MobileNetV2: Inverted Residuals and Linear Bottlenecks
Paper • 1801.04381 • Published • 1
Configuration Parsing Warning:Config file config.json cannot be fetched (too big)
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
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
- Original Weight: MobileNet_V2_Weights.IMAGENET1K_V2
- Dataset: ImageNet
- 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 |
| MobileNetV2 | N1-655 | Activation_fp16 | Model_Link |
| MobileNetV2 | X7 | Amba_optimized | Model_Link |
| MobileNetV2 | X7 | Activation_fp16 | Model_Link |
| MobileNetV2 | CV7 | Amba_optimized | Model_Link |
| MobileNetV2 | CV7 | Activation_fp16 | Model_Link |
| MobileNetV2 | CV72 | Amba_optimized | Model_Link |
| MobileNetV2 | CV72 | Activation_fp16 | Model_Link |
| MobileNetV2 | CV75 | Amba_optimized | Model_Link |
| MobileNetV2 | CV75 | Activation_fp16 | Model_Link |
- Downloads last month
- 20
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support