File size: 2,709 Bytes
e0b3895 a07f7bd 00a9b48 a07f7bd ec17a5b e0b3895 a07f7bd 160af44 e0b3895 a07f7bd 160af44 e0b3895 160af44 e0b3895 2074f99 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 |
# This file is part of OpenCV Zoo project.
# It is subject to the license terms in the LICENSE file found in the same directory.
#
# Copyright (C) 2021, Shenzhen Institute of Artificial Intelligence and Robotics for Society, all rights reserved.
# Third party copyrights are property of their respective owners.
import argparse
import numpy as np
import cv2 as cv
from ppresnet import PPResNet
# Check OpenCV version
assert cv.__version__ >= "4.8.0", \
"Please install latest opencv-python to try this demo: python3 -m pip install --upgrade opencv-python"
# Valid combinations of backends and targets
backend_target_pairs = [
[cv.dnn.DNN_BACKEND_OPENCV, cv.dnn.DNN_TARGET_CPU],
[cv.dnn.DNN_BACKEND_CUDA, cv.dnn.DNN_TARGET_CUDA],
[cv.dnn.DNN_BACKEND_CUDA, cv.dnn.DNN_TARGET_CUDA_FP16],
[cv.dnn.DNN_BACKEND_TIMVX, cv.dnn.DNN_TARGET_NPU],
[cv.dnn.DNN_BACKEND_CANN, cv.dnn.DNN_TARGET_NPU]
]
parser = argparse.ArgumentParser(description='Deep Residual Learning for Image Recognition (https://arxiv.org/abs/1512.03385, https://github.com/PaddlePaddle/PaddleHub)')
parser.add_argument('--input', '-i', type=str,
help='Usage: Set input path to a certain image, omit if using camera.')
parser.add_argument('--model', '-m', type=str, default='image_classification_ppresnet50_2022jan.onnx',
help='Usage: Set model path, defaults to image_classification_ppresnet50_2022jan.onnx.')
parser.add_argument('--backend_target', '-bt', type=int, default=0,
help='''Choose one of the backend-target pair to run this demo:
{:d}: (default) OpenCV implementation + CPU,
{:d}: CUDA + GPU (CUDA),
{:d}: CUDA + GPU (CUDA FP16),
{:d}: TIM-VX + NPU,
{:d}: CANN + NPU
'''.format(*[x for x in range(len(backend_target_pairs))]))
parser.add_argument('--top_k', type=int, default=1,
help='Usage: Get top k predictions.')
args = parser.parse_args()
if __name__ == '__main__':
backend_id = backend_target_pairs[args.backend_target][0]
target_id = backend_target_pairs[args.backend_target][1]
top_k = args.top_k
# Instantiate ResNet
model = PPResNet(modelPath=args.model, topK=top_k, backendId=backend_id, targetId=target_id)
# Read image and get a 224x224 crop from a 256x256 resized
image = cv.imread(args.input)
image = cv.cvtColor(image, cv.COLOR_BGR2RGB)
image = cv.resize(image, dsize=(256, 256))
image = image[16:240, 16:240, :]
# Inference
result = model.infer(image)
# Print result
print('label: {}'.format(result))
|