ssd评估程序eval_ssd_network.py执行错误：OP_REQUIRES failed at save_restore_tensor.cc:170

# =========================================================================== #
# Training | Evaluation flags:
# =========================================================================== #
{'batch_size': <absl.flags._flag.Flag object at 0x000001B293BF4828>,
 'checkpoint_path': <absl.flags._flag.Flag object at 0x000001B293BF49E8>,
 'dataset_dir': <absl.flags._flag.Flag object at 0x000001B293BF4C88>,
 'dataset_name': <absl.flags._flag.Flag object at 0x000001B293BF4B70>,
 'dataset_split_name': <absl.flags._flag.Flag object at 0x000001B293BF4BE0>,
 'eval_dir': <absl.flags._flag.Flag object at 0x000001B293BF4A58>,
 'eval_image_size': <absl.flags._flag.Flag object at 0x000001B293BF4668>,
 'eval_resize': <absl.flags._flag.Flag object at 0x000001B293BF45C0>,
 'gpu_memory_fraction': <absl.flags._flag.Flag object at 0x000001B293BF4E48>,
 'h': <tensorflow.python.platform.app._HelpFlag object at 0x000001B293BF4F28>,
 'help': <tensorflow.python.platform.app._HelpFlag object at 0x000001B293BF4F28>,
 'helpfull': <tensorflow.python.platform.app._HelpfullFlag object at 0x000001B293BF4F98>,
 'helpshort': <tensorflow.python.platform.app._HelpshortFlag object at 0x000001B293BFB048>,
 'keep_top_k': <absl.flags._flag.Flag object at 0x000001B293BF69E8>,
 'master': <absl.flags._flag.Flag object at 0x000001B293BF4940>,
 'matching_threshold': <absl.flags._flag.Flag object at 0x000001B293BF4518>,
 'max_num_batches': <absl.flags._flag.Flag object at 0x000001B293BF48D0>,
 'model_name': <absl.flags._flag.Flag object at 0x000001B293BF4CF8>,
 'moving_average_decay': <absl.flags._flag.Flag object at 0x000001B293BF4DD8>,
 'nms_threshold': <absl.flags._flag.Flag object at 0x000001B293BF4470>,
 'num_classes': <absl.flags._flag.Flag object at 0x000001B293BF4780>,
 'num_preprocessing_threads': <absl.flags._flag.Flag object at 0x000001B293BF4AC8>,
 'preprocessing_name': <absl.flags._flag.Flag object at 0x000001B293BF4D68>,
 'remove_difficult': <absl.flags._flag.BooleanFlag object at 0x000001B293BF46A0>,
 'select_threshold': <absl.flags._flag.Flag object at 0x000001B2F6117B38>,
 'select_top_k': <absl.flags._flag.Flag object at 0x000001B293BCD780>,
 'wait_for_checkpoints': <absl.flags._flag.BooleanFlag object at 0x000001B293BF4E80>}

# =========================================================================== #
# SSD net parameters:
# =========================================================================== #
{'anchor_offset': 0.5,
 'anchor_ratios': [[2, 0.5],
                   [2, 0.5, 3, 0.3333333333333333],
                   [2, 0.5, 3, 0.3333333333333333],
                   [2, 0.5, 3, 0.3333333333333333],
                   [2, 0.5],
                   [2, 0.5]],
 'anchor_size_bounds': [0.15, 0.9],
 'anchor_sizes': [(2.0, 45.0),
                  (45.0, 99.0),
                  (99.0, 153.0),
                  (153.0, 207.0),
                  (207.0, 261.0),
                  (261.0, 315.0)],
 'anchor_steps': [8, 16, 32, 64, 100, 300],
 'feat_layers': ['block4', 'block7', 'block8', 'block9', 'block10', 'block11'],
 'feat_shapes': [(38, 38), (19, 19), (10, 10), (5, 5), (3, 3), (1, 1)],
 'img_shape': (300, 300),
 'no_annotation_label': 2,
 'normalizations': [20, -1, -1, -1, -1, -1],
 'num_classes': 2,
 'prior_scaling': [0.1, 0.1, 0.2, 0.2]}

# =========================================================================== #
# Training | Evaluation dataset files:
# =========================================================================== #
['.\\VOC2007\\test\\tfrecords\\voc_2007_train_000.tfrecord',
 '.\\VOC2007\\test\\tfrecords\\voc_2007_train_001.tfrecord',
 '.\\VOC2007\\test\\tfrecords\\voc_2007_train_002.tfrecord',
 '.\\VOC2007\\test\\tfrecords\\voc_2007_train_003.tfrecord']

WARNING:tensorflow:From D:/work/SSD-Tensorflow-master/eval_ssd_network.py:243: streaming_mean (from tensorflow.contrib.metrics.python.ops.metric_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Please switch to tf.metrics.mean
INFO:tensorflow:Evaluating /tmp/tfmodel/
INFO:tensorflow:Starting evaluation at 2019-03-12-14:32:10
INFO:tensorflow:Graph was finalized.
2019-03-12 22:32:10.434182: I c:\users\user\source\repos\tensorflow\tensorflow\core\platform\cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX AVX2
2019-03-12 22:32:10.658497: I c:\users\user\source\repos\tensorflow\tensorflow\core\common_runtime\gpu\gpu_device.cc:1392] Found device 0 with properties: 
name: GeForce GTX 1070 major: 6 minor: 1 memoryClockRate(GHz): 1.645
pciBusID: 0000:01:00.0
totalMemory: 8.00GiB freeMemory: 6.62GiB
2019-03-12 22:32:10.658842: I c:\users\user\source\repos\tensorflow\tensorflow\core\common_runtime\gpu\gpu_device.cc:1471] Adding visible gpu devices: 0
2019-03-12 22:32:11.307547: I c:\users\user\source\repos\tensorflow\tensorflow\core\common_runtime\gpu\gpu_device.cc:952] Device interconnect StreamExecutor with strength 1 edge matrix:
2019-03-12 22:32:11.307763: I c:\users\user\source\repos\tensorflow\tensorflow\core\common_runtime\gpu\gpu_device.cc:958]      0 
2019-03-12 22:32:11.307907: I c:\users\user\source\repos\tensorflow\tensorflow\core\common_runtime\gpu\gpu_device.cc:971] 0:   N 
2019-03-12 22:32:11.308246: I c:\users\user\source\repos\tensorflow\tensorflow\core\common_runtime\gpu\gpu_device.cc:1084] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 819 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1070, pci bus id: 0000:01:00.0, compute capability: 6.1)
INFO:tensorflow:Restoring parameters from /tmp/tfmodel/
2019-03-12 22:32:11.425660: W c:\users\user\source\repos\tensorflow\tensorflow\core\framework\op_kernel.cc:1318] OP_REQUIRES failed at save_restore_tensor.cc:170 : Invalid argument: Unsuccessful TensorSliceReader constructor: Failed to get matching files on /tmp/tfmodel/: Not found: FindFirstFile failed for: /tmp/tfmodel : ϵͳ�Ҳ���ָ����·����
; No such process

Process finished with exit code -1073741819 (0xC0000005)