mmdetection中使用训练好的模型批量检测图片并保存到文件夹

保存到文件夹查看预测情况

from argparse import ArgumentParser
import os
from mmdet.apis import inference_detector, init_detector  #, show_result_pyplot
import cv2

def show_result_pyplot(model, img, result, score_thr=0.3, fig_size=(15, 10)):
    """Visualize the detection results on the image.

    Args:
        model (nn.Module): The loaded detector.
        img (str or np.ndarray): Image filename or loaded image.
        result (tuple
or list): The detection result, can be either (bbox, segm) or just bbox. score_thr (float): The threshold to visualize the bboxes and masks. fig_size (tuple): Figure size of the pyplot figure. """ if hasattr(model, 'module'): model = model.module img = model.show_result(img, result, score_thr=score_thr, show=False) return img # plt.figure(figsize=fig_size) # plt.imshow(mmcv.bgr2rgb(img)) # plt.show() def main(): # config文件 config_file = '/mmdetection-master/work_dirs/faster_rcnn_r50_fpn_1x_voc0712.py' # 训练好的模型 checkpoint_file = '/mmdetection-master/work_dirs/epoch_100.pth' # model = init_detector(config_file, checkpoint_file) model = init_detector(config_file, checkpoint_file, device='cuda:0') # 图片路径 img_dir = '/data/VOCdevkit/VOC2007/JPEGImages/' # 检测后存放图片路径 out_dir = '/mmdetection-master/frcnn_result/' if not os.path.exists(out_dir): os.mkdir(out_dir) # 测试集的图片名称txt test_path = '/data/VOCdevkit/VOC2007/ImageSets/Main/test.txt' fp = open(test_path, 'r') test_list = fp.readlines() count = 0 imgs = [] for test in test_list: test = test.replace('\n', '') name = img_dir + test + '.jpg' count += 1 print('model is processing the {}/{} images.'.format(count, len(test_list))) # result = inference_detector(model, name) # model = init_detector(config_file, checkpoint_file, device='cuda:0') result = inference_detector(model, name) img = show_result_pyplot(model, name, result, score_thr=0.8) cv2.imwrite("{}/{}.jpg".format(out_dir, test), img) if __name__ == '__main__': main()

 

版权声明:本文为CSDN博主「natures66」的原创文章,遵循CC 4.0 BY-SA版权协议,转载请附上原文出处链接及本声明。
原文链接:https://blog.csdn.net/natures66/article/details/115062657

natures66

我还没有学会写个人说明!

暂无评论

发表评论

相关推荐