Hugging Face's logo

STMicroelectronics
/
tiny_yolo_v2

Object Detection
Model card Files Community
FBAGSTM commited on
Commit
cea78a8
·
verified ·
1 Parent(s): a3deb45

Update Readme ST Model Zoo

Browse files
Files changed (1) hide show
  1. README.md +37 -48
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/tiny_yolo_v2/ST_pretrainedmodel_custom_dataset/LICENSE.md
6
- pipeline_tag: object-detection
7
- ---
8
  # Tiny Yolo v2 quantized
9
 
10
  ## **Use case** : `Object detection`
@@ -64,51 +57,47 @@ For an image resolution of NxM and NC classes
64
  Measures are done with default STM32Cube.AI configuration with enabled input / output allocated option.
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
- | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_224/tiny_yolo_v2_224_int8.tflite) | COCO-Person | Int8 | 224x224x3 | STM32N6 | 392 | 0.0 | 10804.81 | 10.0.0 | 2.0.0 |
70
- | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_custom_dataset/st_person/tiny_yolo_v2_224/tiny_yolo_v2_224_int8.tflite) | ST-Person | Int8 | 224x224x3 | STM32N6 | 392 | 0.0 | 10804.81 | 10.0.0 | 2.0.0 |
71
- | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_416/tiny_yolo_v2_416_int8.tflite) | COCO-Person | Int8 | 416x416x3 | STM32N6 | 1880.12 | 0.0 | 10829 | 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
- | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_224/tiny_yolo_v2_224_int8.tflite) | COCO-Person | Int8 | 224x224x3 | STM32N6570-DK | NPU/MCU | 30.67 | 32.61 |10.0.0 | 2.0.0 |
78
- | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_custom_dataset/st_person/tiny_yolo_v2_224/tiny_yolo_v2_224_int8.tflite) | ST-Person | Int8 | 224x224x3 | STM32N6570-DK | NPU/MCU | 30.67 | 32.61| 10.0.0 | 2.0.0 |
79
- | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_416/tiny_yolo_v2_416_int8.tflite) | COCO-Person | Int8 | 416x416x3 | STM32N6570-DK | NPU/MCU | 50.91 | 19.64 | 10.0.0 | 2.0.0 |
80
-
81
 
82
  ### Reference **MCU** memory footprint based on COCO Person dataset (see Accuracy for details on dataset)
83
 
84
- | Model | Format | Resolution | Series | Activation RAM | Runtime RAM | Weights Flash | Code Flash | Total RAM | Total Flash | STM32Cube.AI version |
85
- |-------------------|--------|--------------|---------|----------------|-------------|---------------|------------|-------------|--------------|-----------------------|
86
- | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_192/tiny_yolo_v2_192_int8.tflite) | Int8 | 192x192x3 | STM32H7 | 220.6 KiB | 7.98 KiB | 10775.98 KiB | 55.85 KiB | 228.58 KiB | 10831.83 KiB | 10.0.0 |
87
- | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_224/tiny_yolo_v2_224_int8.tflite) | Int8 | 224x224x3 | STM32H7 | 249.35 KiB | 7.98 KiB | 10775.98 KiB | 55.8 KiB | 257.33 KiB | 10831.78 KiB | 10.0.0 |
88
- | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_416/tiny_yolo_v2_416_int8.tflite) | Int8 | 416x416x3 | STM32H7 | 1263.07 KiB | 8.03 KiB | 10775.98 KiB | 55.85 KiB | 1271.1 KiB | 10831.83 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
- | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_192/tiny_yolo_v2_192_int8.tflite) | Int8 | 192x192x3 | STM32H747I-DISCO | 1 CPU | 400 MHz | 3006.3 ms | 10.0.0 |
97
- | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_224/tiny_yolo_v2_224_int8.tflite) | Int8 | 224x224x3 | STM32H747I-DISCO | 1 CPU | 400 MHz | 2742.3 ms | 10.0.0 |
98
- | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_416/tiny_yolo_v2_416_int8.tflite) | Int8 | 416x416x3 | STM32H747I-DISCO | 1 CPU | 400 MHz | 10468.2 ms | 10.0.0 |
99
-
100
 
101
  ### Reference **MPU** inference time based on COCO Person dataset (see Accuracy for details on dataset)
102
 
103
 
104
  | Model | Format | Resolution | Quantization | Board | Execution Engine | Frequency | Inference time (ms) | %NPU | %GPU | %CPU | X-LINUX-AI version | Framework |
105
  |--------------|--------|------------|---------------|-------------------|------------------|-----------|---------------------|-------|-------|------|--------------------|-----------------------|
106
- | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_224/tiny_yolo_v2_224_int8.tflite) | Int8 | 224x224x3 | per-channel** | STM32MP257F-DK2 | NPU/GPU | 800 MHz | 120.8 ms | 3.45 | 96.55 |0 | v5.1.0 | OpenVX |
107
- | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_416/tiny_yolo_v2_416_int8.tflite) | Int8 | 416x416x3 | per-channel** | STM32MP257F-DK2 | NPU/GPU | 800 MHz | 425.6 ms | 2.74 | 97.26 |0 | v5.1.0 | OpenVX |
108
- | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_224/tiny_yolo_v2_224_int8.tflite) | Int8 | 224x224x3 | per-channel | STM32MP157F-DK2 | 2 CPU | 800 MHz | 410.50 ms | NA | NA |100 | v5.1.0 | TensorFlowLite 2.11.0 |
109
- | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_416/tiny_yolo_v2_416_int8.tflite) | Int8 | 416x416x3 | per-channel | STM32MP157F-DK2 | 2 CPU | 800 MHz | 1347 ms | NA | NA |100 | v5.1.0 | TensorFlowLite 2.11.0 |
110
- | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_224/tiny_yolo_v2_224_int8.tflite) | Int8 | 224x224x3 | per-channel | STM32MP135F-DK2 | 1 CPU | 1000 MHz | 619.70 ms | NA | NA |100 | v5.1.0 | TensorFlowLite 2.11.0 |
111
- | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_416/tiny_yolo_v2_416_int8.tflite) | Int8 | 416x416x3 | per-channel | STM32MP135F-DK2 | 1 CPU | 1000 MHz | 2105 ms | NA | NA |100 | v5.1.0 | TensorFlowLite 2.11.0 |
112
 
113
  ** **To get the most out of MP25 NPU hardware acceleration, please use per-tensor quantization**
114
 
@@ -118,23 +107,24 @@ Dataset details: [link](https://cocodataset.org/#download) , License [CC BY 4.0]
118
 
119
  | Model | Format | Resolution | AP |
120
  |-------|--------|------------|----------------|
121
- | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_192/tiny_yolo_v2_192_int8.tflite) | Int8 | 192x192x3 | 33.7 % |
122
- | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_192/tiny_yolo_v2_192.h5) | Float | 192x192x3 | 34.5 % |
123
- | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_224/tiny_yolo_v2_224_int8.tflite) | Int8 | 224x224x3 | 37.3 % |
124
- | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_224/tiny_yolo_v2_224.h5) | Float | 224x224x3 | 38.4 % |
125
- | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_416/tiny_yolo_v2_416_int8.tflite) | Int8 | 416x416x3 | 50.7 % |
126
- | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_416/tiny_yolo_v2_416.h5) | Float | 416x416x3 | 51.5 % |
127
 
128
- \* EVAL_IOU = 0.4, NMS_THRESH = 0.5, SCORE_THRESH =0.001
129
 
130
  ### AP on ST Person dataset
 
131
 
132
  | Model | Format | Resolution | AP |
133
  |-------|--------|------------|----------------|
134
- | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_custom_dataset/st_person/tiny_yolo_v2_224/tiny_yolo_v2_224_int8.tflite) | Int8 | 224x224x3 | 34.0 % |
135
 
136
 
137
- \* EVAL_IOU = 0.4, NMS_THRESH = 0.5, SCORE_THRESH =0.001
138
 
139
  ## Retraining and Integration in a simple example:
140
 
@@ -167,5 +157,4 @@ Please refer to the stm32ai-modelzoo-services GitHub [here](https://github.com/S
167
  timestamp = {Mon, 13 Aug 2018 16:48:13 +0200},
168
  biburl = {https://dblp.org/rec/bib/journals/corr/LinMBHPRDZ14},
169
  bibsource = {dblp computer science bibliography, https://dblp.org}
170
- }
171
-
 
 
 
 
 
 
 
 
1
  # Tiny Yolo v2 quantized
2
 
3
  ## **Use case** : `Object detection`
 
57
  Measures are done with default STM32Cube.AI configuration with enabled input / output allocated option.
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
+ | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_224/tiny_yolo_v2_224_int8.tflite) | COCO-Person | Int8 | 224x224x3 | STM32N6 | 392 | 0 | 10794.4 | 10.2.0 | 2.2.0 |
63
+ | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_custom_dataset/st_person/tiny_yolo_v2_224/tiny_yolo_v2_224_int8.tflite) | ST-Person | Int8 | 224x224x3 | STM32N6 | 392 | 0 | 10794.4 | 10.2.0 | 2.2.0 |
64
+ | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_416/tiny_yolo_v2_416_int8.tflite) | COCO-Person | Int8 | 416x416x3 | STM32N6 | 1880.12 | 0 | 10818.4 | 10.2.0 | 2.2.0 |
 
65
 
66
  ### Reference **NPU** inference time based on COCO Person dataset (see Accuracy for details on dataset)
67
+ | Model | Dataset | Format | Resolution | Board | Execution Engine | Inference time (ms) | Inf / sec | STM32Cube.AI version | STEdgeAI Core version |
68
+ |------------------------------------------------------------------------------------------------------------------|-------------|----------|--------------|---------------|--------------------|-----------------------|-------------|------------------------|-------------------------|
69
+ | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_224/tiny_yolo_v2_224_int8.tflite) | COCO-Person | Int8 | 224x224x3 | STM32N6570-DK | NPU/MCU | 30.68 | 32.59 | 10.2.0 | 2.2.0 |
70
+ | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_custom_dataset/st_person/tiny_yolo_v2_224/tiny_yolo_v2_224_int8.tflite) | ST-Person | Int8 | 224x224x3 | STM32N6570-DK | NPU/MCU | 30.68 | 32.59 | 10.2.0 | 2.2.0 |
71
+ | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_416/tiny_yolo_v2_416_int8.tflite) | COCO-Person | Int8 | 416x416x3 | STM32N6570-DK | NPU/MCU | 50.81 | 19.68 | 10.2.0 | 2.2.0 |
 
72
 
73
  ### Reference **MCU** memory footprint based on COCO Person dataset (see Accuracy for details on dataset)
74
 
75
+ | Model | Format | Resolution | Series | Activation RAM | Runtime RAM | Weights Flash | Code Flash | Total RAM | Total Flash | STM32Cube.AI version |
76
+ |------------------------------------------------------------------------------------------------------------------|----------|--------------|----------|------------------|---------------|-----------------|--------------|-------------|---------------|------------------------|
77
+ | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_192/tiny_yolo_v2_192_int8.tflite) | Int8 | 192x192x3 | STM32H7 | 220.6 KiB | 7.98 KiB | 10775.98 KiB | 55.85 KiB | 228.58 KiB | 10831.83 KiB | 10.2.0 |
78
+ | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_224/tiny_yolo_v2_224_int8.tflite) | Int8 | 224x224x3 | STM32H7 | 249.35 | 7.98 KiB | 10775.98 | 55.24 | 257.33 | 10831.22 | 10.2.0 |
79
+ | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_416/tiny_yolo_v2_416_int8.tflite) | Int8 | 416x416x3 | STM32H7 | 1263.07 | 8.03 KiB | 10775.98 | 55.29 | 1271.10 | 10831.27 | 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
+ | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_192/tiny_yolo_v2_192_int8.tflite) | Int8 | 192x192x3 | STM32H747I-DISCO | 1 CPU | 400 MHz | 3006.3 ms | 10.2.0 |
87
+ | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_224/tiny_yolo_v2_224_int8.tflite) | Int8 | 224x224x3 | STM32H747I-DISCO | 1 CPU | 400 MHz | 2712.22 | 10.2.0 |
88
+ | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_416/tiny_yolo_v2_416_int8.tflite) | Int8 | 416x416x3 | STM32H747I-DISCO | 1 CPU | 400 MHz | 10441.33 | 10.2.0 |
 
89
 
90
  ### Reference **MPU** inference time based on COCO Person dataset (see Accuracy for details on dataset)
91
 
92
 
93
  | Model | Format | Resolution | Quantization | Board | Execution Engine | Frequency | Inference time (ms) | %NPU | %GPU | %CPU | X-LINUX-AI version | Framework |
94
  |--------------|--------|------------|---------------|-------------------|------------------|-----------|---------------------|-------|-------|------|--------------------|-----------------------|
95
+ | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_224/tiny_yolo_v2_224_int8.tflite) | Int8 | 224x224x3 | per-channel** | STM32MP257F-DK2 | NPU/GPU | 800 MHz | 137.51 ms | 3.83 | 96.17 |0 | v6.1.0 | OpenVX |
96
+ | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_416/tiny_yolo_v2_416_int8.tflite) | Int8 | 416x416x3 | per-channel** | STM32MP257F-DK2 | NPU/GPU | 800 MHz | 481.09 ms | 2.57 | 97.43 |0 | v6.1.0 | OpenVX |
97
+ | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_224/tiny_yolo_v2_224_int8.tflite) | Int8 | 224x224x3 | per-channel | STM32MP157F-DK2 | 2 CPU | 800 MHz | 417.84 ms | NA | NA |100 | v6.1.0 | TensorFlowLite 2.18.0 |
98
+ | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_416/tiny_yolo_v2_416_int8.tflite) | Int8 | 416x416x3 | per-channel | STM32MP157F-DK2 | 2 CPU | 800 MHz | 1302.07 ms | NA | NA |100 | v6.1.0 | TensorFlowLite 2.18.0 |
99
+ | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_224/tiny_yolo_v2_224_int8.tflite) | Int8 | 224x224x3 | per-channel | STM32MP135F-DK2 | 1 CPU | 1000 MHz | 623.35 ms | NA | NA |100 | v6.1.0 | TensorFlowLite 2.18.0 |
100
+ | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_416/tiny_yolo_v2_416_int8.tflite) | Int8 | 416x416x3 | per-channel | STM32MP135F-DK2 | 1 CPU | 1000 MHz | 2101.3 ms | NA | NA |100 | v6.1.0 | TensorFlowLite 2.18.0 |
101
 
102
  ** **To get the most out of MP25 NPU hardware acceleration, please use per-tensor quantization**
103
 
 
107
 
108
  | Model | Format | Resolution | AP |
109
  |-------|--------|------------|----------------|
110
+ | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_192/tiny_yolo_v2_192_int8.tflite) | Int8 | 192x192x3 | 26.2 % |
111
+ | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_192/tiny_yolo_v2_192.h5) | Float | 192x192x3 | 27.5 % |
112
+ | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_224/tiny_yolo_v2_224_int8.tflite) | Int8 | 224x224x3 | 28.8 % |
113
+ | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_224/tiny_yolo_v2_224.h5) | Float | 224x224x3 | 30.9 % |
114
+ | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_416/tiny_yolo_v2_416_int8.tflite) | Int8 | 416x416x3 | 41.4 % |
115
+ | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_public_dataset/coco_2017_person/tiny_yolo_v2_416/tiny_yolo_v2_416.h5) | Float | 416x416x3 | 43.4 % |
116
 
117
+ \* EVAL_IOU = 0.5, NMS_THRESH = 0.5, SCORE_THRESH = 0.001, MAX_DETECTIONS = 100
118
 
119
  ### AP on ST Person dataset
120
+ This model has been trained using a STMicroelectronics proprietary dataset which is not provided as part of the STM32 model zoo. The ST person dataset has been built by aggregating several public datasets and by applying data augmentation on these public datasets. If users wish to retrain this model it has to be done using another dataset selected by the user.
121
 
122
  | Model | Format | Resolution | AP |
123
  |-------|--------|------------|----------------|
124
+ | [tiny_yolo_v2](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/object_detection/tiny_yolo_v2/ST_pretrainedmodel_custom_dataset/st_person/tiny_yolo_v2_224/tiny_yolo_v2_224_int8.tflite) | Int8 | 224x224x3 | 28.5 % |
125
 
126
 
127
+ \* EVAL_IOU = 0.5, NMS_THRESH = 0.5, SCORE_THRESH = 0.001, MAX_DETECTIONS = 100
128
 
129
  ## Retraining and Integration in a simple example:
130
 
 
157
  timestamp = {Mon, 13 Aug 2018 16:48:13 +0200},
158
  biburl = {https://dblp.org/rec/bib/journals/corr/LinMBHPRDZ14},
159
  bibsource = {dblp computer science bibliography, https://dblp.org}
160
+ }