faster rcnn resnet50模型的特征图
用我的程序代码 生成特征图
类似于这样的
1
您会吗
发下代码
好的
稍等
w我应该给您一个文件包吧 这个能传文件吗
不知道用哪几个
# 导入对应模块包 import os import cv2 import tensorflow as tf import numpy as np import pandas as pd # 导入对应的模块 from object_detect.utils import label_map_util from object_detect.utils import visualization_utils as vis_util from object_detect.utils import ops as utils_ops # Path to frozen detection graph. This is the actual model that is used for the object detection. # 训练好的pb模型文件路径 PATH_TO_FROZEN_GRAPH = 'model/export/ssd_inception/frozen_inference_graph.pb' # List of the strings that is used to add correct label for each box. # 类目配置文件pbtxt文件路径 PATH_TO_LABELS = os.path.join('dataset', 'label.pbtxt') # 类别数量(只有肿瘤一类就填1) NUM_CLASSES = 2 # OpenCV计时函数，获取计时开始时间 start = cv2.getTickCount() # 定义TensorFlow图 detection_graph = tf.Graph() with detection_graph.as_default(): od_graph_def = tf.GraphDef() with tf.gfile.GFile(PATH_TO_FROZEN_GRAPH, 'rb') as fid: serialized_graph = fid.read() od_graph_def.ParseFromString(serialized_graph) tf.import_graph_def(od_graph_def, name='') # 加载配置文件中的类别label label_map = label_map_util.load_labelmap(PATH_TO_LABELS) # 类别转换 categorys = label_map_util.convert_label_map_to_categories(label_map,max_num_classes=NUM_CLASSES,use_display_name=True) # 类别编号index categorys_index = label_map_util.create_category_index(categorys) # 设置GPU配置，允许动态分配GPU显存 config = tf.ConfigProto() config.gpu_options.allow_growth = True # 处理每一张图片的函数 def run_inference_for_single_image(image,graph): with graph.as_default(): with tf.Session() as sess: # 获得图中所有的op ops =tf.get_default_graph().get_operations() # 获得输出op的名字 all_tensor_names = {output.name for op in ops for output in op.outputs} tensor_dict = {} for key in ['num_detections', 'detection_boxes', 'detection_scores', 'detection_classes', 'detection_masks']: tensor_name = key + ':0' # 如果tensor_name在all_tensor_names中 if tensor_name in all_tensor_names: # 则获取到该tensor tensor_dict[key] = tf.get_default_graph().get_tensor_by_name(tensor_name) if 'detection_masks' in tensor_dict: # The following processing is only for single image detection_boxes = tf.squeeze(tensor_dict['detection_boxes'], [0]) detection_masks = tf.squeeze(tensor_dict['detection_masks'], [0]) real_num_detection = tf.cast(tensor_dict['num_detections'][0], tf.int32) detection_boxes = tf.slice(detection_boxes, [0, 0], [real_num_detection, -1]) detection_masks = tf.slice(detection_masks, [0, 0, 0], [real_num_detection, -1, -1]) detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks( detection_masks, detection_boxes, image.shape[0], image.shape[1]) detection_masks_reframed = tf.cast( tf.greater(detection_masks_reframed, 0.5), tf.uint8) tensor_dict['detection_masks'] = tf.expand_dims( detection_masks_reframed, 0) # 图片输入的tensor image_tensor = tf.get_default_graph().get_tensor_by_name('image_tensor:0') # 传入图片运行模型获取结果 output_dict = sess.run(tensor_dict, feed_dict={image_tensor: np.expand_dims(image, 0)}) # 所有的结果都是float32类型的，有些数据需要做数据格式转换 # 检测到目标的数量 output_dict['num_detections'] = int(output_dict['num_detections'][0]) # 目标的类型 output_dict['detection_classes']= output_dict[ 'detection_classes'][0].astype(np.uint8) # 预测框坐标 output_dict['detection_boxes'] = output_dict['detection_boxes'][0] # 预测框置信度 output_dict['detection_scores'] = output_dict['detection_scores'][0] if 'detection_masks' in output_dict: output_dict['detection_masks'] = output_dict['detection_masks'][0] return output_dict imgs_path = 'dataset/test_test/' # os.chdir(imgs_path) i = 1 # 存储标注的数据，图片名，置信度，ymin, xmin, ymax, xmax marks = [] for img in os.listdir(imgs_path): with detection_graph.as_default(): with tf.Session(graph=detection_graph,config=config) as sess: # 读取测试图片 imageName = imgs_path + img # print(imageName) image = cv2.imread(imageName) #image = cv2.imread("./dataset/JPEGImages/1.jpg") image_np_expanded = np.expand_dims(image,axis = 0) image_tensor = detection_graph.get_tensor_by_name('image_tensor:0') boxes = detection_graph.get_tensor_by_name('detection_boxes:0') scores = detection_graph.get_tensor_by_name('detection_scores:0') classes = detection_graph.get_tensor_by_name('detection_classes:0') # # output_dict = run_inference_for_single_image(image,detection_graph) num_detections = detection_graph.get_tensor_by_name('num_detections:0') (boxes,scores,classes,num_detections) = sess.run([boxes,scores,classes,\ num_detections],feed_dict={image_tensor:image_np_expanded}) vis_util.visualize_boxes_and_labels_on_image_array( image, np.squeeze(boxes), np.squeeze(classes).astype(np.int32), np.squeeze(scores), categorys_index, instance_masks = output_dict.get('detection_masks'), min_score_thresh = 0.6, use_normalized_coordinates = True, line_thickness = 3 ) boxes = np.squeeze(boxes) scores = np.squeeze(scores) ymin, xmin, ymax, xmax = boxes[0] score = scores[0] # print(ymin, xmin, ymax, xmax) # print(score) mark = [img,score,ymin, xmin, ymax, xmax] marks.append(mark) # 计时结束 end = cv2.getTickCount() # 计算花费时间 use_time = (end - start) / cv2.getTickFrequency() print("use_time:%0.3fs" % use_time) # 保存结果图。cv2.imwrite只能保存在当前路径，不能指定保存位置， img_name = 'result' +img cv2.imwrite(img_name,image) print('已经标记好第%d张图片'%i) i+=1 #image = cv2.resize(image,None,fx=0.5,fy=0.5,interpolation=cv2.INTER_LINEAR) # 显示结果图 cv2.imshow("object_detection", image) cv2.waitKey(0) cv2.destroyAllWindows() df = pd.DataFrame(data=marks, columns=['imgname','score', 'ymin', 'xmin', 'ymax', 'xmax']) df.to_csv('marked_faster_rcnn.csv', index=False, encoding='utf-8_sig') print("数据导出成功！")
你是想要什么结果呢
就是这样的特征可视化的图 但是不是这张 我把图片发给你吗现在
要是能实现的话 我要那个改过 的代码
谢谢您
能发一个网盘看一下吗