Hugging Face's logo

STMicroelectronics
/
resnetv1

Image Classification
Model card Files Community
FBAGSTM commited on
Commit
df33c02
·
verified ·
1 Parent(s): 3f91535

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +27 -27
README.md CHANGED
@@ -2,7 +2,7 @@
2
  license: other
3
  license_name: sla0044
4
  license_link: >-
5
- https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/LICENSE.md
6
  pipeline_tag: image-classification
7
  ---
8
  # ResNet v1
@@ -77,31 +77,31 @@ For an image resolution of NxM and P classes
77
 
78
  | Model | Format | Resolution | Series | Activation RAM | Runtime RAM | Weights Flash | Code Flash | Total RAM | Total Flash | STM32Cube.AI version |
79
  |---------------------------------------------------------------------------------------------------------------------------------------|--------|-------------|---------|----------------|-------------|---------------|------------|-----------|-------------|-----------------------|
80
- | [ResNet v1 8 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/resnet_v1_8_32_tfs/resnet_v1_8_32_tfs_int8.tflite) | Int8 | 32x32x3 | STM32H7 | 62.51 KiB | 7.21 KiB | 76.9 KiB | 56.45 KiB | 69.72 KiB | 133.35 KiB | 10.0.0 |
81
- | [ST ResNet 8 Hybrid v1 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/st_resnet_8_hybrid_v1_32_tfs/st_resnet_8_hybrid_v1_32_tfs.h5) | Hybrid | 32x32x3 | STM32H7 | 77.84 KiB | 18.38 KiB | 85.79 KiB | 61.75 KiB | 96.22 KiB | 147.54 KiB | 10.0.0 |
82
- | [ST ResNet 8 Hybrid v2 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/st_resnet_8_hybrid_v2_32_tfs/st_resnet_8_hybrid_v2_32_tfs.h5) | Hybrid | 32x32x3 | STM32H7 | 78.99 KiB | 18.38 KiB | 66.28 KiB | 60.99 KiB | 97.37 KiB | 127.27 KiB | 10.0.0 |
83
 
84
  ### Reference **MCU** inference time based on Cifar 10 dataset (see Accuracy for details on dataset)
85
 
86
  | Model | Format | Resolution | Board | Execution Engine | Frequency | Inference time (ms) | STM32Cube.AI version |
87
  |----------------------------------|--------|-------------|------------------|------------------|--------------|---------------------|-----------------------|
88
- | [ResNet v1 8 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/resnet_v1_8_32_tfs/resnet_v1_8_32_tfs_int8.tflite) | Int8 | 32x32x3 | STM32H747I-DISCO | 1 CPU | 400 MHz | 28.67 ms | 10.0.0 |
89
- | [ST ResNet 8 Hybrid v1 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/st_resnet_8_hybrid_v1_32_tfs/st_resnet_8_hybrid_v1_32_tfs.h5) | Hybrid | 32x32x3 | STM32H747I-DISCO | 1 CPU | 400 MHz | 28.93 ms | 10.0.0 |
90
- | [ST ResNet 8 Hybrid v2 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/st_resnet_8_hybrid_v2_32_tfs/st_resnet_8_hybrid_v2_32_tfs.h5) | Hybrid | 32x32x3 | STM32H747I-DISCO | 1 CPU | 400 MHz | 25.2 ms | 10.0.0 |
91
 
92
 
93
  ### Reference **MPU** inference time based on Flowers dataset (see Accuracy for details on dataset)
94
  | Model | Format | Resolution | Quantization | Board | Execution Engine | Frequency | Inference time (ms) | %NPU | %GPU | %CPU | X-LINUX-AI version | Framework |
95
  |---------------------------------------------------------------------------------------------------------------------------------------|----------|------------|---------------|-------------------|------------------|-----------|---------------------|-------|-------|------|--------------------|-----------------------|
96
- | [ResNet v1 8 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/resnet_v1_8_32_tfs/resnet_v1_8_32_tfs_int8.tflite) | Int8 | 32x32x3 | per-channel** | STM32MP257F-DK2 | NPU/GPU | 800 MHz | 2.02 ms | 12.26 | 87.74 | 0 | v5.1.0 | OpenVX |
97
- | [ST ResNet 8 Hybrid v1 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/st_resnet_8_hybrid_v1_32_tfs/st_resnet_8_hybrid_v1_32_tfs.h5) | Hybrid | 32x32x3 | per-channel** | STM32MP257F-DK2 | NPU/GPU | 800 MHz | TBD ms | 0 | 0 | 0 | v5.1.0 | OpenVX |
98
- | [ST ResNet 8 Hybrid v2 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/st_resnet_8_hybrid_v2_32_tfs/st_resnet_8_hybrid_v2_32_tfs.h5) | Hybrid | 32x32x3 | per-channel** | STM32MP257F-DK2 | NPU/GPU | 800 MHz | TBD ms | 0 | 0 | 0 | v5.1.0 | OpenVX |
99
- | [ResNet v1 8 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/resnet_v1_8_32_tfs/resnet_v1_8_32_tfs_int8.tflite) | Int8 | 32x32x3 | per-channel | STM32MP157F-DK2 | 2 CPU | 800 MHz | 6.50 ms | NA | NA | 100 | v5.1.0 | TensorFlowLite 2.11.0 |
100
- | [ST ResNet 8 Hybrid v1 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/st_resnet_8_hybrid_v1_32_tfs/st_resnet_8_hybrid_v1_32_tfs.h5) | Hybrid | 32x32x3 | per-channel | STM32MP157F-DK2 | 2 CPU | 800 MHz | TBD ms | NA | NA | 100 | v5.1.0 | TensorFlowLite 2.11.0 |
101
- | [ST ResNet 8 Hybrid v2 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/st_resnet_8_hybrid_v2_32_tfs/st_resnet_8_hybrid_v2_32_tfs.h5) | Hybrid | 32x32x3 | per-channel | STM32MP157F-DK2 | 2 CPU | 800 MHz | TBD ms | NA | NA | 100 | v5.1.0 | TensorFlowLite 2.11.0 |
102
- | [ResNet v1 8 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/resnet_v1_8_32_tfs/resnet_v1_8_32_tfs_int8.tflite) | Int8 | 32x32x3 | per-channel | STM32MP135F-DK2 | 1 CPU | 1000 MHz | 10.77 ms | NA | NA | 100 | v5.1.0 | TensorFlowLite 2.11.0 |
103
- | [ST ResNet 8 Hybrid v1 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/st_resnet_8_hybrid_v1_32_tfs/st_resnet_8_hybrid_v1_32_tfs.h5) | Hybrid | 32x32x3 | per-channel | STM32MP135F-DK2 | 1 CPU | 1000 MHz | TBD ms | NA | NA | 100 | v5.1.0 | TensorFlowLite 2.11.0 |
104
- | [ST ResNet 8 Hybrid v2 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/st_resnet_8_hybrid_v2_32_tfs/st_resnet_8_hybrid_v2_32_tfs.h5) | Hybrid | 32x32x3 | per-channel | STM32MP135F-DK2 | 1 CPU | 1000 MHz | TBD ms | NA | NA | 100 | v5.1.0 | TensorFlowLite 2.11.0 |
105
 
106
  ** **To get the most out of MP25 NPU hardware acceleration, please use per-tensor quantization**
107
 
@@ -109,22 +109,22 @@ For an image resolution of NxM and P classes
109
 
110
  | Model | Format | Resolution | Series | Activation RAM | Runtime RAM | Weights Flash | Code Flash | Total RAM | Total Flash |
111
  |----------------------------------------------------------------------------------------------------------------------|--------|-------------|---------|----------------|-------------|---------------|------------|-------------|-------------|
112
- | [ResNet v1 32 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar100/resnet_v1_32_32_tfs/resnet_v1_32_32_tfs_int8.tflite) | Int8 | 32x32x3 | STM32H7 | 45.41 KiB | 24.98 KiB | 464.38 KiB | 78.65 KiB | 70.39 KiB | 543.03 KiB |
113
 
114
 
115
  ### Reference **MCU** inference time based on Cifar 100 dataset (see Accuracy for details on dataset)
116
 
117
  | Model | Format | Resolution | Board | Execution Engine | Frequency | Inference time (ms) |
118
  |----------------------------------------------------------------------------------------------------------------------|--------|------------|------------------|------------------|--------------|---------------------|
119
- | [ResNet v1 32 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar100/resnet_v1_32_32_tfs/resnet_v1_32_32_tfs_int8.tflite) | Int8 | 32x32x3 | STM32H747I-DISCO | 1 CPU | 400 MHz | 177.7 ms |
120
 
121
 
122
  ### Reference **MPU** inference time based on Flowers dataset (see Accuracy for details on dataset)
123
  | Model | Format | Resolution | Quantization | Board | Execution Engine | Frequency | Inference time (ms) | %NPU | %GPU | %CPU | X-LINUX-AI version | Framework |
124
  |---------------------------------------------------------------------------------------------------------------------|----------|------------|---------------|-------------------|------------------|-----------|---------------------|-------|-------|------|--------------------|-----------------------|
125
- |[ResNet v1 32 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar100/resnet_v1_32_32_tfs/resnet_v1_32_32_tfs_int8.tflite) | Int8 | 32x32x3 | per-channel | STM32MP257F-DK2 | NPU/GPU | 800 MHz | 9.160 ms | 14.75 | 85.25 | 0 | v5.1.0 | OpenVX |
126
- |[ResNet v1 32 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar100/resnet_v1_32_32_tfs/resnet_v1_32_32_tfs_int8.tflite) | Int8 | 32x32x3 | per-channel | STM32MP157F-DK2 | 2 CPU | 800 MHz | 34.78 ms | NA | NA | 100 | v5.1.0 | TensorFlowLite 2.11.0 |
127
- |[ResNet v1 32 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar100/resnet_v1_32_32_tfs/resnet_v1_32_32_tfs_int8.tflite) | Int8 | 32x32x3 | per-channel | STM32MP135F-DK2 | 1 CPU | 1000 MHz | 55.32 ms | NA | NA | 100 | v5.1.0 | TensorFlowLite 2.11.0 |
128
 
129
 
130
  ### Accuracy with Cifar10 dataset
@@ -135,10 +135,10 @@ images: 60 000
135
 
136
  | Model | Format | Resolution | Top 1 Accuracy |
137
  |------------------------------------------------------------------------------------------------------------------|----------|-------------|----------------|
138
- | [ResNet v1 8 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/resnet_v1_8_32_tfs/resnet_v1_8_32_tfs.h5) | Float | 32x32x3 | 87.01 % |
139
- | [ResNet v1 8 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/resnet_v1_8_32_tfs/resnet_v1_8_32_tfs_int8.tflite) | Int8 | 32x32x3 | 85.59 % |
140
- | [ST ResNet 8 Hybrid v1 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/st_resnet_8_hybrid_v1_32_tfs/st_resnet_8_hybrid_v1_32_tfs.h5) | Hybrid | 32x32x3 | 86 % |
141
- | [ST ResNet 8 Hybrid v2 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/st_resnet_8_hybrid_v2_32_tfs/st_resnet_8_hybrid_v2_32_tfs.h5) | Hybrid | 32x32x3 | 84.85 % |
142
 
143
 
144
  ### Accuracy with Cifar100 dataset
@@ -149,8 +149,8 @@ Number of images: 600 000
149
 
150
  | Model | Format | Resolution | Top 1 Accuracy |
151
  |----------------------------------------------------------------------------------------------------------------------|---------|------------|----------------|
152
- | [ResNet v1 32 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar100/resnet_v1_32_32_tfs/resnet_v1_32_32_tfs.h5) | Float | 32x32x3 | 67.75 % |
153
- | [ResNet v1 32 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar100/resnet_v1_32_32_tfs/resnet_v1_32_32_tfs_int8.tflite) | Int8 | 32x32x3 | 66.58 % |
154
 
155
  ## Retraining and Integration in a simple example:
156
 
 
2
  license: other
3
  license_name: sla0044
4
  license_link: >-
5
+ https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/LICENSE.md
6
  pipeline_tag: image-classification
7
  ---
8
  # ResNet v1
 
77
 
78
  | Model | Format | Resolution | Series | Activation RAM | Runtime RAM | Weights Flash | Code Flash | Total RAM | Total Flash | STM32Cube.AI version |
79
  |---------------------------------------------------------------------------------------------------------------------------------------|--------|-------------|---------|----------------|-------------|---------------|------------|-----------|-------------|-----------------------|
80
+ | [ResNet v1 8 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/resnet_v1_8_32_tfs/resnet_v1_8_32_tfs_int8.tflite) | Int8 | 32x32x3 | STM32H7 | 62.51 KiB | 7.21 KiB | 76.9 KiB | 56.45 KiB | 69.72 KiB | 133.35 KiB | 10.0.0 |
81
+ | [ST ResNet 8 Hybrid v1 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/st_resnet_8_hybrid_v1_32_tfs/st_resnet_8_hybrid_v1_32_tfs.h5) | Hybrid | 32x32x3 | STM32H7 | 77.84 KiB | 18.38 KiB | 85.79 KiB | 61.75 KiB | 96.22 KiB | 147.54 KiB | 10.0.0 |
82
+ | [ST ResNet 8 Hybrid v2 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/st_resnet_8_hybrid_v2_32_tfs/st_resnet_8_hybrid_v2_32_tfs.h5) | Hybrid | 32x32x3 | STM32H7 | 78.99 KiB | 18.38 KiB | 66.28 KiB | 60.99 KiB | 97.37 KiB | 127.27 KiB | 10.0.0 |
83
 
84
  ### Reference **MCU** inference time based on Cifar 10 dataset (see Accuracy for details on dataset)
85
 
86
  | Model | Format | Resolution | Board | Execution Engine | Frequency | Inference time (ms) | STM32Cube.AI version |
87
  |----------------------------------|--------|-------------|------------------|------------------|--------------|---------------------|-----------------------|
88
+ | [ResNet v1 8 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/resnet_v1_8_32_tfs/resnet_v1_8_32_tfs_int8.tflite) | Int8 | 32x32x3 | STM32H747I-DISCO | 1 CPU | 400 MHz | 28.67 ms | 10.0.0 |
89
+ | [ST ResNet 8 Hybrid v1 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/st_resnet_8_hybrid_v1_32_tfs/st_resnet_8_hybrid_v1_32_tfs.h5) | Hybrid | 32x32x3 | STM32H747I-DISCO | 1 CPU | 400 MHz | 28.93 ms | 10.0.0 |
90
+ | [ST ResNet 8 Hybrid v2 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/st_resnet_8_hybrid_v2_32_tfs/st_resnet_8_hybrid_v2_32_tfs.h5) | Hybrid | 32x32x3 | STM32H747I-DISCO | 1 CPU | 400 MHz | 25.2 ms | 10.0.0 |
91
 
92
 
93
  ### Reference **MPU** inference time based on Flowers dataset (see Accuracy for details on dataset)
94
  | Model | Format | Resolution | Quantization | Board | Execution Engine | Frequency | Inference time (ms) | %NPU | %GPU | %CPU | X-LINUX-AI version | Framework |
95
  |---------------------------------------------------------------------------------------------------------------------------------------|----------|------------|---------------|-------------------|------------------|-----------|---------------------|-------|-------|------|--------------------|-----------------------|
96
+ | [ResNet v1 8 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/resnet_v1_8_32_tfs/resnet_v1_8_32_tfs_int8.tflite) | Int8 | 32x32x3 | per-channel** | STM32MP257F-DK2 | NPU/GPU | 800 MHz | 2.02 ms | 12.26 | 87.74 | 0 | v5.1.0 | OpenVX |
97
+ | [ST ResNet 8 Hybrid v1 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/st_resnet_8_hybrid_v1_32_tfs/st_resnet_8_hybrid_v1_32_tfs.h5) | Hybrid | 32x32x3 | per-channel** | STM32MP257F-DK2 | NPU/GPU | 800 MHz | TBD ms | 0 | 0 | 0 | v5.1.0 | OpenVX |
98
+ | [ST ResNet 8 Hybrid v2 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/st_resnet_8_hybrid_v2_32_tfs/st_resnet_8_hybrid_v2_32_tfs.h5) | Hybrid | 32x32x3 | per-channel** | STM32MP257F-DK2 | NPU/GPU | 800 MHz | TBD ms | 0 | 0 | 0 | v5.1.0 | OpenVX |
99
+ | [ResNet v1 8 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/resnet_v1_8_32_tfs/resnet_v1_8_32_tfs_int8.tflite) | Int8 | 32x32x3 | per-channel | STM32MP157F-DK2 | 2 CPU | 800 MHz | 6.50 ms | NA | NA | 100 | v5.1.0 | TensorFlowLite 2.11.0 |
100
+ | [ST ResNet 8 Hybrid v1 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/st_resnet_8_hybrid_v1_32_tfs/st_resnet_8_hybrid_v1_32_tfs.h5) | Hybrid | 32x32x3 | per-channel | STM32MP157F-DK2 | 2 CPU | 800 MHz | TBD ms | NA | NA | 100 | v5.1.0 | TensorFlowLite 2.11.0 |
101
+ | [ST ResNet 8 Hybrid v2 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/st_resnet_8_hybrid_v2_32_tfs/st_resnet_8_hybrid_v2_32_tfs.h5) | Hybrid | 32x32x3 | per-channel | STM32MP157F-DK2 | 2 CPU | 800 MHz | TBD ms | NA | NA | 100 | v5.1.0 | TensorFlowLite 2.11.0 |
102
+ | [ResNet v1 8 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/resnet_v1_8_32_tfs/resnet_v1_8_32_tfs_int8.tflite) | Int8 | 32x32x3 | per-channel | STM32MP135F-DK2 | 1 CPU | 1000 MHz | 10.77 ms | NA | NA | 100 | v5.1.0 | TensorFlowLite 2.11.0 |
103
+ | [ST ResNet 8 Hybrid v1 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/st_resnet_8_hybrid_v1_32_tfs/st_resnet_8_hybrid_v1_32_tfs.h5) | Hybrid | 32x32x3 | per-channel | STM32MP135F-DK2 | 1 CPU | 1000 MHz | TBD ms | NA | NA | 100 | v5.1.0 | TensorFlowLite 2.11.0 |
104
+ | [ST ResNet 8 Hybrid v2 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/st_resnet_8_hybrid_v2_32_tfs/st_resnet_8_hybrid_v2_32_tfs.h5) | Hybrid | 32x32x3 | per-channel | STM32MP135F-DK2 | 1 CPU | 1000 MHz | TBD ms | NA | NA | 100 | v5.1.0 | TensorFlowLite 2.11.0 |
105
 
106
  ** **To get the most out of MP25 NPU hardware acceleration, please use per-tensor quantization**
107
 
 
109
 
110
  | Model | Format | Resolution | Series | Activation RAM | Runtime RAM | Weights Flash | Code Flash | Total RAM | Total Flash |
111
  |----------------------------------------------------------------------------------------------------------------------|--------|-------------|---------|----------------|-------------|---------------|------------|-------------|-------------|
112
+ | [ResNet v1 32 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar100/resnet_v1_32_32_tfs/resnet_v1_32_32_tfs_int8.tflite) | Int8 | 32x32x3 | STM32H7 | 45.41 KiB | 24.98 KiB | 464.38 KiB | 78.65 KiB | 70.39 KiB | 543.03 KiB |
113
 
114
 
115
  ### Reference **MCU** inference time based on Cifar 100 dataset (see Accuracy for details on dataset)
116
 
117
  | Model | Format | Resolution | Board | Execution Engine | Frequency | Inference time (ms) |
118
  |----------------------------------------------------------------------------------------------------------------------|--------|------------|------------------|------------------|--------------|---------------------|
119
+ | [ResNet v1 32 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar100/resnet_v1_32_32_tfs/resnet_v1_32_32_tfs_int8.tflite) | Int8 | 32x32x3 | STM32H747I-DISCO | 1 CPU | 400 MHz | 177.7 ms |
120
 
121
 
122
  ### Reference **MPU** inference time based on Flowers dataset (see Accuracy for details on dataset)
123
  | Model | Format | Resolution | Quantization | Board | Execution Engine | Frequency | Inference time (ms) | %NPU | %GPU | %CPU | X-LINUX-AI version | Framework |
124
  |---------------------------------------------------------------------------------------------------------------------|----------|------------|---------------|-------------------|------------------|-----------|---------------------|-------|-------|------|--------------------|-----------------------|
125
+ |[ResNet v1 32 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar100/resnet_v1_32_32_tfs/resnet_v1_32_32_tfs_int8.tflite) | Int8 | 32x32x3 | per-channel | STM32MP257F-DK2 | NPU/GPU | 800 MHz | 9.160 ms | 14.75 | 85.25 | 0 | v5.1.0 | OpenVX |
126
+ |[ResNet v1 32 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar100/resnet_v1_32_32_tfs/resnet_v1_32_32_tfs_int8.tflite) | Int8 | 32x32x3 | per-channel | STM32MP157F-DK2 | 2 CPU | 800 MHz | 34.78 ms | NA | NA | 100 | v5.1.0 | TensorFlowLite 2.11.0 |
127
+ |[ResNet v1 32 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar100/resnet_v1_32_32_tfs/resnet_v1_32_32_tfs_int8.tflite) | Int8 | 32x32x3 | per-channel | STM32MP135F-DK2 | 1 CPU | 1000 MHz | 55.32 ms | NA | NA | 100 | v5.1.0 | TensorFlowLite 2.11.0 |
128
 
129
 
130
  ### Accuracy with Cifar10 dataset
 
135
 
136
  | Model | Format | Resolution | Top 1 Accuracy |
137
  |------------------------------------------------------------------------------------------------------------------|----------|-------------|----------------|
138
+ | [ResNet v1 8 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/resnet_v1_8_32_tfs/resnet_v1_8_32_tfs.h5) | Float | 32x32x3 | 87.01 % |
139
+ | [ResNet v1 8 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/resnet_v1_8_32_tfs/resnet_v1_8_32_tfs_int8.tflite) | Int8 | 32x32x3 | 85.59 % |
140
+ | [ST ResNet 8 Hybrid v1 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/st_resnet_8_hybrid_v1_32_tfs/st_resnet_8_hybrid_v1_32_tfs.h5) | Hybrid | 32x32x3 | 86 % |
141
+ | [ST ResNet 8 Hybrid v2 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar10/st_resnet_8_hybrid_v2_32_tfs/st_resnet_8_hybrid_v2_32_tfs.h5) | Hybrid | 32x32x3 | 84.85 % |
142
 
143
 
144
  ### Accuracy with Cifar100 dataset
 
149
 
150
  | Model | Format | Resolution | Top 1 Accuracy |
151
  |----------------------------------------------------------------------------------------------------------------------|---------|------------|----------------|
152
+ | [ResNet v1 32 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar100/resnet_v1_32_32_tfs/resnet_v1_32_32_tfs.h5) | Float | 32x32x3 | 67.75 % |
153
+ | [ResNet v1 32 tfs](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/image_classification/resnetv1/ST_pretrainedmodel_public_dataset/cifar100/resnet_v1_32_32_tfs/resnet_v1_32_32_tfs_int8.tflite) | Int8 | 32x32x3 | 66.58 % |
154
 
155
  ## Retraining and Integration in a simple example:
156