python-3.x - 评估 tf.keras.model 输出之间的成对距离

Question

我正在尝试在 tensorflow 中创建自定义损失函数。我正在使用tensorflow v2.0.rc0来运行代码。以下是代码和函数 min_dist_loss 计算神经网络输出之间的成对损失。这是代码

def min_dist_loss(_, y_pred):
    distances = []
    for i in range(0, 16):
        for j in range(i + 1, 16):
            distances.append(tf.linalg.norm(y_pred[i] - y_pred[j]))
    return -tf.reduce_min(distances)

模块正在初始化和编译，如下

import tensorflow as tf
from tensorboard.plugins.hparams import api as hp

HP_NUM_UNITS = hp.HParam('num_units', hp.Discrete([6, 7]))
HP_OPTIMIZER = hp.HParam('optimizer', hp.Discrete(['adam', 'sgd']))

METRIC_ACCURACY = 'accuracy'

with tf.summary.create_file_writer('logs\hparam_tuning').as_default():
    hp.hparams_config(
        hparams=[HP_NUM_UNITS, HP_OPTIMIZER],
        metrics=[hp.Metric(METRIC_ACCURACY, display_name='Accuracy')]
    )

def train_test_model(logdir, hparams):
    weight1 = np.random.normal(loc=0.0, scale=0.01, size=[4, hparams[HP_NUM_UNITS]])
    init1 = tf.constant_initializer(weight1)
    weight2 = np.random.normal(loc=0.0, scale=0.01, size=[hparams[HP_NUM_UNITS], 7])
    init2 = tf.constant_initializer(weight2)
    model = tf.keras.models.Sequential([
        # tf.keras.layers.Flatten(),
        tf.keras.layers.Dense(hparams[HP_NUM_UNITS], activation=tf.nn.sigmoid, kernel_initializer=init1),
        tf.keras.layers.Dense(7, activation=tf.nn.sigmoid, kernel_initializer=init2) if hparams[HP_NUM_UNITS] == 6 else
        None,
    ])
    model.compile(
        optimizer=hparams[HP_OPTIMIZER],
        loss=min_dist_loss,
        # metrics=['accuracy'],
    )
    x_train = [list(k) for k in itertools.product([0, 1], repeat=4)]
    shuffle(x_train)
    x_train = 2 * np.array(x_train) - 1
    model.fit(
        x_train, epochs=1, batch_size=16,
        callbacks=[
            tf.keras.callbacks.TensorBoard(logdir),
            hp.KerasCallback(logdir, hparams)
        ],
    )

现在，由于 min_dist_loss 中的张量对象 y_pred 是形状 [?, 7] 的对象，因此使用 i 进行索引 抛出以下错误:

Traceback (most recent call last):
  File "/home/pc/Documents/user/code/keras_tensorflow/src/try1.py", line 95, in <module>
    run('logs\hparam_tuning' + run_name, hparams)
  File "/home/pc/Documents/user/code/keras_tensorflow/src/try1.py", line 78, in run
    accuracy = train_test_model(run_dir, hparams)
  File "/home/pc/Documents/user/code/keras_tensorflow/src/try1.py", line 66, in train_test_model
    hp.KerasCallback(logdir, hparams)
  File "/home/pc/Documents/user/code/keras_tensorflow/venv/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training.py", line 734, in fit
    use_multiprocessing=use_multiprocessing)
  File "/home/pc/Documents/user/code/keras_tensorflow/venv/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_v2.py", line 324, in fit
    total_epochs=epochs)
  File "/home/pc/Documents/user/code/keras_tensorflow/venv/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_v2.py", line 123, in run_one_epoch
    batch_outs = execution_function(iterator)
  File "/home/pc/Documents/user/code/keras_tensorflow/venv/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_v2_utils.py", line 86, in execution_function
    distributed_function(input_fn))
  File "/home/pc/Documents/user/code/keras_tensorflow/venv/lib/python3.6/site-packages/tensorflow_core/python/eager/def_function.py", line 427, in __call__
    self._initialize(args, kwds, add_initializers_to=initializer_map)
  File "/home/pc/Documents/user/code/keras_tensorflow/venv/lib/python3.6/site-packages/tensorflow_core/python/eager/def_function.py", line 370, in _initialize
    *args, **kwds))
  File "/home/pc/Documents/user/code/keras_tensorflow/venv/lib/python3.6/site-packages/tensorflow_core/python/eager/function.py", line 1847, in _get_concrete_function_internal_garbage_collected
    graph_function, _, _ = self._maybe_define_function(args, kwargs)
  File "/home/pc/Documents/user/code/keras_tensorflow/venv/lib/python3.6/site-packages/tensorflow_core/python/eager/function.py", line 2147, in _maybe_define_function
    graph_function = self._create_graph_function(args, kwargs)
  File "/home/pc/Documents/user/code/keras_tensorflow/venv/lib/python3.6/site-packages/tensorflow_core/python/eager/function.py", line 2038, in _create_graph_function
    capture_by_value=self._capture_by_value),
  File "/home/pc/Documents/user/code/keras_tensorflow/venv/lib/python3.6/site-packages/tensorflow_core/python/framework/func_graph.py", line 915, in func_graph_from_py_func
    func_outputs = python_func(*func_args, **func_kwargs)
  File "/home/pc/Documents/user/code/keras_tensorflow/venv/lib/python3.6/site-packages/tensorflow_core/python/eager/def_function.py", line 320, in wrapped_fn
    return weak_wrapped_fn().__wrapped__(*args, **kwds)
  File "/home/pc/Documents/user/code/keras_tensorflow/venv/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_v2_utils.py", line 73, in distributed_function
    per_replica_function, args=(model, x, y, sample_weights))
  File "/home/pc/Documents/user/code/keras_tensorflow/venv/lib/python3.6/site-packages/tensorflow_core/python/distribute/distribute_lib.py", line 760, in experimental_run_v2
    return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
  File "/home/pc/Documents/user/code/keras_tensorflow/venv/lib/python3.6/site-packages/tensorflow_core/python/distribute/distribute_lib.py", line 1787, in call_for_each_replica
    return self._call_for_each_replica(fn, args, kwargs)
  File "/home/pc/Documents/user/code/keras_tensorflow/venv/lib/python3.6/site-packages/tensorflow_core/python/distribute/distribute_lib.py", line 2132, in _call_for_each_replica
    return fn(*args, **kwargs)
  File "/home/pc/Documents/user/code/keras_tensorflow/venv/lib/python3.6/site-packages/tensorflow_core/python/autograph/impl/api.py", line 292, in wrapper
    return func(*args, **kwargs)
  File "/home/pc/Documents/user/code/keras_tensorflow/venv/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_v2_utils.py", line 264, in train_on_batch
    output_loss_metrics=model._output_loss_metrics)
  File "/home/pc/Documents/user/code/keras_tensorflow/venv/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_eager.py", line 311, in train_on_batch
    output_loss_metrics=output_loss_metrics))
  File "/home/pc/Documents/user/code/keras_tensorflow/venv/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_eager.py", line 252, in _process_single_batch
    training=training))
  File "/home/pc/Documents/user/code/keras_tensorflow/venv/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_eager.py", line 166, in _model_loss
    per_sample_losses = loss_fn.call(targets[i], outs[i])
IndexError: list index out of range

<小时/>

如何计算此设置中的最小距离？任何帮助表示赞赏。另外，如果代码的其他部分有错误，欢迎指出。我刚开始在 tensorflow 上使用 keras。

Answer 1

Keras 也希望您提供真实的标签。由于您正在定义自己的损失函数并且没有使用真正的标签，因此您可以传递一些垃圾标签。例如:np.arange(16)。

如下更改您的model.fit，它应该可以工作

model.fit(
    x_train, np.arange(x_train.shape[0]), epochs=1, batch_size=16,
    callbacks=[
        tf.keras.callbacks.TensorBoard(logdir),
        hp.KerasCallback(logdir, hparams)
    ],
)