| --- |
| license: other |
| license_name: aplux-model-farm |
| license_link: https://huggingface.co/APLUX-Agora/MobileNet-v2/blob/main/LICENSE_MODEL_FARM.pdf |
| pipeline_tag: image-classification |
| tags: [Agora, QNN, AIoT, Qualcomm] |
| --- |
| |
| # MobileNetV2 model resources |
|
|
| 经典轻量分类网络，ImageNet 1000 类。 |
|
|
| Board builds that [Agora](https://mega.aidlux.com) runs and measures on real Qualcomm boards. Try it online, without a board: https://mega.aidlux.com/models/mobilenet-v2 |
|
|
| | SoC · board | Precisions | Measured on Agora (default precision) | |
| | --- | --- | --- | |
| | QCS6490 · 犀牛派 A1 (Rhino Pi A1) | W8A16 | 1.4 ms | |
| | QCS8550 · 犀牛派 X1 (Rhino Pi X1) | FP16, W8A16 | 0.7 ms | |
|
|
| Task: 分类. Inputs: image (image). Outputs: label (label). |
|
|
| ## Download |
|
|
| ```bash |
| export AGORA_WORKSPACE="$HOME/my-mobilenet-v2" |
| export AGORA_SOC='QCS8550' |
| hf download APLUX-Agora/MobileNet-v2 \ |
| --include "targets/$AGORA_SOC/*" --local-dir "$AGORA_WORKSPACE/resources" |
| ``` |
|
|
| Each `targets/<SoC>/` holds `model.json` (default precision and variant paths) and one directory per precision. Context binaries are named `model.bin`; multi-file packages are kept as published by Model Farm. |
|
|
| Pre- and post-processing, the runner and an exported project: open the model on Agora and choose “部署指南”, or export any workflow that uses it. |
|
|
| ## Licence and provenance |
|
|
| Source model licence: see the original model's terms. |
| Converted, deployable resources: APLUX Model Farm License (LICENSE_MODEL_FARM.pdf). See NOTICE.md and SHA256SUMS. |
|
|
