Question

我尝试为我的数据集训练Keras R-FCN，并且我需要保存完整的模型，因为在完成之前无法全部训练模型，所以我需要在恢复训练时恢复模型。

但是，如果我减轻重量，仅代码能正常工作，那么我无法使用modelCheckpoint或model.save保存完整模型。

我使用TensorFlow-GPU 1.15.0和Keras 2.2.4

File "/content/testing.py", line 130, in <module>
    ses.run(main())
  File "/content/testing.py", line 123, in main
    layers='all')
  File "/content/KerasRFCN/Model/Model.py", line 546, in train
    use_multiprocessing=False,
  File "/usr/local/lib/python3.6/dist-packages/keras/legacy/interfaces.py", line 91, in wrapper
    return func(*args, **kwargs)
  File "/usr/local/lib/python3.6/dist-packages/keras/engine/training.py", line 1418, in fit_generator
    initial_epoch=initial_epoch)
  File "/usr/local/lib/python3.6/dist-packages/keras/engine/training_generator.py", line 251, in fit_generator
    callbacks.on_epoch_end(epoch, epoch_logs)
  File "/usr/local/lib/python3.6/dist-packages/keras/callbacks.py", line 79, in on_epoch_end
    callback.on_epoch_end(epoch, logs)
  File "/usr/local/lib/python3.6/dist-packages/keras/callbacks.py", line 446, in on_epoch_end
    self.model.save(filepath, overwrite=True)
  File "/usr/local/lib/python3.6/dist-packages/keras/engine/network.py", line 1090, in save
    save_model(self, filepath, overwrite, include_optimizer)
  File "/usr/local/lib/python3.6/dist-packages/keras/engine/saving.py", line 382, in save_model
    _serialize_model(model, f, include_optimizer)
  File "/usr/local/lib/python3.6/dist-packages/keras/engine/saving.py", line 83, in _serialize_model
    model_config['config'] = model.get_config()
  File "/usr/local/lib/python3.6/dist-packages/keras/engine/network.py", line 931, in get_config
    return copy.deepcopy(config)
  File "/usr/lib/python3.6/copy.py", line 150, in deepcopy
    y = copier(x, memo)
  File "/usr/lib/python3.6/copy.py", line 240, in _deepcopy_dict
    y[deepcopy(key, memo)] = deepcopy(value, memo)
  File "/usr/lib/python3.6/copy.py", line 150, in deepcopy
    y = copier(x, memo)
  File "/usr/lib/python3.6/copy.py", line 215, in _deepcopy_list
    append(deepcopy(a, memo))
  File "/usr/lib/python3.6/copy.py", line 150, in deepcopy
    y = copier(x, memo)
  File "/usr/lib/python3.6/copy.py", line 240, in _deepcopy_dict
    y[deepcopy(key, memo)] = deepcopy(value, memo)
  File "/usr/lib/python3.6/copy.py", line 150, in deepcopy
    y = copier(x, memo)
  File "/usr/lib/python3.6/copy.py", line 240, in _deepcopy_dict
    y[deepcopy(key, memo)] = deepcopy(value, memo)
  File "/usr/lib/python3.6/copy.py", line 150, in deepcopy
    y = copier(x, memo)
  File "/usr/lib/python3.6/copy.py", line 220, in _deepcopy_tuple
    y = [deepcopy(a, memo) for a in x]
  File "/usr/lib/python3.6/copy.py", line 220, in <listcomp>
    y = [deepcopy(a, memo) for a in x]
  File "/usr/lib/python3.6/copy.py", line 150, in deepcopy
    y = copier(x, memo)
  File "/usr/lib/python3.6/copy.py", line 220, in _deepcopy_tuple
    y = [deepcopy(a, memo) for a in x]
  File "/usr/lib/python3.6/copy.py", line 220, in <listcomp>
    y = [deepcopy(a, memo) for a in x]
  File "/usr/lib/python3.6/copy.py", line 180, in deepcopy
    y = _reconstruct(x, memo, *rv)
  File "/usr/lib/python3.6/copy.py", line 280, in _reconstruct
    state = deepcopy(state, memo)
  File "/usr/lib/python3.6/copy.py", line 150, in deepcopy
    y = copier(x, memo)
  File "/usr/lib/python3.6/copy.py", line 240, in _deepcopy_dict
    y[deepcopy(key, memo)] = deepcopy(value, memo)
  File "/usr/lib/python3.6/copy.py", line 180, in deepcopy
    y = _reconstruct(x, memo, *rv)
  File "/usr/lib/python3.6/copy.py", line 280, in _reconstruct
    state = deepcopy(state, memo)
  File "/usr/lib/python3.6/copy.py", line 150, in deepcopy
    y = copier(x, memo)
  File "/usr/lib/python3.6/copy.py", line 240, in _deepcopy_dict
    y[deepcopy(key, memo)] = deepcopy(value, memo)
  File "/usr/lib/python3.6/copy.py", line 180, in deepcopy
    y = _reconstruct(x, memo, *rv)
  File "/usr/lib/python3.6/copy.py", line 280, in _reconstruct
    state = deepcopy(state, memo)
  File "/usr/lib/python3.6/copy.py", line 150, in deepcopy
    y = copier(x, memo)
  File "/usr/lib/python3.6/copy.py", line 240, in _deepcopy_dict
    y[deepcopy(key, memo)] = deepcopy(value, memo)
  File "/usr/lib/python3.6/copy.py", line 169, in deepcopy
    rv = reductor(4)
TypeError: can't pickle _thread.RLock objects

这是问题代码：

    h, w = K.shape(input_image)[1], K.shape(input_image)[2]
    image_scale = K.cast(K.stack([h, w, h, w], axis=0), tf.float32)
    gt_boxes = KL.Lambda(lambda x: x / image_scale)(input_gt_boxes)

在添加此代码之前，我的模型可以正常工作并成功保存完整模型

Answer 1

因为我已经解决了我的问题，所以我将分享我的解决方案，就像标题所说的错误typeError: can't pickle thread rlock object显然是因为模型中有原始张量徘徊而发生的，在这种情况下，def是根据我的自定义生成的模型。

我要采取的解决方案是使一个包含计算的函数与k.shape有关，并在lambda层内部调用该函数。这是我采用的示例解决方案。

这是问题代码

h, w = K.shape(input_image)[1], K.shape(input_image)[2]
image_scale = K.cast(K.stack([h, w, h, w], axis=0), "float32")
gt_boxes = KL.lambda(lambda x: x/image_scale)(input_gt_boxes)

然后将代码移入函数

def gtBoxes(input_image, input_gt_boxes):
h, w = K.shape(input_image)[1], K.shape(input_image)[2]
image_scale = K.cast(K.stack([h, w, h, w], axis=0), "float32")
gt_boxes = input_gt_boxes/image_scale
return gt_boxes

在我的自定义模型中建立了内部def之后，我在lambda层内部将其称为

gt_boxes = KL.Lambda(lambda x: gtBoxes(*x))([input_image, input_gt_boxes])

我从TensorFlow GitHub问题中的一个问题中得到了这个解决方案，但是我采用了不同的方法，因为即使使用了与该问题中的解决方案相同的方法，仍然遇到该错误。

TypeError：无法腌制_thread.RLock对象，K.shape问题

1 个答案: