as_list() 未在 y_t_rank = len(y_t.shape.as_list()) 上的未知 TensorShape 上定义并且与指标相关 [英] as_list() is not defined on an unknown TensorShape on y_t_rank = len(y_t.shape.as_list()) and related to metrics

问题描述

TF 2.3.0.dev20200620

TF 2.3.0.dev20200620

对于带有 sigmoid 二进制输出的模型，我在 .fit(...) 期间遇到了这个错误.我使用 tf.data.Dataset 作为输入管道.奇怪的是它取决于指标:

I got this error during .fit(...) for a model with a sigmoid binary output. I used tf.data.Dataset as the input pipeline. The strange thing is it depends on the metric:

不工作:

model.compile(
    optimizer=tf.keras.optimizers.Adam(lr=1e-4, decay=1e-6),
    loss=tf.keras.losses.BinaryCrossentropy(),
    metrics=['accuracy']
)

工作:

model.compile(
    optimizer=tf.keras.optimizers.Adam(lr=1e-4, decay=1e-6),
    loss=tf.keras.losses.BinaryCrossentropy(),
    metrics=[tf.keras.metrics.BinaryAccuracy()]
)

但据我所知，准确性"应该没问题.事实上，使用 tf.keras.preprocessing.image_dataset_from_directory 而不是使用我自己的 tf.data.Dataset 自定义设置(如果需要可以提供)，不会出现这样的错误.这是教程 https://keras.io/examples/vision/image_classification_from_scratch 中的情况.

But as I understood, 'accuracy' should be fine. In fact, instead of using my own tf.data.Dataset custom setup (can be provided if needed), using tf.keras.preprocessing.image_dataset_from_directory give no such error. This is the case from tutorial https://keras.io/examples/vision/image_classification_from_scratch.

跟踪粘贴在下面.请注意，这与其他 2 个较旧的问题不同.它以某种方式涉及指标.

Trace is pasted below. Notice this is diff from other 2 older questions. it involves somehow the metrics.

值错误:在用户代码中:

ValueError: in user code:

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:806 train_function  *
    return step_function(self, iterator)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:796 step_function  **
    outputs = model.distribute_strategy.run(run_step, args=(data,))
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:1211 run
    return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2526 call_for_each_replica
    return self._call_for_each_replica(fn, args, kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2886 _call_for_each_replica
    return fn(*args, **kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:789 run_step  **
    outputs = model.train_step(data)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:759 train_step
    self.compiled_metrics.update_state(y, y_pred, sample_weight)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/compile_utils.py:388 update_state
    self.build(y_pred, y_true)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/compile_utils.py:319 build
    self._metrics, y_true, y_pred)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/nest.py:1139 map_structure_up_to
    **kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/nest.py:1235 map_structure_with_tuple_paths_up_to
    *flat_value_lists)]
/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/nest.py:1234 <listcomp>
    results = [func(*args, **kwargs) for args in zip(flat_path_list,
/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/nest.py:1137 <lambda>
    lambda _, *values: func(*values),  # Discards the path arg.
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/compile_utils.py:419 _get_metric_objects
    return [self._get_metric_object(m, y_t, y_p) for m in metrics]
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/compile_utils.py:419 <listcomp>
    return [self._get_metric_object(m, y_t, y_p) for m in metrics]
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/compile_utils.py:440 _get_metric_object
    y_t_rank = len(y_t.shape.as_list())
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/tensor_shape.py:1190 as_list
    raise ValueError("as_list() is not defined on an unknown TensorShape.")

ValueError: as_list() is not defined on an unknown TensorShape.

推荐答案

在使用准确度"指标时遇到了完全相同的问题.

Had exactly the same problem when using 'accuracy' metric.

我关注了https://github.com/tensorflow/tensorflow/issues/32912#issuecomment-550363802 示例:

def _fixup_shape(images, labels, weights):
    images.set_shape([None, None, None, 3])
    labels.set_shape([None, 19]) # I have 19 classes
    weights.set_shape([None])
    return images, labels, weights
dataset = dataset.map(_fixup_shape)

帮助我解决了问题.

但是，在我的例子中，不是像上面 kawingkelvin 那样使用一个 map 函数来加载和 set_shape，我需要使用两个 map 函数，因为 TF 代码中存在一些错误.

But, in my case, instead of using one map function, as kawingkelvin did above, to load and set_shape inside, I needed to use two map functions because of some errors in the TF code.

我的最终解决方案是使用以下顺序:dataset.batch.map(get_data).map(fix_shape).prefetch

The final solution for me was to use the following order: dataset.batch.map(get_data).map(fix_shape).prefetch

注意:批处理可以在 map(get_data) 之前和之后完成，具体取决于 get_data 函数的创建方式.Fix_shape 必须在之后完成.

NOTE: batch can be done both before and after map(get_data) depending on how your get_data function is created. Fix_shape must be done after.

这篇关于as_list() 未在 y_t_rank = len(y_t.shape.as_list()) 上的未知 TensorShape 上定义并且与指标相关的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！