XW-AIOT/Test_AI
4
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

TensorRT测试

Browse Source
This commit is contained in:
16337
2026-01-20 11:14:10 +08:00
commit 189c6fa786
51 changed files with 9251 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

254
benchmark_results/benchmark_results_20260119_105249.json Normal file
View File

@@ -0,0 +1,254 @@
{
"pytorch": {
"single_inference": {
"engine_type": "pytorch",
"test_type": "single_inference",
"avg_fps": 100.24536806990137,
"max_fps": 110.55717075617225,
"min_fps": 61.984852201102704,
"avg_latency_ms": 8.500274059532323,
"max_latency_ms": 403.38873863220215,
"min_latency_ms": 5.989313125610352,
"avg_gpu_util": 51.25,
"max_gpu_util": 59.0,
"avg_gpu_memory_mb": 2344.9926470588234,
"max_gpu_memory_mb": 2379.0,
"avg_cpu_util": 12.881617647058825,
"max_cpu_util": 23.4,
"test_duration": 30.0392644405365,
"total_frames": 2998,
"concurrent_streams": 1,
"batch_size": 1
},
"batch_inference": [
{
"engine_type": "pytorch",
"test_type": "batch_inference",
"avg_fps": 64.4045757619785,
"max_fps": 89.99753243536232,
"min_fps": 41.372814262097606,
"avg_latency_ms": 13.55419647036575,
"max_latency_ms": 30.249357223510742,
"min_latency_ms": 5.991935729980469,
"avg_gpu_util": 34.93103448275862,
"max_gpu_util": 49.0,
"avg_gpu_memory_mb": 2355.8390804597702,
"max_gpu_memory_mb": 2428.0,
"avg_cpu_util": 19.886206896551727,
"max_cpu_util": 36.9,
"test_duration": 20.23624587059021,
"total_frames": 1270,
"concurrent_streams": 1,
"batch_size": 1
},
{
"engine_type": "pytorch",
"test_type": "batch_inference",
"avg_fps": 91.21476622119891,
"max_fps": 113.58396186681749,
"min_fps": 57.70930049399445,
"avg_latency_ms": 8.738896898601366,
"max_latency_ms": 61.615705490112305,
"min_latency_ms": 5.488753318786621,
"avg_gpu_util": 45.870588235294115,
"max_gpu_util": 59.0,
"avg_gpu_memory_mb": 2450.0470588235294,
"max_gpu_memory_mb": 2468.0,
"avg_cpu_util": 21.7764705882353,
"max_cpu_util": 47.9,
"test_duration": 20.111130475997925,
"total_frames": 1840,
"concurrent_streams": 1,
"batch_size": 2
},
{
"engine_type": "pytorch",
"test_type": "batch_inference",
"avg_fps": 122.78650133644099,
"max_fps": 130.98923241919346,
"min_fps": 112.29584439660107,
"avg_latency_ms": 6.340374306934636,
"max_latency_ms": 15.185177326202393,
"min_latency_ms": 5.218327045440674,
"avg_gpu_util": 54.765957446808514,
"max_gpu_util": 65.0,
"avg_gpu_memory_mb": 2517.6063829787236,
"max_gpu_memory_mb": 2520.0,
"avg_cpu_util": 13.004255319148939,
"max_cpu_util": 26.1,
"test_duration": 20.237423181533813,
"total_frames": 2460,
"concurrent_streams": 1,
"batch_size": 4
},
{
"engine_type": "pytorch",
"test_type": "batch_inference",
"avg_fps": 131.4137397809772,
"max_fps": 135.72617271577812,
"min_fps": 127.20820602543212,
"avg_latency_ms": 5.919770266872047,
"max_latency_ms": 8.72543454170227,
"min_latency_ms": 5.304574966430664,
"avg_gpu_util": 54.364583333333336,
"max_gpu_util": 65.0,
"avg_gpu_memory_mb": 2658.0,
"max_gpu_memory_mb": 2658.0,
"avg_cpu_util": 11.676041666666668,
"max_cpu_util": 24.9,
"test_duration": 20.144667863845825,
"total_frames": 2632,
"concurrent_streams": 1,
"batch_size": 8
}
],
"concurrent_streams": [
{
"engine_type": "pytorch",
"test_type": "concurrent_streams",
"avg_fps": 86.61065429991031,
"max_fps": 91.65636816278463,
"min_fps": 74.91135953012753,
"avg_latency_ms": 9.865907093056878,
"max_latency_ms": 51.9556999206543,
"min_latency_ms": 5.739450454711914,
"avg_gpu_util": 41.992805755395686,
"max_gpu_util": 53.0,
"avg_gpu_memory_mb": 2668.0,
"max_gpu_memory_mb": 2668.0,
"avg_cpu_util": 12.158992805755394,
"max_cpu_util": 35.4,
"test_duration": 30.0897319316864,
"total_frames": 2606,
"concurrent_streams": 1,
"batch_size": 1
},
{
"engine_type": "pytorch",
"test_type": "concurrent_streams",
"avg_fps": 50.604124453126666,
"max_fps": 56.399205092541045,
"min_fps": 44.21814201679432,
"avg_latency_ms": 18.050234584261236,
"max_latency_ms": 108.1399917602539,
"min_latency_ms": 10.535240173339844,
"avg_gpu_util": 50.98571428571429,
"max_gpu_util": 59.0,
"avg_gpu_memory_mb": 2676.0142857142855,
"max_gpu_memory_mb": 2678.0,
"avg_cpu_util": 13.657142857142857,
"max_cpu_util": 27.7,
"test_duration": 30.174683809280396,
"total_frames": 3033,
"concurrent_streams": 2,
"batch_size": 1
},
{
"engine_type": "pytorch",
"test_type": "concurrent_streams",
"avg_fps": 25.20076967057634,
"max_fps": 27.41376443219628,
"min_fps": 20.344201696820978,
"avg_latency_ms": 37.94886581168687,
"max_latency_ms": 186.68317794799805,
"min_latency_ms": 25.99501609802246,
"avg_gpu_util": 51.269503546099294,
"max_gpu_util": 61.0,
"avg_gpu_memory_mb": 2727.7801418439717,
"max_gpu_memory_mb": 2729.0,
"avg_cpu_util": 13.13262411347518,
"max_cpu_util": 26.7,
"test_duration": 30.055187463760376,
"total_frames": 3025,
"concurrent_streams": 4,
"batch_size": 1
},
{
"engine_type": "pytorch",
"test_type": "concurrent_streams",
"avg_fps": 16.443634992975014,
"max_fps": 18.21782815591864,
"min_fps": 12.60178365570841,
"avg_latency_ms": 59.1324243117457,
"max_latency_ms": 286.2060070037842,
"min_latency_ms": 40.11201858520508,
"avg_gpu_util": 50.878571428571426,
"max_gpu_util": 62.0,
"avg_gpu_memory_mb": 2809.542857142857,
"max_gpu_memory_mb": 2811.0,
"avg_cpu_util": 14.005714285714285,
"max_cpu_util": 35.0,
"test_duration": 30.247394561767578,
"total_frames": 2963,
"concurrent_streams": 6,
"batch_size": 1
},
{
"engine_type": "pytorch",
"test_type": "concurrent_streams",
"avg_fps": 11.761025734785418,
"max_fps": 13.709483947109453,
"min_fps": 7.478060641178502,
"avg_latency_ms": 83.21984625841317,
"max_latency_ms": 415.6522750854492,
"min_latency_ms": 47.42121696472168,
"avg_gpu_util": 50.3768115942029,
"max_gpu_util": 62.0,
"avg_gpu_memory_mb": 2892.7971014492755,
"max_gpu_memory_mb": 2896.0,
"avg_cpu_util": 14.269565217391303,
"max_cpu_util": 28.0,
"test_duration": 30.105501174926758,
"total_frames": 2826,
"concurrent_streams": 8,
"batch_size": 1
},
{
"engine_type": "pytorch",
"test_type": "concurrent_streams",
"avg_fps": 9.67794335949032,
"max_fps": 10.828001123698611,
"min_fps": 5.445376536594264,
"avg_latency_ms": 101.43148489424453,
"max_latency_ms": 551.2466430664062,
"min_latency_ms": 58.533430099487305,
"avg_gpu_util": 50.35971223021583,
"max_gpu_util": 59.0,
"avg_gpu_memory_mb": 2974.5251798561153,
"max_gpu_memory_mb": 2980.0,
"avg_cpu_util": 13.387769784172662,
"max_cpu_util": 25.8,
"test_duration": 30.12100648880005,
"total_frames": 2910,
"concurrent_streams": 10,
"batch_size": 1
}
]
},
"tensorrt": {
"single_inference": {
"engine_type": "tensorrt",
"test_type": "single_inference",
"avg_fps": 140.12202951994948,
"max_fps": 147.96355409164133,
"min_fps": 91.86217292446764,
"avg_latency_ms": 5.382912677464209,
"max_latency_ms": 97.11408615112305,
"min_latency_ms": 3.026247024536133,
"avg_gpu_util": 36.347517730496456,
"max_gpu_util": 42.0,
"avg_gpu_memory_mb": 2907.744680851064,
"max_gpu_memory_mb": 2908.0,
"avg_cpu_util": 12.994326241134752,
"max_cpu_util": 32.3,
"test_duration": 30.1738224029541,
"total_frames": 4212,
"concurrent_streams": 1,
"batch_size": 1
},
"error": "input size torch.Size([2, 3, 640, 640]) not equal to max model size (1, 3, 640, 640)"
},
"comparison": {},
"timestamp": "2026-01-19T10:42:47.687903",
"model_path": "C:/Users/16337/PycharmProjects/Security/yolo11n.pt"
}