, 224});

Or using onnx API:

import onnx model = onnx.load('alexnet_fixed.onnx') model.graph.input[0].type.tensor_type.shape.dim[0].dim_param = '?' onnx.save(model, 'dynamic_alexnet.onnx') onnx.checker.check_model(model)

If you still got below error after you modified the dimensions, that means you have to regenerate your onnx model with dynamic input shape. This error happened when you use dynamic shape for some model with static tensor, TRT 7.1 will support this case so that you don’t regenerate your model, refer to the below introduction of Onnx-GraghSurgeon

INTERNAL_ERROR: Assertion failed: mg.nodes[mg.regionIndices[outputRegion]].size == mg.nodes[mg.regionIndices[inputRegion]].size ../builder/cudnnBuilderBlockChooser.cpp:136 Aborting…

### How to use trtexec to run inference with dynamic shape?

trtexec --explicitBatch --onnx=mobilenet_dynamic.onnx \ --minShapes=data:1x3x224x224 \ # kMIN shape --optShapes=data:3x3x224x224 \ # kOPT shape --maxShapes=data:5x3x224x224 \ # kMAX shape --shapes=data:3x3x224x224 \ # Inference shape - this is like context->setBindingDimensions() --saveEngine=mobilenet_dynamic.engine

If you have onnx exported from TF with input “x:0”, you also could run with

trtexec … --shapes=\'x:0\':5x3x224x224 …

### How to convert onnx model to a tensorrt engine?

Use OnnxParser to parse the onnx model, and then build engine as usual, if you’re not familiar with onnxParser and building engine, please refer to https://github.com/NVIDIA/TensorRT/blob/master/samples/opensource/sampleOnnxMNIST/sampleOnnxMNIST.cpp

You also could use trtexec to do the same thing with below cmd:

trtexec --explicitBatch --onnx=your_model.onnx

### If you met some error during converting onnx to engine

If you met some error during parsing, please add “--verbose” into trtexec cmd line to see if there is anything wrong with parsing some node, and check below two things:

1. Check ONNX model using checker function and see if it passes?

import onnx model = onnx.load("model.onnx") onnx.checker.check_model(model)

2. If (1) passes, maybe try onnx-simplifier on it. https://github.com/daquexian/onnx-simplifier

3. If (2) doesn’t work, there could be some unsupported operator casung the parsing error. Please check the OnnxParser supported operators list here, https://github.com/onnx/onnx-tensorrt/blob/84b5be1d6fc03564f2c0dba85a2ee75bad242c2e/operators.md. Or you need to see if anything looks off in Netron when viewing the failing nodes. You also could try with newer onnx opset during the converting of onnx model.

Tips: If you’re converting tf model to onnx, you might have a try with:

onnx_graph = tf2onnx.optimizer.optimize_graph(onnx_graph)

This will help to avoid some converting error

### Some performance tests about dynamic shape with onnx model

Test environment

GPU: T4

TensorRT: 7.0

CUDA: 10.2

MobilenetV2 | OptimizationProfile | Engine size(bit) |
---|---|---|

Fixed shape [1, 3, 224 ,224] | - | 14487087 |

Dynamic shape [-1, 3, 224, 224] | Not setting, default to [1, 3, 224 ,224] | 14487537 |

--minShapes=data:1x3x224x224 --optShapes=data:5x3x224x224 --maxShapes=data:10x3x224x224 | 14595945 | |

--minShapes=data:10x3x224x224 --optShapes=data:15x3x224x224 --maxShapes=data:20x3x224x224 | 14601941 | |

--minShapes=data:1x3x224x224 --optShapes=data:16x3x224x224 --maxShapes=data:32x3x224x224 | 14604501 |

MobilenetV2 | Inference Batch | Execution time(ms) |
---|---|---|

Fixed shape [1, 3, 224 ,224] | 1 | 1.01 |

Dynamic shape [-1, 3, 224, 224] --minShapes=data:1x3x224x224 --optShapes=data:8x3x224x224 --maxShapes=data:16x3x224x224 | 1 | 1.36 |

8 | 4.47 | |

16 | 8.76 | |

Dynamic shape [-1, 3, 224, 224] --minShapes=data:1x3x224x224 --optShapes=data:16x3x224x224 --maxShapes=data:32x3x224x224 | 1 | 1.44 |

8 | 4.56 | |

16 | 8.23 | |

32 | 16.21 |

As the test results showed,

1. The engine size will increase if it is built with dynamic shape and OptimizationProfile, the bigger shape you set, the bigger engine size. but it will not increase much.

2. The performance will be the best when the inference shape is the same as the optShape you set.

### Introduce some use cases of onnx-graphsurgeon

ONNX GraphSurgeon(Onnx-GS) is a tool that allows you to easily generate new ONNX graphs, or modify existing ones. It was released with TensorRT OSS. You may follow the readme to install it. This section will introduce some use cases modifying the onnx model using Onnx-GS.

#### 1. Make dynamic

Since TRT 6.0 released, it only support explicit batch onnx model. So some users have to make the model input dynamic, below sample is showing how to use onnx-GS to modify the input without regenerating the onnx model in the training framework.

Here is the sample to make the model input dynamic:

import onnx_graphsurgeon as gs import onnx graph1 = gs.import_onnx(onnx.load("resnet10.onnx")) tensors = graph1.tensors() tensors["input"].shape[0] = gs.Tensor.DYNAMIC tensors["Layer7_cov_Y"].shape[0] = gs.Tensor.DYNAMIC tensors["Layer7_bbox_Y"].shape[0] = gs.Tensor.DYNAMIC onnx.save(gs.export_onnx(graph1.cleanup().toposort()), "resnet10_dynamic.onnx")

If you still got error during building the engine, you may find the node which has static dims, let's say it's node named "OC2_DUMMY_1", then you need to change its first dims like this.

# Array is not writeable, need to copy it first. tensors["OC2_DUMMY_1"].values = np.array(tensors["OC2_DUMMY_1"].values) tensors["OC2_DUMMY_1"].values[0] = gs.Tensor.DYNAMIC

#### 2. Change node's name

Here is the sample changing input and output names.

tensors["input"].name = "data" tensors["Layer7_cov_Y"].name = "Layer7_cov" tensors["Layer7_bbox_Y"].name = "Layer7_bbox"

#### 3. Prune the model with a certain output layer

Sometimes we need to prune the model for narrowing down some issue, we could use the below script to specifically set the output tensor as you want:

import onnx_graphsurgeon as gs import numpy as np import sys import onnx # Cut the model to generate the model ended to the test node print("cut model: ", sys.argv[1], " to end with node ", sys.argv[2]) graph = gs.import_onnx(onnx.load(sys.argv[1])) tensors = graph.tensors() graph.outputs = [tensors[str(sys.argv[2])].to_variable(dtype=np.float32)] # removing any unnecessary nodes or tensors, so that we are left with only the subgraph. graph.cleanup() om=str(sys.argv[1]) new_onnx_model_name=om[:om.rfind(".")]+"_ended_node_"+sys.argv[2]+".onnx" onnx.save(gs.export_onnx(graph), new_onnx_model_name)

#### 4. Add your Plugin

Onnx-GS also can be used for modifying the model with the custom plugin.

Download this sample.

Note that this sample only shows how to apply the layer params to the plugin layer and replace the original node with the plugin node.

We can see what the sample did as below, it replace the "DCNv2" with the plugin named "DCNv2_SS":