Hugging Face's logo

STMicroelectronics
/
st_yolo_lc_v1

Object Detection
Model card Files
xet
Community
FBAGSTM commited on
Commit
6e23b40
·
verified ·
1 Parent(s): 25c6fa8

Update Readme ST Model Zoo

Browse files
Files changed (1) hide show
  1. README.md +39 -51
README.md CHANGED
@@ -1,10 +1,3 @@
1
- ---
2
- license: other
3
- license_name: sla0044
4
- license_link: >-
5
- https://github.com/STMicroelectronics/stm32aimodelzoo/object_detection/st_yolo_lc_v1/ST_pretrainedmodel_public_dataset/LICENSE.md
6
- pipeline_tag: object-detection
7
- ---
8
  # ST YOLO LC V1 quantized
9
 
10
  ## **Use case** : `Object detection`
@@ -64,53 +57,49 @@ Measures are done with default STM32Cube.AI configuration with enabled input / o
64
 
65
 
66
  ### Reference **NPU** memory footprint based on COCO Person dataset (see Accuracy for details on dataset)
67
- |Model | Dataset | Format | Resolution | Series | Internal RAM (KiB) | External RAM (KiB)| Weights Flash (KiB)| STM32Cube.AI version | STEdgeAI Core version |
68
- |----------|------------------|--------|-------------|------------------|------------------|---------------------|-------|----------------------|-------------------------|
69
- | [st_yolo_lc_v1](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/st_yolo_lc_v1/ST_pretrainedmodel_public_dataset/coco_2017_person/st_yolo_lc_v1_192/st_yolo_lc_v1_192_int8.tflite)| COCO-Person | Int8 | 192x192x3 | STM32N6 | 252 | 0.0 | 328.19 | 10.0.0 | 2.0.0 |
70
- | [st_yolo_lc_v1](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/st_yolo_lc_v1/ST_pretrainedmodel_public_dataset/coco_2017_person/st_yolo_lc_v1_224/st_yolo_lc_v1_224_int8.tflite)| COCO-Person | Int8 | 256x256x3 | STM32N6 | 343 | 0.0 | 328.19 | 10.0.0 | 2.0.0 |
71
- | [st_yolo_lc_v1](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/st_yolo_lc_v1/ST_pretrainedmodel_public_dataset/coco_2017_person/st_yolo_lc_v1_256/st_yolo_lc_v1_256_int8.tflite)| COCO-Person | Int8 | 256x256x3 | STM32N6 | 576 | 0.0 | 328.19 | 10.0.0 | 2.0.0 |
72
-
73
-
74
  ### Reference **NPU** inference time based on COCO Person dataset (see Accuracy for details on dataset)
75
- | Model | Dataset | Format | Resolution | Board | Execution Engine | Inference time (ms) | Inf / sec | STM32Cube.AI version | STEdgeAI Core version |
76
- |--------|------------------|--------|-------------|------------------|------------------|---------------------|-------|----------------------|-------------------------|
77
- | [st_yolo_lc_v1](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/st_yolo_lc_v1/ST_pretrainedmodel_public_dataset/coco_2017_person/st_yolo_lc_v1_192/st_yolo_lc_v1_192_int8.tflite) | COCO-Person | Int8 | 192x192x3 | STM32N6570-DK | NPU/MCU | 1.96 | 510.20 | 10.0.0 | 2.0.0 |
78
- | [st_yolo_lc_v1](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/st_yolo_lc_v1/ST_pretrainedmodel_public_dataset/coco_2017_person/st_yolo_lc_v1_224/st_yolo_lc_v1_224_int8.tflite) | COCO-Person | Int8 | 256x256x3 | STM32N6570-DK | NPU/MCU | 2.35 | 425.53 | 10.0.0 | 2.0.0 |
79
- | [st_yolo_lc_v1](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/st_yolo_lc_v1/ST_pretrainedmodel_public_dataset/coco_2017_person/st_yolo_lc_v1_256/st_yolo_lc_v1_256_int8.tflite) | COCO-Person | Int8 256x256x3 | STM32N6570-DK | NPU/MCU | 3.01 | 332.23 | 10.0.0 | 2.0.0 |
80
 
81
  ### Reference **MCU** memory footprint based on COCO Person dataset (see Accuracy for details on dataset)
82
 
83
 
84
- | Model | Format | Resolution | Series | Activation RAM | Runtime RAM | Weights Flash | Code Flash | Total RAM | Total Flash | STM32Cube.AI version |
85
- |-------------------|--------|------------|---------|----------------|-------------|---------------|-----------------|--------------|-------------|-----------------------|
86
- | st_yolo_lc_v1 | Int8 | 192x192x3 | STM32H7 | 166.29 KiB | 8.09 KiB | 276.73 KiB | 53.48 KiB | 174.38 KiB | 330.21 KiB | 10.0.0 |
87
- | st_yolo_lc_v1 | Int8 | 224x224x3 | STM32H7 | 217.29 KiB | 8.09 KiB | 276.73 KiB | 53.48 KiB | 225.38 KiB | 330.21 KiB | 10.0.0 |
88
- | st_yolo_lc_v1 | Int8 | 256x256x3 | STM32H7 | 278.29 KiB | 8.09 KiB | 276.73 KiB | 53.48 KiB | 286.38 KiB | 330.21 KiB | 10.0.0 |
89
-
90
 
91
  ### Reference **MCU** inference time based on COCO Person dataset (see Accuracy for details on dataset)
92
 
93
 
94
- | Model | Format | Resolution | Board | Execution Engine | Frequency | Inference time (ms) | STM32Cube.AI version |
95
- |-------------------|--------|------------|------------------|------------------|-------------|---------------------|-----------------------|
96
- | st_yolo_lc_v1 | Int8 | 192x192x3 | STM32H747I-DISCO | 1 CPU | 400 MHz | 179.01 | 10.0.0 |
97
- | st_yolo_lc_v1 | Int8 | 224x224x3 | STM32H747I-DISCO | 1 CPU | 400 MHz | 244.7 | 10.0.0 |
98
- | st_yolo_lc_v1 | Int8 | 256x256x3 | STM32H747I-DISCO | 1 CPU | 400 MHz | 321.38 | 10.0.0 |
99
-
100
 
101
  ### Reference **MPU** inference time based on COCO Person dataset (see Accuracy for details on dataset)
102
 
103
  | Model | Format | Resolution | Quantization | Board | Execution Engine | Frequency | Inference time (ms) | %NPU | %GPU | %CPU | X-LINUX-AI version | Framework |
104
  |---------------|--------|------------|---------------|-------------------|------------------|-----------|---------------------|-------|-------|------|--------------------|-----------------------|
105
- | st_yolo_lc_v1 | Int8 | 192x192x3 | per-channel** | STM32MP257F-DK2 | NPU/GPU | 800 MHz | 12.00 ms | 2.62 | 97.38 |0 | v5.1.0 | OpenVX |
106
- | st_yolo_lc_v1 | Int8 | 224x224x3 | per-channel** | STM32MP257F-DK2 | NPU/GPU | 800 MHz | 17.92 ms | 2.43 | 97.57 |0 | v5.1.0 | OpenVX |
107
- | st_yolo_lc_v1 | Int8 | 256x256x3 | per-channel** | STM32MP257F-DK2 | NPU/GPU | 800 MHz | 14.43 ms | 3.20 | 96.80 |0 | v5.1.0 | OpenVX |
108
- | st_yolo_lc_v1 | Int8 | 192x192x3 | per-channel | STM32MP157F-DK2 | 2 CPU | 800 MHz | 32.84 ms | NA | NA |100 | v5.1.0 | TensorFlowLite 2.11.0 |
109
- | st_yolo_lc_v1 | Int8 | 224x224x3 | per-channel | STM32MP157F-DK2 | 2 CPU | 800 MHz | 45.13 ms | NA | NA |100 | v5.1.0 | TensorFlowLite 2.11.0 |
110
- | st_yolo_lc_v1 | Int8 | 256x256x3 | per-channel | STM32MP157F-DK2 | 2 CPU | 800 MHz | 59.38 ms | NA | NA |100 | v5.1.0 | TensorFlowLite 2.11.0 |
111
- | st_yolo_lc_v1 | Int8 | 192x192x3 | per-channel | STM32MP135F-DK2 | 1 CPU | 1000 MHz | 52.64 ms | NA | NA |100 | v5.1.0 | TensorFlowLite 2.11.0 |
112
- | st_yolo_lc_v1 | Int8 | 224x224x3 | per-channel | STM32MP135F-DK2 | 1 CPU | 1000 MHz | 71.26 ms | NA | NA |100 | v5.1.0 | TensorFlowLite 2.11.0 |
113
- | st_yolo_lc_v1 | Int8 | 256x256x3 | per-channel | STM32MP135F-DK2 | 1 CPU | 1000 MHz | 93.50 ms | NA | NA |100 | v5.1.0 | TensorFlowLite 2.11.0 |
114
 
115
  ** **To get the most out of MP25 NPU hardware acceleration, please use per-tensor quantization**
116
 
@@ -119,16 +108,16 @@ Measures are done with default STM32Cube.AI configuration with enabled input / o
119
 
120
  Dataset details: [link](https://cocodataset.org/#download) , License [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/legalcode) , Quotation[[1]](#1) , Number of classes: 80, Number of images: 118,287
121
 
122
- | Model | Format | Resolution | AP |
123
- |-------|--------|------------|----------------|
124
- | st_yolo_lc_v1 | Int8 | 192x192x3 | 39.0 % |
125
- | st_yolo_lc_v1 | Float | 192x192x3 | 39.2 % |
126
- | st_yolo_lc_v1 | Int8 | 224x224x3 | 42.94 % |
127
- | st_yolo_lc_v1 | Float | 224x224x3 | 41.7 % |
128
- | st_yolo_lc_v1 | Int8 | 256x256x3 | 43.8 % |
129
- | st_yolo_lc_v1 | Float | 256x256x3 | 44.7 % |
130
 
131
- \* EVAL_IOU = 0.4, NMS_THRESH = 0.5, SCORE_THRESH =0.001
132
 
133
 
134
  ## Retraining and Integration in a simple example:
@@ -160,5 +149,4 @@ Please refer to the stm32ai-modelzoo-services GitHub [here](https://github.com/S
160
  timestamp = {Mon, 13 Aug 2018 16:48:13 +0200},
161
  biburl = {https://dblp.org/rec/bib/journals/corr/LinMBHPRDZ14},
162
  bibsource = {dblp computer science bibliography, https://dblp.org}
163
- }
164
-
 
 
 
 
 
 
 
 
1
  # ST YOLO LC V1 quantized
2
 
3
  ## **Use case** : `Object detection`
 
57
 
58
 
59
  ### Reference **NPU** memory footprint based on COCO Person dataset (see Accuracy for details on dataset)
60
+ | Model | Dataset | Format | Resolution | Series | Internal RAM (KiB) | External RAM (KiB) | Weights Flash (KiB) | STM32Cube.AI version | STEdgeAI Core version |
61
+ |---------------------------------------------------------------------------------------------------------------------|-------------|----------|--------------|----------|----------------------|----------------------|-----------------------|------------------------|-------------------------|
62
+ | [st_yolo_lc_v1](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/st_yolo_lc_v1/ST_pretrainedmodel_public_dataset/coco_2017_person/st_yolo_lc_v1_192/st_yolo_lc_v1_192_int8.tflite) | COCO-Person | Int8 | 192x192x3 | STM32N6 | 252 | 0 | 316.69 | 10.2.0 | 2.2.0 |
63
+ | [st_yolo_lc_v1](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/st_yolo_lc_v1/ST_pretrainedmodel_public_dataset/coco_2017_person/st_yolo_lc_v1_224/st_yolo_lc_v1_224_int8.tflite) | COCO-Person | Int8 | 224x224x3 | STM32N6 | 343 | 0 | 316.69 | 10.2.0 | 2.2.0 |
64
+ | [st_yolo_lc_v1](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/st_yolo_lc_v1/ST_pretrainedmodel_public_dataset/coco_2017_person/st_yolo_lc_v1_256/st_yolo_lc_v1_256_int8.tflite) | COCO-Person | Int8 | 256x256x3 | STM32N6 | 576 | 0 | 316.69 | 10.2.0 | 2.2.0 |
 
 
65
  ### Reference **NPU** inference time based on COCO Person dataset (see Accuracy for details on dataset)
66
+ | Model | Dataset | Format | Resolution | Board | Execution Engine | Inference time (ms) | Inf / sec | STM32Cube.AI version | STEdgeAI Core version |
67
+ |---------------------------------------------------------------------------------------------------------------------|-------------|----------|--------------|---------------|--------------------|-----------------------|-------------|------------------------|-------------------------|
68
+ | [st_yolo_lc_v1](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/st_yolo_lc_v1/ST_pretrainedmodel_public_dataset/coco_2017_person/st_yolo_lc_v1_192/st_yolo_lc_v1_192_int8.tflite) | COCO-Person | Int8 | 192x192x3 | STM32N6570-DK | NPU/MCU | 1.96 | 510.2 | 10.2.0 | 2.2.0 |
69
+ | [st_yolo_lc_v1](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/st_yolo_lc_v1/ST_pretrainedmodel_public_dataset/coco_2017_person/st_yolo_lc_v1_224/st_yolo_lc_v1_224_int8.tflite) | COCO-Person | Int8 | 224x224x3 | STM32N6570-DK | NPU/MCU | 2.36 | 423.73 | 10.2.0 | 2.2.0 |
70
+ | [st_yolo_lc_v1](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/st_yolo_lc_v1/ST_pretrainedmodel_public_dataset/coco_2017_person/st_yolo_lc_v1_224/st_yolo_lc_v1_256_int8.tflite) | COCO-Person | Int8 | 256x256x3 | STM32N6570-DK | NPU/MCU | 3.02 | 331.13 | 10.2.0 | 2.2.0 |
71
 
72
  ### Reference **MCU** memory footprint based on COCO Person dataset (see Accuracy for details on dataset)
73
 
74
 
75
+ | Model | Format | Resolution | Series | Activation RAM | Runtime RAM | Weights Flash | Code Flash | Total RAM | Total Flash | STM32Cube.AI version |
76
+ |---------------------------------------------------------------------------------------------------------------------|----------|--------------|----------|------------------|---------------|-----------------|--------------|-------------|---------------|------------------------|
77
+ | [st_yolo_lc_v1](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/st_yolo_lc_v1/ST_pretrainedmodel_public_dataset/coco_2017_person/st_yolo_lc_v1_192/st_yolo_lc_v1_192_int8.tflite) | Int8 | 192x192x3 | STM32H7 | 166.29 | 8.09 | 276.73 | 52.81 | 174.38 | 329.54 | 10.2.0 |
78
+ | [st_yolo_lc_v1](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/st_yolo_lc_v1/ST_pretrainedmodel_public_dataset/coco_2017_person/st_yolo_lc_v1_224/st_yolo_lc_v1_224_int8.tflite) | Int8 | 224x224x3 | STM32H7 | 217.29 | 8.09 | 276.73 | 52.82 | 225.38 | 329.55 | 10.2.0 |
79
+ | [st_yolo_lc_v1](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/st_yolo_lc_v1/ST_pretrainedmodel_public_dataset/coco_2017_person/st_yolo_lc_v1_256/st_yolo_lc_v1_256_int8.tflite) | Int8 | 256x256x3 | STM32H7 | 278.29 | 8.09 | 276.73 | 52.81 | 286.38 | 329.54 | 10.2.0 |
 
80
 
81
  ### Reference **MCU** inference time based on COCO Person dataset (see Accuracy for details on dataset)
82
 
83
 
84
+ | Model | Format | Resolution | Board | Execution Engine | Frequency | Inference time (ms) | STM32Cube.AI version |
85
+ |---------------------------------------------------------------------------------------------------------------------|----------|--------------|------------------|--------------------|-------------|-----------------------|------------------------|
86
+ | [st_yolo_lc_v1](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/st_yolo_lc_v1/ST_pretrainedmodel_public_dataset/coco_2017_person/st_yolo_lc_v1_192/st_yolo_lc_v1_192_int8.tflite) | Int8 | 192x192x3 | STM32H747I-DISCO | 1 CPU | 400 MHz | 179.36 | 10.2.0 |
87
+ | [st_yolo_lc_v1](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/st_yolo_lc_v1/ST_pretrainedmodel_public_dataset/coco_2017_person/st_yolo_lc_v1_224/st_yolo_lc_v1_224_int8.tflite) | Int8 | 224x224x3 | STM32H747I-DISCO | 1 CPU | 400 MHz | 244.75 | 10.2.0 |
88
+ | [st_yolo_lc_v1](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/st_yolo_lc_v1/ST_pretrainedmodel_public_dataset/coco_2017_person/st_yolo_lc_v1_256/st_yolo_lc_v1_256_int8.tflite) | Int8 | 256x256x3 | STM32H747I-DISCO | 1 CPU | 400 MHz | 320.79 | 10.2.0 |
 
89
 
90
  ### Reference **MPU** inference time based on COCO Person dataset (see Accuracy for details on dataset)
91
 
92
  | Model | Format | Resolution | Quantization | Board | Execution Engine | Frequency | Inference time (ms) | %NPU | %GPU | %CPU | X-LINUX-AI version | Framework |
93
  |---------------|--------|------------|---------------|-------------------|------------------|-----------|---------------------|-------|-------|------|--------------------|-----------------------|
94
+ | st_yolo_lc_v1 | Int8 | 192x192x3 | per-channel** | STM32MP257F-DK2 | NPU/GPU | 800 MHz | 11.88 ms | 2.62 | 97.38 |0 | v6.1.0 | OpenVX |
95
+ | st_yolo_lc_v1 | Int8 | 224x224x3 | per-channel** | STM32MP257F-DK2 | NPU/GPU | 800 MHz | 17.60 ms | 3.33 | 96.67 |0 | v6.1.0 | OpenVX |
96
+ | st_yolo_lc_v1 | Int8 | 256x256x3 | per-channel** | STM32MP257F-DK2 | NPU/GPU | 800 MHz | 13.93 ms | 5.12 | 94.88 |0 | v6.1.0 | OpenVX |
97
+ | st_yolo_lc_v1 | Int8 | 192x192x3 | per-channel | STM32MP157F-DK2 | 2 CPU | 800 MHz | 33.38 ms | NA | NA |100 | v6.1.0 | TensorFlowLite 2.18.0 |
98
+ | st_yolo_lc_v1 | Int8 | 224x224x3 | per-channel | STM32MP157F-DK2 | 2 CPU | 800 MHz | 45.43 ms | NA | NA |100 | v6.1.0 | TensorFlowLite 2.18.0 |
99
+ | st_yolo_lc_v1 | Int8 | 256x256x3 | per-channel | STM32MP157F-DK2 | 2 CPU | 800 MHz | 58.80 ms | NA | NA |100 | v6.1.0 | TensorFlowLite 2.18.0 |
100
+ | st_yolo_lc_v1 | Int8 | 192x192x3 | per-channel | STM32MP135F-DK2 | 1 CPU | 1000 MHz | 52.63 ms | NA | NA |100 | v6.1.0 | TensorFlowLite 2.18.0 |
101
+ | st_yolo_lc_v1 | Int8 | 224x224x3 | per-channel | STM32MP135F-DK2 | 1 CPU | 1000 MHz | 72.51 ms | NA | NA |100 | v6.1.0 | TensorFlowLite 2.18.0 |
102
+ | st_yolo_lc_v1 | Int8 | 256x256x3 | per-channel | STM32MP135F-DK2 | 1 CPU | 1000 MHz | 95.84 ms | NA | NA |100 | v6.1.0 | TensorFlowLite 2.18.0 |
103
 
104
  ** **To get the most out of MP25 NPU hardware acceleration, please use per-tensor quantization**
105
 
 
108
 
109
  Dataset details: [link](https://cocodataset.org/#download) , License [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/legalcode) , Quotation[[1]](#1) , Number of classes: 80, Number of images: 118,287
110
 
111
+ | Model | Format | Resolution | AP |
112
+ |-------|--------|------------|----|
113
+ | st_yolo_lc_v1 | Int8 | 192x192x3 | 30.7 % |
114
+ | st_yolo_lc_v1 | Float | 192x192x3 | 31.2 % |
115
+ | st_yolo_lc_v1 | Int8 | 224x224x3 | 34.2 % |
116
+ | st_yolo_lc_v1 | Float | 224x224x3 | 33.8 % |
117
+ | st_yolo_lc_v1 | Int8 | 256x256x3 | 35.6 % |
118
+ | st_yolo_lc_v1 | Float | 256x256x3 | 36.4 % |
119
 
120
+ \* EVAL_IOU = 0.5, NMS_THRESH = 0.5, SCORE_THRESH = 0.001, MAX_DETECTIONS = 100
121
 
122
 
123
  ## Retraining and Integration in a simple example:
 
149
  timestamp = {Mon, 13 Aug 2018 16:48:13 +0200},
150
  biburl = {https://dblp.org/rec/bib/journals/corr/LinMBHPRDZ14},
151
  bibsource = {dblp computer science bibliography, https://dblp.org}
152
+ }