Tensorflow &引用；Conv2D op目前仅支持CPU上的NHWC张量格式；尽管NHWC格式（YOLO 3）存在错误

为了学习如何使用Tensorflow 2和YOLO框架，我正在尝试从中运行一些示例代码。我的笔记本电脑有一个M1000M图形卡，我从NVIDIA安装了CUDA平台

因此，所讨论的代码是这一位：

tf.compat.v1.disable_eager_execution()

_MODEL_SIZE = (416, 416)
_CLASS_NAMES_FILE = './data/labels/coco.names'
_MAX_OUTPUT_SIZE = 20


def main(type, iou_threshold, confidence_threshold, input_names):
    class_names = load_class_names(_CLASS_NAMES_FILE)
    n_classes = len(class_names)

    model = Yolo_v3(n_classes=n_classes, model_size=_MODEL_SIZE,
                    max_output_size=_MAX_OUTPUT_SIZE,
                    iou_threshold=iou_threshold,
                    confidence_threshold=confidence_threshold)

    if type == 'images':
        batch_size = len(input_names)
        batch = load_images(input_names, model_size=_MODEL_SIZE)
        inputs = tf.compat.v1.placeholder(tf.float32, [batch_size, *_MODEL_SIZE, 3])
        detections = model(inputs, training=False)
        saver = tf.compat.v1.train.Saver(tf.compat.v1.global_variables(scope='yolo_v3_model'))

        with tf.compat.v1.Session() as sess:
            saver.restore(sess, './weights/model.ckpt')
            detection_result = sess.run(detections, feed_dict={inputs: batch})

        draw_boxes(input_names, detection_result, class_names, _MODEL_SIZE)

        print('Detections have been saved successfully.')

在执行此操作时（还想知道为什么启动detection.py一开始不使用GPU），我得到了错误消息：

File "C:\SDKs etc\Python 3.8\lib\site-packages\tensorflow\python\client\session.py", line 1451, in _call_tf_sessionrun
    return tf_session.TF_SessionRun_wrapper(self._session, options, feed_dict,
tensorflow.python.framework.errors_impl.UnimplementedError: The Conv2D op currently only supports the NHWC tensor format on the CPU. The op was given the format: NCHW
         [[{{node yolo_v3_model/conv2d/Conv2D}}]]

完整日志请参阅

如果我理解正确的话，

inputs=tf.compat.v1.placeholder（tf.float32，[batch\u size，*\u MODEL\u size，3]）

的格式已经是NHWC（MODEL size是一个由2个数字组成的元组），我不知道我需要如何在代码中进行更改才能在CPU上运行

如果我理解正确，输入的格式= 占位符（tf.float32，[batch\u size，*\u MODEL\u size，3]）是 已经是NHWC（型号大小是2个数字的元组），我不知道怎么做 我需要更改代码中的内容，以使其在CPU上运行

是的，你是。但是：

后来：

def __call__(self, inputs, training):
    """Add operations to detect boxes for a batch of input images.
    Args:
        inputs: A Tensor representing a batch of input images.
        training: A boolean, whether to use in training or inference mode.
    Returns:
        A list containing class-to-boxes dictionaries
            for each sample in the batch.
    """
    with tf.compat.v1.variable_scope('yolo_v3_model'):
        if self.data_format == 'channels_first':
            inputs = tf.transpose(inputs, [0, 3, 1, 2])

解决方案：

按预期检查工作

如果没有-创建模型时手动设置订单：

model=Yolo\u v3（n\u classes=n\u classes，model\u size=\u model\u size，

max\u output\u size=\u max\u output\u size，

iou\u threshold=iou\u threshold，

置信度阈值=置信度阈值，

data\u format='channels\u last'）

---

我回答了你的问题了吗？还是有什么不清楚的地方？很难说。问题是，我太笨了，无法在Cuda安装后针对这个特定问题重新启动。然而，我最终使用conda而不是pip来安装依赖项，因为这会自动拉取所有cuda依赖项

def __call__(self, inputs, training):
    """Add operations to detect boxes for a batch of input images.
    Args:
        inputs: A Tensor representing a batch of input images.
        training: A boolean, whether to use in training or inference mode.
    Returns:
        A list containing class-to-boxes dictionaries
            for each sample in the batch.
    """
    with tf.compat.v1.variable_scope('yolo_v3_model'):
        if self.data_format == 'channels_first':
            inputs = tf.transpose(inputs, [0, 3, 1, 2])