训练和预测模块 API 不使用烧瓶同时运行

Question

我用 Mask_RCNN module 和烧瓶

当我不添加 K.clear_session() 时，我会在训练和预测模块中遇到这个错误

error 无法将 feed_dict 键解释为 Tensor：Tensor Tensor(\"Placeholder:0\", shape=(7, 7, 3, 64), dtype=float32) 不是此图的元素。"}

Weights:  coco
Dataset:  ./files/coco/dataset
Logs:  ./files/coco/log1/
..........................config.........................

Configurations:
BACKBONE                       resnet101
BACKBONE_STRIDES               [4, 8, 16, 32, 64]
BATCH_SIZE                     1
BBOX_STD_DEV                   [0.1 0.1 0.2 0.2]
DETECTION_MAX_INSTANCES        100
DETECTION_MIN_CONFIDENCE       0.744
DETECTION_NMS_THRESHOLD        0.3
GPU_COUNT                      1
GRADIENT_CLIP_NORM             5.0
IMAGES_PER_GPU                 1
IMAGE_MAX_DIM                  1024
IMAGE_META_SIZE                24
IMAGE_MIN_DIM                  800
IMAGE_MIN_SCALE                0
IMAGE_RESIZE_MODE              square
IMAGE_SHAPE                    [1024 1024    3]
LEARNING_MOMENTUM              0.9
LEARNING_RATE                  0.001
LOSS_WEIGHTS                   {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0}
MASK_POOL_SIZE                 14
MASK_SHAPE                     [28, 28]
MAX_GT_INSTANCES               100
MEAN_PIXEL                     [123.7 116.8 103.9]
MINI_MASK_SHAPE                (56, 56)
NAME                           surgery
NUM_CLASSES                    12
POOL_SIZE                      7
POST_NMS_ROIS_INFERENCE        1000
POST_NMS_ROIS_TRAINING         2000
ROI_POSITIVE_RATIO             0.33
RPN_ANCHOR_RATIOS              [0.5, 1, 2]
RPN_ANCHOR_SCALES              (32, 64, 128, 256, 512)
RPN_ANCHOR_STRIDE              1
RPN_BBOX_STD_DEV               [0.1 0.1 0.2 0.2]
RPN_NMS_THRESHOLD              0.7
RPN_TRAIN_ANCHORS_PER_IMAGE    256
STEPS_PER_EPOCH                100
TRAIN_BN                       False
TRAIN_ROIS_PER_IMAGE           200
USE_MINI_MASK                  True
USE_RPN_ROIS                   True
VALIDATION_STEPS               20
WEIGHT_DECAY                   0.0001


Loading weights  ./routeDefine/coco/mrcnn/mask_rcnn_coco.h5
Exception in thread Thread-4:
Traceback (most recent call last):
  File "/home/ubuntu/anaconda3/envs/tf-gpu/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1092, in _run
    subfeed, allow_tensor=True, allow_operation=False)
  File "/home/ubuntu/anaconda3/envs/tf-gpu/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3490, in as_graph_element
    return self._as_graph_element_locked(obj, allow_tensor, allow_operation)
  File "/home/ubuntu/anaconda3/envs/tf-gpu/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3569, in _as_graph_element_locked
    raise ValueError("Tensor %s is not an element of this graph." % obj)
ValueError: Tensor Tensor("Placeholder:0", shape=(7, 7, 3, 64), dtype=float32) is not an element of this graph.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/ubuntu/anaconda3/envs/tf-gpu/lib/python3.6/threading.py", line 916, in _bootstrap_inner
    self.run()
  File "/home/ubuntu/anaconda3/envs/tf-gpu/lib/python3.6/threading.py", line 864, in run
    self._target(*self._args, **self._kwargs)
  File "/home/ubuntu/AI_Project6/routeDefine/coco/saveModelmn.py", line 111, in model
    main()
  File "/home/ubuntu/AI_Project6/routeDefine/coco/saveModelmn.py", line 108, in main
    trainmodel()
  File "/home/ubuntu/AI_Project6/routeDefine/coco/savemodel.py", line 342, in trainmodel
    "mrcnn_bbox", "mrcnn_mask"])
  File "/home/ubuntu/AI_Project6/routeDefine/coco/mrcnn/modelsave.py", line 2101, in load_weights
    saving.load_weights_from_hdf5_group_by_name(f, layers)
  File "/home/ubuntu/anaconda3/envs/tf-gpu/lib/python3.6/site-packages/keras/engine/saving.py", line 1022, in load_weights_from_hdf5_group_by_name
    K.batch_set_value(weight_value_tuples)
  File "/home/ubuntu/anaconda3/envs/tf-gpu/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 2440, in batch_set_value
    get_session().run(assign_ops, feed_dict=feed_dict)
  File "/home/ubuntu/anaconda3/envs/tf-gpu/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 929, in run
    run_metadata_ptr)
  File "/home/ubuntu/anaconda3/envs/tf-gpu/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1095, in _run
    'Cannot interpret feed_dict key as Tensor: ' + e.args[0])
TypeError: Cannot interpret feed_dict key as Tensor: Tensor Tensor("Placeholder:0", shape=(7, 7, 3, 64), dtype=float32) is not an element of this graph.

如果我使用K.clear_session() 运行文件，那么它会停止当前的工作模块并启动我想要运行的模块，就像如果预测模块正在运行然后我点击训练模块它会停止预测并运行训练。

请帮帮我

Answer 1

似乎您正在尝试在不同的会话中进行训练和预测

由于你还没有分享源代码，我可以建议你以下

1. 为训练和预测创建不同的占位符
2. 将 sess 设为全局变量，这样对于 Flask GET/POST 装饰器函数，您将共享同一个会话对象