cyy/yolov26n_model
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add YOLOv26n RDK X5 model and quantized artifacts

Browse Source
This commit is contained in:
cyy_mac
2026-08-07 11:15:41 +08:00
commit 7931375c8e
92 changed files with 24515 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

983
x5_quantization/checker_output/Extracted from {main_graph}_subgraph_0.html Normal file
View File

File diff suppressed because one or more lines are too long

213
x5_quantization/checker_output/Extracted from {main_graph}_subgraph_0.json Normal file
View File

@@ -0,0 +1,213 @@
{
"summary": {
"BPU OPs per frame (effective)": 2940160000,
"BPU OPs per run (effective)": 2940160000,
"BPU PE number": 1,
"BPU core number": 1,
"BPU march": "B25E",
"DDR bytes per frame": 122035200,
"DDR bytes per run": 122035200,
"DDR bytes per second": 6401297850,
"DDR megabytes per frame": 116.382,
"DDR megabytes per run": 116.382,
"DDR megabytes per second": 6104.8,
"FPS": 52.45,
"HBDK version": "3.49.15",
"compiling options": "-f hbir -m /tmp/tmpo3cnuwll/Extracted from {main_graph}_subgraph_0.hbir -o /tmp/tmpo3cnuwll/Extracted from {main_graph}_subgraph_0.hbm --march bayes-e --progressbar --input-layout NHWC --output-layout NHWC",
"frame per run": 1,
"frame per second": 52.45,
"input features": [
[
"input name",
"input size"
],
[
"images_calibrated_quantized",
"1x3x640x640"
]
],
"interval computing unit utilization": [
0.206,
0.136,
0.068,
0.095,
0.104,
0.052,
0.167,
0.104,
0.082,
0.094,
0.052,
0.116,
0.091,
0.078,
0.139,
0.247,
0.104,
0.142,
0.077,
0.194,
0.256,
0.115,
0.256,
0.164,
0.162,
0.161,
0.072,
0.12,
0.106,
0.147,
0.098,
0.086,
0.109,
0.27,
0.17,
0.084,
0.031,
0.084,
0.021
],
"interval computing units utilization": [
0.206,
0.136,
0.068,
0.095,
0.104,
0.052,
0.167,
0.104,
0.082,
0.094,
0.052,
0.116,
0.091,
0.078,
0.139,
0.247,
0.104,
0.142,
0.077,
0.194,
0.256,
0.115,
0.256,
0.164,
0.162,
0.161,
0.072,
0.12,
0.106,
0.147,
0.098,
0.086,
0.109,
0.27,
0.17,
0.084,
0.031,
0.084,
0.021
],
"interval loading bandwidth (megabytes/s)": [
1567,
2772,
3728,
3375,
3253,
3419,
3569,
3332,
3128,
3129,
3537,
3324,
3110,
3711,
3551,
2800,
2935,
3320,
3151,
3267,
2933,
2795,
3095,
3004,
3036,
3189,
3001,
3210,
3715,
2631,
1875,
2797,
3808,
4172,
3242,
2191,
2842,
3508,
1912
],
"interval number": 39,
"interval storing bandwidth (megabytes/s)": [
4079,
3124,
2647,
3125,
3125,
3125,
2729,
2767,
3276,
3279,
2977,
3140,
3215,
2768,
2770,
2887,
2803,
2794,
3141,
2869,
2425,
2636,
2421,
2226,
2437,
2483,
3134,
3174,
2502,
3435,
4276,
3652,
2602,
1582,
2150,
3870,
3841,
3115,
1647
],
"interval time (ms)": 0.5,
"latency (ms)": 19.06,
"latency (ms) by segments": [
19.064
],
"latency (us)": 19064.1,
"loaded bytes per frame": 63139840,
"loaded bytes per run": 63139840,
"model json CRC": "4bd1303b",
"model json file": "/tmp/tmpo3cnuwll/Extracted from {main_graph}_subgraph_0.hbir",
"model name": "Extracted from {main_graph}_subgraph_0",
"model param CRC": "00000000",
"multicore sync time (ms)": 0.0,
"run per second": 52.45,
"runtime version": "3.15.55.0",
"stored bytes per frame": 58895360,
"stored bytes per run": 58895360,
"worst FPS": 52.45
}
}

983
x5_quantization/checker_output/Extracted from {main_graph}_subgraph_1.html Normal file
View File

File diff suppressed because one or more lines are too long

257
x5_quantization/checker_output/Extracted from {main_graph}_subgraph_1.json Normal file
View File

@@ -0,0 +1,257 @@
{
"summary": {
"BPU OPs per frame (effective)": 2136627200,
"BPU OPs per run (effective)": 2136627200,
"BPU PE number": 1,
"BPU core number": 1,
"BPU march": "B25E",
"DDR bytes per frame": 138583616,
"DDR bytes per run": 138583616,
"DDR bytes per second": 6348938021,
"DDR megabytes per frame": 132.164,
"DDR megabytes per run": 132.164,
"DDR megabytes per second": 6054.8,
"FPS": 45.81,
"HBDK version": "3.49.15",
"compiling options": "-f hbir -m /tmp/tmpo3cnuwll/Extracted from {main_graph}_subgraph_1.hbir -o /tmp/tmpo3cnuwll/Extracted from {main_graph}_subgraph_1.hbm --march bayes-e --progressbar --input-layout NHWC --output-layout NHWC",
"frame per run": 1,
"frame per second": 45.81,
"input features": [
[
"input name",
"input size"
],
[
"/model.10/m/m.0/attn/Transpose_1_output_0_calibrated_quantized",
"1x2x400x400"
],
[
"/model.10/m/m.0/attn/Split_nhwc2nchw_transposed_output2",
"1x2x64x400"
],
[
"/model.10/m/m.0/attn/pe/conv/Conv_nchw2nhwc_transposed_input0",
"1x20x20x128"
],
[
"/model.10/Split_output_1_quantized",
"1x20x20x128"
],
[
"/model.10/Split_output_0_quantized",
"1x20x20x128"
],
[
"/model.6/cv2/act/Mul_output_0_quantized",
"1x40x40x128"
],
[
"/model.4/cv2/act/Mul_output_0_quantized",
"1x80x80x128"
]
],
"interval computing unit utilization": [
0.101,
0.101,
0.199,
0.154,
0.112,
0.108,
0.101,
0.079,
0.106,
0.185,
0.096,
0.355,
0.093,
0.139,
0.152,
0.124,
0.185,
0.039,
0.128,
0.103,
0.117,
0.112,
0.085,
0.148,
0.134,
0.137,
0.16,
0.172,
0.132,
0.178,
0.172,
0.155,
0.041,
0.159,
0.132,
0.102,
0.108,
0.106,
0.092,
0.258,
0.211,
0.005,
0.068,
0.063
],
"interval computing units utilization": [
0.101,
0.101,
0.199,
0.154,
0.112,
0.108,
0.101,
0.079,
0.106,
0.185,
0.096,
0.355,
0.093,
0.139,
0.152,
0.124,
0.185,
0.039,
0.128,
0.103,
0.117,
0.112,
0.085,
0.148,
0.134,
0.137,
0.16,
0.172,
0.132,
0.178,
0.172,
0.155,
0.041,
0.159,
0.132,
0.102,
0.108,
0.106,
0.092,
0.258,
0.211,
0.005,
0.068,
0.063
],
"interval loading bandwidth (megabytes/s)": [
3201,
2992,
2422,
1226,
830,
2343,
3369,
3361,
3314,
4400,
5767,
4176,
2968,
3160,
3091,
3270,
2892,
2888,
3125,
3881,
3804,
3113,
3257,
3351,
3364,
3170,
3187,
3041,
2923,
3186,
3201,
3079,
3135,
3143,
3389,
1956,
1806,
3369,
4712,
4296,
1800,
2998,
3677,
2265
],
"interval number": 44,
"interval storing bandwidth (megabytes/s)": [
3021,
3283,
3521,
4563,
5338,
3978,
2983,
3096,
3125,
1674,
351,
1289,
2402,
2939,
2861,
2539,
2782,
3369,
3389,
2392,
2421,
2929,
2929,
2832,
2636,
2832,
2645,
2539,
2726,
2529,
2333,
2513,
3134,
3191,
2505,
4209,
4556,
2963,
1693,
1549,
3476,
3214,
3125,
3059
],
"interval time (ms)": 0.5,
"latency (ms)": 21.83,
"latency (ms) by segments": [
21.828
],
"latency (us)": 21827.8,
"loaded bytes per frame": 72009792,
"loaded bytes per run": 72009792,
"model json CRC": "f7a1faaa",
"model json file": "/tmp/tmpo3cnuwll/Extracted from {main_graph}_subgraph_1.hbir",
"model name": "Extracted from {main_graph}_subgraph_1",
"model param CRC": "00000000",
"multicore sync time (ms)": 0.0,
"run per second": 45.81,
"runtime version": "3.15.55.0",
"stored bytes per frame": 66573824,
"stored bytes per run": 66573824,
"worst FPS": 45.81
}
}

983
x5_quantization/checker_output/Extracted from {main_graph}_subgraph_2.html Normal file
View File

File diff suppressed because one or more lines are too long

221
x5_quantization/checker_output/Extracted from {main_graph}_subgraph_2.json Normal file
View File

@@ -0,0 +1,221 @@
{
"summary": {
"BPU OPs per frame (effective)": 236339200,
"BPU OPs per run (effective)": 236339200,
"BPU PE number": 1,
"BPU core number": 1,
"BPU march": "B25E",
"DDR bytes per frame": 44277504,
"DDR bytes per run": 44277504,
"DDR bytes per second": 6318416482,
"DDR megabytes per frame": 42.226,
"DDR megabytes per run": 42.226,
"DDR megabytes per second": 6025.7,
"FPS": 142.7,
"HBDK version": "3.49.15",
"compiling options": "-f hbir -m /tmp/tmpo3cnuwll/Extracted from {main_graph}_subgraph_2.hbir -o /tmp/tmpo3cnuwll/Extracted from {main_graph}_subgraph_2.hbm --march bayes-e --progressbar --input-layout NHWC --output-layout NHWC",
"frame per run": 1,
"frame per second": 142.7,
"input features": [
[
"input name",
"input size"
],
[
"/model.22/m.0/m.0.1/attn/Transpose_1_output_0_calibrated_quantized",
"1x2x400x400"
],
[
"/model.22/m.0/m.0.1/attn/Split_nhwc2nchw_transposed_output2",
"1x2x64x400"
],
[
"/model.22/m.0/m.0.1/attn/pe/conv/Conv_nchw2nhwc_transposed_input0",
"1x20x20x128"
],
[
"/model.22/m.0/m.0.0/Add_output_0_quantized",
"1x20x20x128"
],
[
"/model.22/Split_output_0_quantized",
"1x20x20x128"
],
[
"/model.22/Split_output_1_quantized",
"1x20x20x128"
]
],
"interval computing unit utilization": [
0.062,
0.124,
0.098,
0.168,
0.05,
0.267,
0.229,
0.072,
0.12,
0.192,
0.192,
0.0,
0.088,
0.092,
0.179,
0.092,
0.087,
0.088,
0.092,
0.092,
0.179,
0.087,
0.0,
0.231,
0.231,
0.0,
0.231,
0.231,
0.615,
0.053,
0.08,
0.094,
0.137,
0.202,
0.122,
0.015
],
"interval computing units utilization": [
0.062,
0.124,
0.098,
0.168,
0.05,
0.267,
0.229,
0.072,
0.12,
0.192,
0.192,
0.0,
0.088,
0.092,
0.179,
0.092,
0.087,
0.088,
0.092,
0.092,
0.179,
0.087,
0.0,
0.231,
0.231,
0.0,
0.231,
0.231,
0.615,
0.053,
0.08,
0.094,
0.137,
0.202,
0.122,
0.015
],
"interval loading bandwidth (megabytes/s)": [
3916,
3024,
3019,
2929,
2502,
3547,
2578,
800,
244,
244,
488,
479,
2166,
3848,
3448,
2996,
2807,
3103,
3678,
3833,
3401,
2827,
4333,
5733,
5182,
5985,
6007,
4590,
2693,
2304,
3413,
3548,
3477,
3290,
3187,
1519
],
"interval number": 36,
"interval storing bandwidth (megabytes/s)": [
2539,
3234,
3166,
3147,
3772,
2322,
2589,
5149,
6193,
5762,
5251,
5956,
4636,
2612,
2683,
3135,
3654,
3371,
2780,
2612,
2730,
3320,
2469,
573,
292,
313,
292,
858,
1367,
2343,
3125,
2783,
2490,
2294,
2157,
1165
],
"interval time (ms)": 0.2,
"latency (ms)": 7.01,
"latency (ms) by segments": [
7.008
],
"latency (us)": 7007.7,
"loaded bytes per frame": 22904576,
"loaded bytes per run": 22904576,
"model json CRC": "29e36293",
"model json file": "/tmp/tmpo3cnuwll/Extracted from {main_graph}_subgraph_2.hbir",
"model name": "Extracted from {main_graph}_subgraph_2",
"model param CRC": "00000000",
"multicore sync time (ms)": 0.0,
"run per second": 142.7,
"runtime version": "3.15.55.0",
"stored bytes per frame": 21372928,
"stored bytes per run": 21372928,
"worst FPS": 142.7
}
}

BIN
x5_quantization/checker_output/calibrated_model.onnx Normal file
View File

Binary file not shown.

BIN
x5_quantization/checker_output/checker_hybrid_horizonrt.bin Normal file
View File

Binary file not shown.

983
x5_quantization/checker_output/main_graph_subgraph_0.html Normal file
View File

File diff suppressed because one or more lines are too long

213
x5_quantization/checker_output/main_graph_subgraph_0.json Normal file
View File

@@ -0,0 +1,213 @@
{
"summary": {
"BPU OPs per frame (effective)": 2940160000,
"BPU OPs per run (effective)": 2940160000,
"BPU PE number": 1,
"BPU core number": 1,
"BPU march": "B25E",
"DDR bytes per frame": 122035200,
"DDR bytes per run": 122035200,
"DDR bytes per second": 6401297850,
"DDR megabytes per frame": 116.382,
"DDR megabytes per run": 116.382,
"DDR megabytes per second": 6104.8,
"FPS": 52.45,
"HBDK version": "3.49.15",
"compiling options": "-f hbir -m /tmp/tmp0plq7oph/main_graph_subgraph_0.hbir -o /tmp/tmp0plq7oph/main_graph_subgraph_0.hbm --march bayes-e --progressbar --input-layout NHWC --output-layout NHWC",
"frame per run": 1,
"frame per second": 52.45,
"input features": [
[
"input name",
"input size"
],
[
"images_calibrated_quantized",
"1x3x640x640"
]
],
"interval computing unit utilization": [
0.206,
0.136,
0.068,
0.095,
0.104,
0.052,
0.167,
0.104,
0.082,
0.094,
0.052,
0.116,
0.091,
0.078,
0.139,
0.247,
0.104,
0.142,
0.077,
0.194,
0.256,
0.115,
0.256,
0.164,
0.162,
0.161,
0.072,
0.12,
0.106,
0.147,
0.098,
0.086,
0.109,
0.27,
0.17,
0.084,
0.031,
0.084,
0.021
],
"interval computing units utilization": [
0.206,
0.136,
0.068,
0.095,
0.104,
0.052,
0.167,
0.104,
0.082,
0.094,
0.052,
0.116,
0.091,
0.078,
0.139,
0.247,
0.104,
0.142,
0.077,
0.194,
0.256,
0.115,
0.256,
0.164,
0.162,
0.161,
0.072,
0.12,
0.106,
0.147,
0.098,
0.086,
0.109,
0.27,
0.17,
0.084,
0.031,
0.084,
0.021
],
"interval loading bandwidth (megabytes/s)": [
1567,
2772,
3728,
3375,
3253,
3419,
3569,
3332,
3128,
3129,
3537,
3324,
3110,
3711,
3551,
2800,
2935,
3320,
3151,
3267,
2933,
2795,
3095,
3004,
3036,
3189,
3001,
3210,
3715,
2631,
1875,
2797,
3808,
4172,
3242,
2191,
2842,
3508,
1912
],
"interval number": 39,
"interval storing bandwidth (megabytes/s)": [
4079,
3124,
2647,
3125,
3125,
3125,
2729,
2767,
3276,
3279,
2977,
3140,
3215,
2768,
2770,
2887,
2803,
2794,
3141,
2869,
2425,
2636,
2421,
2226,
2437,
2483,
3134,
3174,
2502,
3435,
4276,
3652,
2602,
1582,
2150,
3870,
3841,
3115,
1647
],
"interval time (ms)": 0.5,
"latency (ms)": 19.06,
"latency (ms) by segments": [
19.064
],
"latency (us)": 19064.1,
"loaded bytes per frame": 63139840,
"loaded bytes per run": 63139840,
"model json CRC": "4bd1303b",
"model json file": "/tmp/tmp0plq7oph/main_graph_subgraph_0.hbir",
"model name": "main_graph_subgraph_0",
"model param CRC": "00000000",
"multicore sync time (ms)": 0.0,
"run per second": 52.45,
"runtime version": "3.15.55.0",
"stored bytes per frame": 58895360,
"stored bytes per run": 58895360,
"worst FPS": 52.45
}
}

983
x5_quantization/checker_output/main_graph_subgraph_1.html Normal file
View File

File diff suppressed because one or more lines are too long

273
x5_quantization/checker_output/main_graph_subgraph_1.json Normal file
View File

@@ -0,0 +1,273 @@
{
"summary": {
"BPU OPs per frame (effective)": 2136627200,
"BPU OPs per run (effective)": 2136627200,
"BPU PE number": 1,
"BPU core number": 1,
"BPU march": "B25E",
"DDR bytes per frame": 149824064,
"DDR bytes per run": 149824064,
"DDR bytes per second": 6365457415,
"DDR megabytes per frame": 142.883,
"DDR megabytes per run": 142.883,
"DDR megabytes per second": 6070.6,
"FPS": 42.49,
"HBDK version": "3.49.15",
"compiling options": "-f hbir -m /tmp/tmp0plq7oph/main_graph_subgraph_1.hbir -o /tmp/tmp0plq7oph/main_graph_subgraph_1.hbm --march bayes-e --progressbar --input-layout NHWC --output-layout NHWC",
"frame per run": 1,
"frame per second": 42.49,
"input features": [
[
"input name",
"input size"
],
[
"/model.10/m/m.0/attn/Transpose_1_output_0_calibrated_quantized",
"1x2x400x400"
],
[
"/model.10/m/m.0/attn/Split_nhwc2nchw_transposed_output2",
"1x2x64x400"
],
[
"/model.10/m/m.0/attn/pe/conv/Conv_nchw2nhwc_transposed_input0",
"1x20x20x128"
],
[
"/model.10/Split_output_1_quantized",
"1x20x20x128"
],
[
"/model.10/Split_output_0_quantized",
"1x20x20x128"
],
[
"/model.6/cv2/act/Mul_output_0_quantized",
"1x40x40x128"
],
[
"/model.4/cv2/act/Mul_output_0_quantized",
"1x80x80x128"
]
],
"interval computing unit utilization": [
0.101,
0.101,
0.199,
0.154,
0.112,
0.108,
0.101,
0.079,
0.106,
0.185,
0.096,
0.355,
0.093,
0.139,
0.152,
0.124,
0.185,
0.039,
0.128,
0.103,
0.117,
0.112,
0.085,
0.148,
0.134,
0.137,
0.093,
0.163,
0.118,
0.124,
0.173,
0.106,
0.219,
0.144,
0.157,
0.064,
0.128,
0.1,
0.186,
0.072,
0.108,
0.126,
0.226,
0.159,
0.084,
0.031,
0.084,
0.021
],
"interval computing units utilization": [
0.101,
0.101,
0.199,
0.154,
0.112,
0.108,
0.101,
0.079,
0.106,
0.185,
0.096,
0.355,
0.093,
0.139,
0.152,
0.124,
0.185,
0.039,
0.128,
0.103,
0.117,
0.112,
0.085,
0.148,
0.134,
0.137,
0.093,
0.163,
0.118,
0.124,
0.173,
0.106,
0.219,
0.144,
0.157,
0.064,
0.128,
0.1,
0.186,
0.072,
0.108,
0.126,
0.226,
0.159,
0.084,
0.031,
0.084,
0.021
],
"interval loading bandwidth (megabytes/s)": [
3201,
2992,
2422,
1226,
830,
2343,
3369,
3361,
3314,
4400,
5767,
4176,
2968,
3160,
3091,
3270,
2892,
2888,
3125,
3881,
3804,
3113,
3257,
3351,
3364,
3207,
2952,
3133,
3392,
2887,
2981,
3392,
3286,
3127,
3018,
2975,
3132,
3628,
2591,
1769,
2832,
3808,
4208,
3242,
2314,
3034,
3506,
1721
],
"interval number": 48,
"interval storing bandwidth (megabytes/s)": [
3021,
3283,
3521,
4563,
5338,
3978,
2983,
3096,
3125,
1674,
351,
1289,
2402,
2939,
2861,
2539,
2782,
3369,
3389,
2392,
2421,
2929,
2929,
2832,
2636,
2788,
3193,
2944,
2573,
3218,
2852,
2454,
2415,
2336,
2602,
3137,
3250,
2570,
3364,
4348,
3632,
2462,
1638,
2343,
3786,
3648,
3115,
1647
],
"interval time (ms)": 0.5,
"latency (ms)": 23.54,
"latency (ms) by segments": [
23.537
],
"latency (us)": 23537.0,
"loaded bytes per frame": 77695040,
"loaded bytes per run": 77695040,
"model json CRC": "d4eae3d3",
"model json file": "/tmp/tmp0plq7oph/main_graph_subgraph_1.hbir",
"model name": "main_graph_subgraph_1",
"model param CRC": "00000000",
"multicore sync time (ms)": 0.0,
"run per second": 42.49,
"runtime version": "3.15.55.0",
"stored bytes per frame": 72129024,
"stored bytes per run": 72129024,
"worst FPS": 42.49
}
}

983
x5_quantization/checker_output/main_graph_subgraph_2.html Normal file
View File

File diff suppressed because one or more lines are too long

191
x5_quantization/checker_output/main_graph_subgraph_2.json Normal file
View File

@@ -0,0 +1,191 @@
{
"summary": {
"BPU OPs per frame (effective)": 236339200,
"BPU OPs per run (effective)": 236339200,
"BPU PE number": 1,
"BPU core number": 1,
"BPU march": "B25E",
"DDR bytes per frame": 69526848,
"DDR bytes per run": 69526848,
"DDR bytes per second": 6007224548,
"DDR megabytes per frame": 66.306,
"DDR megabytes per run": 66.306,
"DDR megabytes per second": 5728.9,
"FPS": 86.4,
"HBDK version": "3.49.15",
"compiling options": "-f hbir -m /tmp/tmp0plq7oph/main_graph_subgraph_2.hbir -o /tmp/tmp0plq7oph/main_graph_subgraph_2.hbm --march bayes-e --progressbar --input-layout NHWC --output-layout NHWC",
"frame per run": 1,
"frame per second": 86.4,
"input features": [
[
"input name",
"input size"
],
[
"/model.22/m.0/m.0.1/attn/Transpose_1_output_0_calibrated_quantized",
"1x2x400x400"
],
[
"/model.22/m.0/m.0.1/attn/Split_nhwc2nchw_transposed_output2",
"1x2x64x400"
],
[
"/model.22/m.0/m.0.1/attn/pe/conv/Conv_nchw2nhwc_transposed_input0",
"1x20x20x128"
],
[
"/model.22/m.0/m.0.0/Add_output_0_quantized",
"1x20x20x128"
],
[
"/model.22/Split_output_0_quantized",
"1x20x20x128"
],
[
"/model.22/Split_output_1_quantized",
"1x20x20x128"
],
[
"/model.23/Reshape_output_0_quantized",
"1x1x4x6400"
],
[
"/model.23/Reshape_1_output_0_quantized",
"1x1x4x1600"
],
[
"/model.23/Reshape_3_output_0_quantized",
"1x1x4x6400"
],
[
"/model.23/Reshape_4_output_0_quantized",
"1x1x4x1600"
]
],
"interval computing unit utilization": [
0.101,
0.101,
0.199,
0.154,
0.112,
0.108,
0.101,
0.079,
0.106,
0.185,
0.096,
0.355,
0.093,
0.157,
0.081,
0.075,
0.081,
0.088,
0.306,
0.215,
0.665,
0.293,
0.186,
0.04
],
"interval computing units utilization": [
0.101,
0.101,
0.199,
0.154,
0.112,
0.108,
0.101,
0.079,
0.106,
0.185,
0.096,
0.355,
0.093,
0.157,
0.081,
0.075,
0.081,
0.088,
0.306,
0.215,
0.665,
0.293,
0.186,
0.04
],
"interval loading bandwidth (megabytes/s)": [
3201,
2992,
2422,
1226,
830,
2343,
3369,
3361,
3314,
4400,
5767,
4176,
2968,
3307,
3182,
3782,
3875,
3431,
2435,
2139,
2077,
1788,
2890,
1952
],
"interval number": 24,
"interval storing bandwidth (megabytes/s)": [
3021,
3283,
3521,
4563,
5338,
3978,
2983,
3096,
3125,
1674,
351,
1289,
2402,
2529,
2602,
2379,
2306,
2694,
2816,
2836,
1861,
1879,
2413,
1197
],
"interval time (ms)": 0.5,
"latency (ms)": 11.57,
"latency (ms) by segments": [
11.479,
0.0,
0.095
],
"latency (us)": 11573.9,
"loaded bytes per frame": 36598144,
"loaded bytes per run": 36598144,
"model json CRC": "7202325c",
"model json file": "/tmp/tmp0plq7oph/main_graph_subgraph_2.hbir",
"model name": "main_graph_subgraph_2",
"model param CRC": "00000000",
"multicore sync time (ms)": 0.0,
"run per second": 86.4,
"runtime version": "3.15.55.0",
"stored bytes per frame": 32928704,
"stored bytes per run": 32928704,
"worst FPS": 86.4
}
}

983
x5_quantization/checker_output/main_graph_subgraph_3.html Normal file
View File

File diff suppressed because one or more lines are too long

86
x5_quantization/checker_output/main_graph_subgraph_3.json Normal file
View File

@@ -0,0 +1,86 @@
{
"summary": {
"BPU PE number": 1,
"BPU core number": 1,
"BPU march": "B25E",
"DDR bytes per frame": 1396800,
"DDR bytes per run": 1396800,
"DDR bytes per second": 5072300619,
"DDR megabytes per frame": 1.332,
"DDR megabytes per run": 1.332,
"DDR megabytes per second": 4837.3,
"FPS": 3631.37,
"HBDK version": "3.49.15",
"compiling options": "-f hbir -m /tmp/tmp0plq7oph/main_graph_subgraph_3.hbir -o /tmp/tmp0plq7oph/main_graph_subgraph_3.hbm --march bayes-e --progressbar --input-layout NHWC --output-layout NHWC",
"frame per run": 1,
"frame per second": 3631.37,
"input features": [
[
"input name",
"input size"
],
[
"/model.23/Split_output_1_quantized",
"1x1x8400x4"
],
[
"/model.23/Expand_output_0_/model.23/GatherElements_cast_input",
"1x1x300x4"
]
],
"interval computing unit utilization": [
0.403,
0.101,
0.194,
0.187,
0.317,
0.11
],
"interval computing units utilization": [
0.403,
0.101,
0.194,
0.187,
0.317,
0.11
],
"interval loading bandwidth (megabytes/s)": [
1831,
2380,
3024,
2792,
2317,
1639
],
"interval number": 6,
"interval storing bandwidth (megabytes/s)": [
1975,
2642,
2857,
2262,
2158,
1603
],
"interval time (ms)": 0.05,
"latency (ms)": 0.28,
"latency (ms) by segments": [
0.0,
0.157,
0.0,
0.118
],
"latency (us)": 275.4,
"loaded bytes per frame": 714368,
"loaded bytes per run": 714368,
"model json CRC": "d2eeed26",
"model json file": "/tmp/tmp0plq7oph/main_graph_subgraph_3.hbir",
"model name": "main_graph_subgraph_3",
"model param CRC": "00000000",
"multicore sync time (ms)": 0.0,
"run per second": 3631.37,
"runtime version": "3.15.55.0",
"stored bytes per frame": 682432,
"stored bytes per run": 682432,
"worst FPS": 3631.37
}
}

983
x5_quantization/checker_output/main_graph_subgraph_4.html Normal file
View File

File diff suppressed because one or more lines are too long

100
x5_quantization/checker_output/main_graph_subgraph_4.json Normal file
View File

@@ -0,0 +1,100 @@
{
"summary": {
"BPU PE number": 1,
"BPU core number": 1,
"BPU march": "B25E",
"DDR bytes per frame": 120960,
"DDR bytes per run": 120960,
"DDR bytes per second": 3114475513,
"DDR megabytes per frame": 0.115,
"DDR megabytes per run": 0.115,
"DDR megabytes per second": 2970.2,
"FPS": 25747.98,
"HBDK version": "3.49.15",
"compiling options": "-f hbir -m /tmp/tmp0plq7oph/main_graph_subgraph_4.hbir -o /tmp/tmp0plq7oph/main_graph_subgraph_4.hbm --march bayes-e --progressbar --input-layout NHWC --output-layout NHWC",
"frame per run": 1,
"frame per second": 25747.98,
"input features": [
[
"input name",
"input size"
],
[
"/model.23/Split_output_0_quantized",
"1x1x8400x4"
],
[
"/model.23/Expand_1_output_0_/model.23/GatherElements_2_cast_input",
"1x1x300x4"
],
[
"/model.23/Unsqueeze_2_output_0_calibrated_Requantize_requantized_output",
"1x1x300x1"
],
[
"/model.23/Cast_2_output_0_calibrated_quantized",
"1x1x300x1"
]
],
"interval computing unit utilization": [
0.103,
0.072,
0.154,
0.262,
0.074,
0.09,
0.088,
0.38
],
"interval computing units utilization": [
0.103,
0.072,
0.154,
0.262,
0.074,
0.09,
0.088,
0.38
],
"interval loading bandwidth (megabytes/s)": [
1159,
1988,
4125,
3204,
1013,
952,
1382,
1293
],
"interval number": 8,
"interval storing bandwidth (megabytes/s)": [
1049,
1049,
524,
463,
1220,
1066,
1366,
1515
],
"interval time (ms)": 0.005,
"latency (ms)": 0.04,
"latency (ms) by segments": [
0.0,
0.039
],
"latency (us)": 38.8,
"loaded bytes per frame": 78016,
"loaded bytes per run": 78016,
"model json CRC": "6234711c",
"model json file": "/tmp/tmp0plq7oph/main_graph_subgraph_4.hbir",
"model name": "main_graph_subgraph_4",
"model param CRC": "00000000",
"multicore sync time (ms)": 0.0,
"run per second": 25747.98,
"runtime version": "3.15.55.0",
"stored bytes per frame": 42944,
"stored bytes per run": 42944,
"worst FPS": 25747.98
}
}

BIN
x5_quantization/checker_output/optimized_float_model.onnx Normal file
View File

Binary file not shown.

BIN
x5_quantization/checker_output/original_float_model.onnx Normal file
View File

Binary file not shown.

4235
x5_quantization/checker_output/quant_info.json Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
x5_quantization/checker_output/quantized_model.onnx Normal file
View File

Binary file not shown.