MNN/pymnn/test
zhaode.wzd 05a1623773 [Compile:Bugfix] Bugfix of action and compile. 2023-09-21 21:30:09 +08:00
..
playground [MNN:Sync] Sync internal github 2021-07-29 11:47:13 +08:00
scripts [MNN:Sync] Sync internal github 2021-07-29 11:47:13 +08:00
README.md [MNN:Sync] Sync internal gitlab 2022-06-24 18:30:05 +08:00
benchmark.py Sync Internal 2.0.4 2022-08-12 10:30:48 +08:00
model_test.py [MNN:Sync] Sync 2.4.2 2023-04-11 11:12:00 +08:00
train_test.sh [MNN:Sync] Sync internal gitlab 2022-06-24 18:30:05 +08:00
unit_test.py [Compile:Bugfix] Bugfix of action and compile. 2023-09-21 21:30:09 +08:00

README.md

Pymnn Test Cases

1. Unit Test

python3 unit_test.py

2. Model Test

python3 model_test.py ~/AliNNModel

3. Train Test

./train_test.sh

4. Quant Test

python3 ../examples/MNNQuant/test_mnn_offline_quant.py \
        --mnn_model your_model.mnn \
        --quant_imgs <path_to_imgs> \
        --quant_model ./quant_model.mnn

5. Benchmark MNN.numpy

pip install prettytable
python3 benchmark.py

6. Playgroud Test (just internal usage)

# 拷贝AliNNModel所有模型和测试数据到MNN工作台工程下
python scripts/pullTestModel.py --alinnmodel_path ../../../AliNNModel --playground_path playground/playground
# 拷贝AliNNModel指定模型mobilenet, Ranfa和测试数据到MNN工作台工程下
python scripts/pullTestModel.py --alinnmodel_path ../../../AliNNModel --playground_path playground/playground --models mobilenet Ranfa