tf_inference.py

import tensorflow as tf
import numpy as np
from object_detection.utils import ops as utils_ops

class InferenceEngine:
    def __init__(self, ckpt_file):
        self.path_to_ckpt = ckpt_file
        self.detection_graph = self.load_tfgraph()

    def load_tfgraph(self):
        """ Load TF graph into memory"""
        detection_graph = tf.Graph()
        with detection_graph.as_default():
            od_graph_def = tf.GraphDef()
            with tf.gfile.GFile(self.path_to_ckpt, 'rb') as fid:
                serialized_graph = fid.read()
                od_graph_def.ParseFromString(serialized_graph)
                tf.import_graph_def(od_graph_def, name='')
        return detection_graph

    def run_inference_for_single_image(self, image_np):
        """ Run inference for a single image """
        with self.detection_graph.as_default():
            with tf.Session() as sess:
            # Get handles to input and output tensors
                ops = tf.get_default_graph().get_operations()
                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'
                    if tensor_name in all_tensor_names:
                        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])
                    # Reframe is required to translate mask from box coordinates to image coordinates and fit the image size.
                    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_np.shape[0], image_np.shape[1])
                    detection_masks_reframed = tf.cast(tf.greater(detection_masks_reframed, 0.5), tf.uint8)
                    # Follow the convention by adding back the batch dimension
                    tensor_dict['detection_masks'] = tf.expand_dims(detection_masks_reframed, 0)
                image_tensor = tf.get_default_graph().get_tensor_by_name('image_tensor:0')

                # Run inference
                output_dict = sess.run(tensor_dict,feed_dict={image_tensor: np.expand_dims(image_np, 0)})

                # all outputs are float32 numpy arrays, so convert types as appropriate
                output_dict['num_detections'] = int(output_dict['num_detections'][0])
                output_dict['detection_classes'] = output_dict['detection_classes'][0].astype(np.uint8)
                output_dict['detection_boxes'] = output_dict['detection_boxes'][0]
                output_dict['detection_scores'] = output_dict['detection_scores'][0]
                if 'detection_masks' in output_dict:
                    output_dict['detection_masks'] = output_dict['detection_masks'][0]
                    # Need to include only the ones with confidence > threshold
        return output_dict