| --- |
| library_name: pytorch |
| --- |
| |
|  |
|
|
| MobileNetV2 introduces an efficient convolutional architecture based on inverted residual blocks and linear bottlenecks, enabling high accuracy at very low computational cost for mobile and embedded vision applications. |
|
|
| Original paper: [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://arxiv.org/abs/1801.04381) |
|
|
| # MobileNetV2 |
|
|
| This model uses the MobileNetV2 architecture with width multiplier = 1.0, providing a balanced trade-off between accuracy and efficiency. It is optimized for low-latency, low-power inference and is commonly used for on-device image classification as well as a backbone for mobile-friendly detection and segmentation models. |
|
|
| Model Configuration: |
| - Reference implementation: [MobileNetV2](https://pytorch.org/vision/stable/models/generated/torchvision.models.mobilenet_v2.html) |
| - Original Weight: [MobileNet_V2_Weights.IMAGENET1K_V2](https://download.pytorch.org/models/mobilenet_v2-7ebf99e0.pth) |
| - Resolution: 3x224x224 |
| - Support Cooper version: |
| - Cooper SDK: [2.5.4] |
| - Cooper Foundry: [2.3] |
|
|
| | Model | Device | compression | Model Link | |
| | :-----: | :-----: | :-----: | ------- | |
| | MobileNetV2 | N1-655 | Amba_optimized | [Model_Link](https://huggingface.co/Ambarella/MobileNetV2/blob/main/n1-655_mobilenet_v2_amba_optimized.bin) | |
| | MobileNetV2 | N1-655 | Activation_fp16 | [Model_Link](https://huggingface.co/Ambarella/MobileNetV2/blob/main/n1-655_mobilenet_v2_act16.bin) | |
| | MobileNetV2 | CV7 | Amba_optimized | [Model_Link](https://huggingface.co/Ambarella/MobileNetV2/blob/main/cv7_mobilenet_v2_amba_optimized.bin) | |
| | MobileNetV2 | CV7 | Activation_fp16 | [Model_Link](https://huggingface.co/Ambarella/MobileNetV2/blob/main/cv7_mobilenet_v2_act16.bin) | |
| | MobileNetV2 | CV72 | Amba_optimized | [Model_Link](https://huggingface.co/Ambarella/MobileNetV2/blob/main/cv72_mobilenet_v2_amba_optimized.bin) | |
| | MobileNetV2 | CV72 | Activation_fp16 | [Model_Link](https://huggingface.co/Ambarella/MobileNetV2/blob/main/cv72_mobilenet_v2_act16.bin) | |
| | MobileNetV2 | CV75 | Amba_optimized | [Model_Link](https://huggingface.co/Ambarella/MobileNetV2/blob/main/cv75_mobilenet_v2_amba_optimized.bin) | |
| | MobileNetV2 | CV75 | Activation_fp16 | [Model_Link](https://huggingface.co/Ambarella/MobileNetV2/blob/main/cv75_mobilenet_v2_act16.bin) | |
|
|
