Skip to content

[PyTorch] Added support of .pt files and different modules

Valentina Kustikova requested to merge github/fork/a-sidorova/feature/pytorch/pt into master

Created by: a-sidorova

Добавлена поддержка кастомных моделей и моделей из других модулей.

(.pytorch) a-sidorova@asidorova-desktop:~/university/openvino-dl-benchmark/src/inference$ python3 inference_pytorch.py -mn resnest50 -mm resnest-50.resnest -w /home/a-sidorova/university/openvino-dl-benchmark/src/inference/resnest-50/resnest50-528c19ca.pth -t classification -i ../../results/validation/images/ILSVRC2012_val_00000023.JPEG -is 1 3 224 224 --norm --mean 0.485 0.456 0.406 --std 0.229 0.224 0.225 --model_type baseline
[ INFO ] Loading model from module resnest-50.resnest
[ INFO ] Loading model with weights from file /home/a-sidorova/university/openvino-dl-benchmark/src/inference/resnest-50/resnest50-528c19ca.pth
[ INFO ] Get device for inference
[ INFO ] Inference will be executed on CPU
[ INFO ] Inference will be executed on baseline model
[ INFO ] Shape for input layer data: [1, 3, 224, 224]
[ INFO ] Preparing input data ['../../results/validation/images/ILSVRC2012_val_00000023.JPEG']
[ INFO ] Starting inference (1 iterations) on CPU
[ INFO ] Computing performance metrics
[ INFO ] Converting output tensor to print results
[ INFO ] Inference results
[ INFO ] Top 5 results:
[ INFO ] Result for image 1
[ INFO ]        0.8672453 Granny Smith
[ INFO ]        0.0019027 pomegranate
[ INFO ]        0.0018386 orange
[ INFO ]        0.0018165 lemon
[ INFO ]        0.0016820 piggy bank, penny bank
[ INFO ] Performance results
[ INFO ] Average time of single pass : 3.452
[ INFO ] FPS : 0.290
[ INFO ] Latency : 3.452

Merge request reports