Skip to content

Fixed default requests arg

Evgeni Vasilev requested to merge github/fork/a-sidorova/fix/inference/sync_requests into master

Created by: a-sidorova

Возвращение устанавливать количество запросов по умолчанию

До изменений:

(.ov2) C:\Users\Alexandra Sidorova\Documents\openvino>python .\openvino-dl-benchmark\src\inference\inference_async_mode.py -m "C:\Users\Alexandra Sidorova\Documents\openvino\models\public\mixnet-l\FP32\mixnet-l.xml" -w "C:\Users\Alexandra Sidorova\Documents\openvino\models\public\mixnet-l\FP32\mixnet-l.bin" -i ".\imgs\apple.png"
[ INFO ] Inference Engine initialization
[ INFO ] Loading model files:
         C:\Users\Alexandra Sidorova\Documents\openvino\models\public\mixnet-l\FP32\mixnet-l.xml
         C:\Users\Alexandra Sidorova\Documents\openvino\models\public\mixnet-l\FP32\mixnet-l.bin
[ INFO ] Shape for input layer IteratorGetNext:0: 1x224x224x3
[ INFO ] Prepare input data
[ INFO ] Create executable network
[ INFO ] Runtime parameters
[ INFO ] DEVICE: CPU
[ INFO ]   AVAILABLE_DEVICES  , ['']
[ INFO ]   RANGE_FOR_ASYNC_INFER_REQUESTS  , (1, 1, 1)
[ INFO ]   RANGE_FOR_STREAMS  , (1, 12)
[ INFO ]   FULL_DEVICE_NAME  , Intel(R) Core(TM) i7-9750H CPU @ 2.60GHz
[ INFO ]   OPTIMIZATION_CAPABILITIES  , ['FP32', 'FP16', 'INT8', 'BIN', 'EXPORT_IMPORT']
[ INFO ]   CACHE_DIR  ,
[ INFO ]   NUM_STREAMS  , 4
[ INFO ]   INFERENCE_NUM_THREADS  , 0
[ INFO ]   PERF_COUNT  , False
[ INFO ]   PERFORMANCE_HINT_NUM_REQUESTS  , 0
[ INFO ] Starting inference (1 iterations) with None requests on CPU
ERROR! : __init__(): incompatible constructor arguments. The following argument types are supported:
    1. openvino.pyopenvino.AsyncInferQueue(model: openvino.pyopenvino.CompiledModel, jobs: int = 0)
Invoked with: <CompiledModel:
inputs[
<ConstOutput: names[IteratorGetNext:0] shape{1,224,224,3} type: f32>
]
outputs[
<ConstOutput: names[logits, logits:0, mixnet-l/mixnet_model/head/dense/BiasAdd:0] shape{1,1000} type: f32>
]>, None

После:

(.ov2) C:\Users\Alexandra Sidorova\Documents\openvino>python .\openvino-dl-benchmark\src\inference\inference_async_mode.py -m "C:\Users\Alexandra Sidorova\Documents\openvino\models\public\mixnet-l\FP32\mixnet-l.xml" -w "C:\Users\Alexandra Sidorova\Documents\openvino\models\public\mixnet-l\FP32\mixnet-l.bin" -i ".\imgs\apple.png"     
[ INFO ] Inference Engine initialization
[ INFO ] Loading model files:
         C:\Users\Alexandra Sidorova\Documents\openvino\models\public\mixnet-l\FP32\mixnet-l.xml
         C:\Users\Alexandra Sidorova\Documents\openvino\models\public\mixnet-l\FP32\mixnet-l.bin
[ INFO ] Shape for input layer IteratorGetNext:0: 1x224x224x3
[ INFO ] Prepare input data
[ INFO ] Create executable network
[ INFO ] Runtime parameters
[ INFO ] DEVICE: CPU
[ INFO ]   AVAILABLE_DEVICES  , ['']
[ INFO ]   RANGE_FOR_ASYNC_INFER_REQUESTS  , (1, 1, 1)
[ INFO ]   RANGE_FOR_STREAMS  , (1, 12)
[ INFO ]   FULL_DEVICE_NAME  , Intel(R) Core(TM) i7-9750H CPU @ 2.60GHz
[ INFO ]   OPTIMIZATION_CAPABILITIES  , ['FP32', 'FP16', 'INT8', 'BIN', 'EXPORT_IMPORT']
[ INFO ]   CACHE_DIR  ,
[ INFO ]   NUM_STREAMS  , 4
[ INFO ]   INFERENCE_NUM_THREADS  , 0
[ INFO ]   PERF_COUNT  , False
[ INFO ]   PERFORMANCE_HINT_NUM_REQUESTS  , 0
[ INFO ] Starting inference (1 iterations) with 0 requests on CPU
[ INFO ] Average time of single pass : 0.025
[ INFO ] FPS : 40.052

Merge request reports