TensorFlow Object Detection API版本适配困惑及TF1.15运行报错求助

Hey there! Let's work through your confusion and errors one by one:

一、关于TensorFlow版本冲突的困惑 #

其实这个问题是因为Object Detection API的版本迭代导致的文档滞后：

• 早期的API版本确实只支持TensorFlow 1.x，但现在官方已经完成了TF2.x的适配，并且当前官方主推的就是TF2.x版本。
• 你看到的“暂不支持TF2.x”的页面应该是旧文档，而Demo要求安装TF2.x是因为它基于最新的TF2分支API。建议你直接使用TensorFlow 2.x版本搭配最新的Object Detection API，这样版本匹配，后续也能获得更好的支持。

二、TF1.15运行Demo时的TypeError错误 #

从你给出的模型调用输出可以看到，所有返回的结果都是Tensor对象（比如num_detections是<tf.Tensor 'StatefulPartitionedCall:4' shape=(?,) dtype=float32>），而不是实际的数值。这是因为：

• 在TensorFlow 1.x中，默认是图执行模式，Tensor只是计算图中的节点，需要通过会话（Session）来运行才能得到具体数值；而你可能用了TF2风格的模型加载/调用方式，导致返回的是未计算的Tensor。

修复方法（针对TF1.15） #

修改你的run_inference_for_single_image函数，添加会话运行的逻辑：

def run_inference_for_single_image(image, graph):
    with 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.shape[0], image.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, 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]
    return output_dict

核心是用sess.run()来执行Tensor计算，得到实际的数值数组，再从中提取需要的结果。

更推荐的方案 #

直接切换到TensorFlow 2.x版本，使用官方最新的Object Detection API。TF2默认开启 eager execution，不需要手动管理会话，推理代码会更简洁，也能和Demo的要求匹配，避免版本不兼容的问题。

内容的提问来源于stack exchange，提问作者Aakash