若该文为原创文章,转载请注明原文出处。
通过ResNet50网络训练了识别10类车的模型并成功了转换成了onnx模型
具体训练过程可以参考文章AI项目十七:ResNet50训练部署教程-CSDN博客
这里部署使用rknn-toolkit2工具转换成RKNN模型并测试
rknn-toolkit2工具安装在前面文章有説明了,自行安装。
接下来测试并转成RKNN模型
一、onnx转成rknn模型
在rknn-toolkit2-master/examples/onnx目录下创建04_resnet50目录。
在04_resnet50目录下创建test.py文本
import os
import urllib.request as request
import urllib
import traceback
import time
import sys
import numpy as np
import cv2
from rknn.api import RKNN
ONNX_MODEL = '10class_ResNet50.onnx'
RKNN_MODEL = '10class_ResNet50.rknn'
def show_outputs(outputs):
output = outputs[0][0]
output_sorted = sorted(output, reverse=True)
top5_str = 'resnet50v2\n-----TOP 5-----\n'
for i in range(5):
value = output_sorted[i]
index = np.where(output == value)
for j in range(len(index)):
if (i + j) >= 5:
break
if value > 0:
topi = '{}: {}\n'.format(index[j], value)
else:
topi = '-1: 0.0\n'
top5_str += topi
print(top5_str)
def readable_speed(speed):
speed_bytes = float(speed)
speed_kbytes = speed_bytes / 1024
if speed_kbytes > 1024:
speed_mbytes = speed_kbytes / 1024
if speed_mbytes > 1024:
speed_gbytes = speed_mbytes / 1024
return "{:.2f} GB/s".format(speed_gbytes)
else:
return "{:.2f} MB/s".format(speed_mbytes)
else:
return "{:.2f} KB/s".format(speed_kbytes)
def show_progress(blocknum, blocksize, totalsize):
speed = (blocknum * blocksize) / (time.time() - start_time)
speed_str = " Speed: {}".format(readable_speed(speed))
recv_size = blocknum * blocksize
f = sys.stdout
progress = (recv_size / totalsize)
progress_str = "{:.2f}%".format(progress * 100)
n = round(progress * 50)
s = ('#' * n).ljust(50, '-')
f.write(progress_str.ljust(8, ' ') + '[' + s + ']' + speed_str)
f.flush()
f.write('\r\n')
if __name__ == '__main__':
# Create RKNN object
rknn = RKNN(verbose=True)
# If resnet50v2 does not exist, download it.
# Download address:
# https://s3.amazonaws.com/onnx-model-zoo/resnet/resnet50v2/resnet50v2.onnx
if not os.path.exists(ONNX_MODEL):
print('--> Download {}'.format(ONNX_MODEL))
url = 'https://s3.amazonaws.com/onnx-model-zoo/resnet/resnet50v2/resnet50v2.onnx'
download_file = ONNX_MODEL
try:
start_time = time.time()
urllib.request.urlretrieve(url, download_file, show_progress)
except:
print('Download {} failed.'.format(download_file))
print(traceback.format_exc())
exit(-1)
print('done')
# pre-process config
print('--> config model')
rknn.config(mean_values=[123.675, 116.28, 103.53], std_values=[58.82, 58.82, 58.82])
print('done')
# Load model
print('--> Loading model')
ret = rknn.load_onnx(model=ONNX_MODEL)
if ret != 0:
print('Load model failed!')
exit(ret)
print('done')
# Build model
print('--> Building model')
ret = rknn.build(do_quantization=True, dataset='./dataset.txt')
if ret != 0:
print('Build model failed!')
exit(ret)
print('done')
# Export rknn model
print('--> Export rknn model')
ret = rknn.export_rknn(RKNN_MODEL)
if ret != 0:
print('Export rknn model failed!')
exit(ret)
print('done')
# Set inputs
img1 = cv2.imread('./test.jpg')
img1 = cv2.cvtColor(img1, cv2.COLOR_BGR2RGB)
img = cv2.resize(img1, (224, 224))
# Init runtime environment
print('--> Init runtime environment')
ret = rknn.init_runtime()
if ret != 0:
print('Init runtime environment failed!')
exit(ret)
print('done')
# Inference
print('--> Running model')
outputs = rknn.inference(inputs=[img])
np.save('./onnx_resnet50v2_0.npy', outputs[0])
x = outputs[0]
output = np.exp(x)/np.sum(np.exp(x))
outputs = [output]
show_outputs(outputs)
print('done')
rknn.release()
程序里有个需要注意的,resnet50模型使用的是224*224大小,所以在加载图片时,需要把图片缩放成224*224大小,否则会报下面的错误
E inference: The input(ndarray) shape (1, 768, 1024, 3) is wrong, expect 'nhwc' like (1, 224, 224, 3)!
运行
python test.py
成功运行
如有侵权,或需要完整代码,请及时联系博主。