tensorflow识别物体并框出来

要使用TensorFlow识别物体并框出来，可以使用目标检测模型，如Faster R-CNN，SSD或YOLO等。这些模型可以识别图像中的物体，并用边界框框出它们。

以下是实现此功能的一些步骤：

1. 安装 TensorFlow Object Detection API

您需要安装TensorFlow Object Detection API，该API提供了训练和推断目标检测模型所需的工具和库。您可以在此处找到安装说明：https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/installation.md

2. 下载预训练模型

TensorFlow Object Detection API提供了一些预训练的目标检测模型，您可以从以下链接中选择一个模型并下载其预训练权重：https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md

3. 加载模型

使用TensorFlow Object Detection API加载预训练模型，并将其用于图像中的目标检测。您可以使用以下代码段加载模型：

import tensorflow as tf
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util

# Path to frozen detection graph. This is the actual model that is used for the object detection.
PATH_TO_CKPT = 'path/to/frozen_inference_graph.pb'

# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = 'path/to/label_map.pbtxt'

NUM_CLASSES = 90

# Load the frozen detection graph into memory
detection_graph = tf.Graph()
with detection_graph.as_default():
    od_graph_def = tf.GraphDef()
    with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
        serialized_graph = fid.read()
        od_graph_def.ParseFromString(serialized_graph)
        tf.import_graph_def(od_graph_def, name='')

# Load label map
label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES, use_display_name=True)
category_index = label_map_util.create_category_index(categories)

4. 运行推断

使用加载的模型运行推断，并绘制边界框以框出检测到的物体。您可以使用以下代码段运行推断：

import numpy as np
import cv2

# Load image
image = cv2.imread('path/to/image.jpg')

# Define input and output tensors (i.e., image and bounding boxes)
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')
num_detections = detection_graph.get_tensor_by_name('num_detections:0')

# Run inference
with detection_graph.as_default():
    with tf.Session() as sess:
        # Expand dimensions since the model expects images to have shape: [1, None, None, 3]
        image_expanded = np.expand_dims(image, axis=0)
        (boxes, scores, classes, num) = sess.run(
            [detection_boxes, detection_scores, detection_classes, num_detections],
            feed_dict={image_tensor: image_expanded})

        # Visualize the results
        vis_util.visualize_boxes_and_labels_on_image_array(
            image,
            np.squeeze(boxes),
            np.squeeze(classes).astype(np.int32),
            np.squeeze(scores),
            category_index,
            use_normalized_coordinates=True,
            line_thickness=8)

        # Display the resulting image
        cv2.imshow('Object detection', cv2.resize(image, (800, 600)))
        cv2.waitKey(0)
        cv2.destroyAllWindows()

这将在图像中绘制边界框，以框出检测到的物体。您可以根据需要调整绘制边界框的参数，例如线条宽度和颜色。