TensorFlow 目标检测模型转换为 OpenCV DNN 可调用格式

#!/usr/bin/python3
#!--*-- coding:utf-8 --*--
import os
import numpy as np
import cv2
import matplotlib.pyplot as plt
import tensorflow as tf


model_path = "/path/to/ssd_mobilenet_v2_coco_2018_03_29"
frozen_pb_file = os.path.join(model_path, 'frozen_inference_graph.pb')

score_threshold = 0.3

img_file = 'test.jpg'

# Read the graph.
with tf.gfile.FastGFile(frozen_pb_file, 'rb') as f:
    graph_def = tf.GraphDef()
    graph_def.ParseFromString(f.read())


with tf.Session() as sess:
    # Restore session
    sess.graph.as_default()
    tf.import_graph_def(graph_def, name='')

    # Read and preprocess an image.
    img_cv2 = cv2.imread(img_file)
    img_height, img_width, _ = img_cv2.shape

    img_in = cv2.resize(img_cv2, (300, 300))
    img_in = img_in[:, :, [2, 1, 0]]  # BGR2RGB

    # Run the model
    outputs = sess.run([sess.graph.get_tensor_by_name('num_detections:0'),
                    sess.graph.get_tensor_by_name('detection_scores:0'),
                    sess.graph.get_tensor_by_name('detection_boxes:0'),
                    sess.graph.get_tensor_by_name('detection_classes:0')],
                   feed_dict={
                       'image_tensor:0': img_in.reshape(1, 
                                                        img_in.shape[0], 
                                                        img_in.shape[1], 
                                                        3)})

    # Visualize detected bounding boxes.
    num_detections = int(outputs[0][0])
    for i in range(num_detections):
        classId = int(outputs[3][0][i])
        score = float(outputs[1][0][i])
        bbox = [float(v) for v in outputs[2][0][i]]
        if score > score_threshold:
            x = bbox[1] * img_width
            y = bbox[0] * img_height
            right = bbox[3] * img_width
            bottom = bbox[2] * img_height
            cv2.rectangle(img_cv2, 
                          (int(x), int(y)), 
                          (int(right), int(bottom)), 
                          (125, 255, 51), 
                          thickness=2)

plt.figure(figsize=(10, 8))
plt.imshow(img_cv2[:, :, ::-1])
plt.title("TensorFlow MobileNetV2-SSD")
plt.axis("off")
plt.show()

 python3 tf_text_graph_faster_rcnn.py \
 	--input '/path/to/faster_rcnn_resnet50_coco_2018_01_28/frozen_inference_graph.pb' \
 	--config '/path/to/faster_rcnn_resnet50_coco.config' \
 	--output '/path/to/faster_rcnn_resnet50_coco_2018_01_28/graph.pbtxt'  

python3 tf_text_graph_ssd.py \
	--input /path/to/ssd_inception_v2_coco_2018_01_28/frozen_inference_graph.pb \
	--config /path/to/ssd_inception_v2_coco.config \
	--output /path/to/ssd_inception_v2_coco_2018_01_28/graph.pbtxt

python3 tf_text_graph_mask_rcnn2.py \
	--input '/path/to/mask_rcnn_resnet50_atrous_coco_2018_01_28/frozen_inference_graph.pb' \
	--config '/path/to/mask_rcnn_resnet50_atrous_coco.config' \
	--output '/path/to/mask_rcnn_resnet50_atrous_coco_2018_01_28/graph.pbtxt' 

python3 tf_text_graph_ssd.py \
	--input '/path/to/ssd_mobilenet_v2_coco_2018_03_29/frozen_inference_graph.pb' \
	--config '/path/to/ssd_mobilenet_v2_coco.config' \
	--output '/path/to/ssd_mobilenet_v2_coco_2018_03_29/graph.pbtxt' 

Scale: [0.200000-0.950000]
Aspect ratios: [1.0, 2.0, 0.5, 3.0, 0.3333]
Reduce boxes in the lowest layer: True
Number of classes: 90
Number of layers: 6
box predictor: convolutional
Input image size: 300x300

#!/usr/bin/python
#!--*-- coding:utf-8 --*--
import cv2
import matplotlib.pyplot as plt


pb_file = '/path/to/ssd_inception_v2_coco_2018_01_28/frozen_inference_graph.pb'
pbtxt_file = '/path/to/ssd_inception_v2_coco_2018_01_28/graph.pbtxt'
net = cv2.dnn.readNetFromTensorflow(pb_file, pbtxt_file)

score_threshold = 0.3

img_file = 'test.jpg'

img_cv2 = cv2.imread(img_file)
height, width, _ = img_cv2.shape
net.setInput(cv2.dnn.blobFromImage(img_cv2, 
                                   size=(300, 300), 
                                   swapRB=True, 
                                   crop=False))

out = net.forward()
print(out)

for detection in out[0, 0, :,:]:
    score = float(detection[2])
    if score > score_threshold:
        left = detection[3] * width
        top = detection[4] * height
        right = detection[5] * width
        bottom = detection[6] * height
        cv2.rectangle(img_cv2, 
                      (int(left), int(top)), 
                      (int(right), int(bottom)), 
                      (23, 230, 210), 
                      thickness=2)

t, _ = net.getPerfProfile()
label = 'Inference time: %.2f ms' % \
            (t * 1000.0 / cv2.getTickFrequency())
cv2.putText(img_cv2, label, (0, 15), 
            cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255))


plt.figure(figsize=(10, 8))
plt.imshow(img_cv2[:, :, ::-1])
plt.title("OpenCV DNN MobileNetV2-SSD")
plt.axis("off")
plt.show()