Keras - 验证损失和准确性停留在 0
Keras - Validation Loss and Accuracy stuck at 0
我正在尝试为 Tensorflow keras 中的二元分类训练一个简单的 2 层全连接神经网络。我使用 sklearn 的 train_test_split().
将我的数据分成 80-20 的训练集和验证集
当我调用 model.fit(X_train, y_train, validation_data=[X_val, y_val]) 时，它显示所有时期的验证损失和准确性为 0，但它训练得很好。
此外，当我尝试在验证集上对其进行评估时，输出是非零的。
有人可以解释一下为什么我在验证时遇到这个 0 损失 0 准确度错误。感谢您的帮助。
这是此错误的完整示例代码 (MCVE)：https://colab.research.google.com/drive/1P8iCUlnD87vqtuS5YTdoePcDOVEKpBHr?usp=sharing
如果您使用 keras 而不是 tf.keras 一切正常。
使用tf.keras，我什至尝试了validation_data = [X_train, y_train]，这也给出了零精度。
这里有一个演示：
model.fit(X_train, y_train, validation_data=[X_train.to_numpy(), y_train.to_numpy()],
epochs=10, batch_size=64)
Epoch 1/10
8/8 [==============================] - 0s 6ms/step - loss: 0.7898 - accuracy: 0.6087 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00
Epoch 2/10
8/8 [==============================] - 0s 6ms/step - loss: 0.6710 - accuracy: 0.6500 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00
Epoch 3/10
8/8 [==============================] - 0s 5ms/step - loss: 0.6748 - accuracy: 0.6500 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00
Epoch 4/10
8/8 [==============================] - 0s 6ms/step - loss: 0.6716 - accuracy: 0.6370 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00
Epoch 5/10
8/8 [==============================] - 0s 6ms/step - loss: 0.6085 - accuracy: 0.6326 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00
Epoch 6/10
8/8 [==============================] - 0s 6ms/step - loss: 0.6744 - accuracy: 0.6326 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00
Epoch 7/10
8/8 [==============================] - 0s 6ms/step - loss: 0.6102 - accuracy: 0.6522 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00
Epoch 8/10
8/8 [==============================] - 0s 6ms/step - loss: 0.7032 - accuracy: 0.6109 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00
Epoch 9/10
8/8 [==============================] - 0s 5ms/step - loss: 0.6283 - accuracy: 0.6717 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00
Epoch 10/10
8/8 [==============================] - 0s 5ms/step - loss: 0.6120 - accuracy: 0.6652 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00
因此，fit 的 tensorflow 实施肯定存在一些问题。
我翻了一下源码，好像是负责validation_data的部分：
...
...
# Run validation.
if validation_data and self._should_eval(epoch, validation_freq):
val_x, val_y, val_sample_weight = (
data_adapter.unpack_x_y_sample_weight(validation_data))
val_logs = self.evaluate(
x=val_x,
y=val_y,
sample_weight=val_sample_weight,
batch_size=validation_batch_size or batch_size,
steps=validation_steps,
callbacks=callbacks,
max_queue_size=max_queue_size,
workers=workers,
use_multiprocessing=use_multiprocessing,
return_dict=True)
val_logs = {'val_' + name: val for name, val in val_logs.items()}
epoch_logs.update(val_logs)
内部调用 model.evaluate，因为我们已经确定 evaluate 工作正常，我意识到唯一的罪魁祸首可能是 unpack_x_y_sample_weight。
所以，我研究了实现：
def unpack_x_y_sample_weight(data):
"""Unpacks user-provided data tuple."""
if not isinstance(data, tuple):
return (data, None, None)
elif len(data) == 1:
return (data[0], None, None)
elif len(data) == 2:
return (data[0], data[1], None)
elif len(data) == 3:
return (data[0], data[1], data[2])
raise ValueError("Data not understood.")
这太疯狂了，但是如果您只传递一个元组而不是列表，由于 unpack_x_y_sample_weight 内部的检查，一切都可以正常工作。 （在这一步之后你的标签丢失了，并且数据以某种方式在 evaluate 中得到修复，所以你在没有合理标签的情况下进行训练，这似乎是一个错误，但文档明确指出要传递元组）
以下代码给出了正确的验证精度和损失：
model.fit(X_train, y_train, validation_data=(X_train.to_numpy(), y_train.to_numpy()),
epochs=10, batch_size=64)
Epoch 1/10
8/8 [==============================] - 0s 7ms/step - loss: 0.5832 - accuracy: 0.6696 - val_loss: 0.6892 - val_accuracy: 0.6674
Epoch 2/10
8/8 [==============================] - 0s 7ms/step - loss: 0.6385 - accuracy: 0.6804 - val_loss: 0.8984 - val_accuracy: 0.5565
Epoch 3/10
8/8 [==============================] - 0s 7ms/step - loss: 0.6822 - accuracy: 0.6391 - val_loss: 0.6556 - val_accuracy: 0.6739
Epoch 4/10
8/8 [==============================] - 0s 6ms/step - loss: 0.6276 - accuracy: 0.6609 - val_loss: 1.0691 - val_accuracy: 0.5630
Epoch 5/10
8/8 [==============================] - 0s 7ms/step - loss: 0.7048 - accuracy: 0.6239 - val_loss: 0.6474 - val_accuracy: 0.6326
Epoch 6/10
8/8 [==============================] - 0s 7ms/step - loss: 0.6545 - accuracy: 0.6500 - val_loss: 0.6659 - val_accuracy: 0.6043
Epoch 7/10
8/8 [==============================] - 0s 7ms/step - loss: 0.5796 - accuracy: 0.6913 - val_loss: 0.6891 - val_accuracy: 0.6435
Epoch 8/10
8/8 [==============================] - 0s 7ms/step - loss: 0.5915 - accuracy: 0.6891 - val_loss: 0.5307 - val_accuracy: 0.7152
Epoch 9/10
8/8 [==============================] - 0s 7ms/step - loss: 0.5571 - accuracy: 0.7000 - val_loss: 0.5465 - val_accuracy: 0.6957
Epoch 10/10
8/8 [==============================] - 0s 7ms/step - loss: 0.7133 - accuracy: 0.6283 - val_loss: 0.7046 - val_accuracy: 0.6413
因此，由于这似乎是一个 bug，我刚刚在 Tensorflow Github repo:
打开了一个相关问题
我正在尝试为 Tensorflow keras 中的二元分类训练一个简单的 2 层全连接神经网络。我使用 sklearn 的 train_test_split().
当我调用 model.fit(X_train, y_train, validation_data=[X_val, y_val]) 时，它显示所有时期的验证损失和准确性为 0，但它训练得很好。
此外，当我尝试在验证集上对其进行评估时，输出是非零的。
有人可以解释一下为什么我在验证时遇到这个 0 损失 0 准确度错误。感谢您的帮助。
这是此错误的完整示例代码 (MCVE)：https://colab.research.google.com/drive/1P8iCUlnD87vqtuS5YTdoePcDOVEKpBHr?usp=sharing
如果您使用
keras而不是tf.keras一切正常。使用
tf.keras，我什至尝试了validation_data = [X_train, y_train]，这也给出了零精度。
这里有一个演示：
model.fit(X_train, y_train, validation_data=[X_train.to_numpy(), y_train.to_numpy()],
epochs=10, batch_size=64)
Epoch 1/10
8/8 [==============================] - 0s 6ms/step - loss: 0.7898 - accuracy: 0.6087 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00
Epoch 2/10
8/8 [==============================] - 0s 6ms/step - loss: 0.6710 - accuracy: 0.6500 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00
Epoch 3/10
8/8 [==============================] - 0s 5ms/step - loss: 0.6748 - accuracy: 0.6500 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00
Epoch 4/10
8/8 [==============================] - 0s 6ms/step - loss: 0.6716 - accuracy: 0.6370 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00
Epoch 5/10
8/8 [==============================] - 0s 6ms/step - loss: 0.6085 - accuracy: 0.6326 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00
Epoch 6/10
8/8 [==============================] - 0s 6ms/step - loss: 0.6744 - accuracy: 0.6326 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00
Epoch 7/10
8/8 [==============================] - 0s 6ms/step - loss: 0.6102 - accuracy: 0.6522 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00
Epoch 8/10
8/8 [==============================] - 0s 6ms/step - loss: 0.7032 - accuracy: 0.6109 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00
Epoch 9/10
8/8 [==============================] - 0s 5ms/step - loss: 0.6283 - accuracy: 0.6717 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00
Epoch 10/10
8/8 [==============================] - 0s 5ms/step - loss: 0.6120 - accuracy: 0.6652 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00
因此，fit 的 tensorflow 实施肯定存在一些问题。
我翻了一下源码，好像是负责validation_data的部分：
...
...
# Run validation.
if validation_data and self._should_eval(epoch, validation_freq):
val_x, val_y, val_sample_weight = (
data_adapter.unpack_x_y_sample_weight(validation_data))
val_logs = self.evaluate(
x=val_x,
y=val_y,
sample_weight=val_sample_weight,
batch_size=validation_batch_size or batch_size,
steps=validation_steps,
callbacks=callbacks,
max_queue_size=max_queue_size,
workers=workers,
use_multiprocessing=use_multiprocessing,
return_dict=True)
val_logs = {'val_' + name: val for name, val in val_logs.items()}
epoch_logs.update(val_logs)
内部调用 model.evaluate，因为我们已经确定 evaluate 工作正常，我意识到唯一的罪魁祸首可能是 unpack_x_y_sample_weight。
所以，我研究了实现：
def unpack_x_y_sample_weight(data):
"""Unpacks user-provided data tuple."""
if not isinstance(data, tuple):
return (data, None, None)
elif len(data) == 1:
return (data[0], None, None)
elif len(data) == 2:
return (data[0], data[1], None)
elif len(data) == 3:
return (data[0], data[1], data[2])
raise ValueError("Data not understood.")
这太疯狂了，但是如果您只传递一个元组而不是列表，由于 unpack_x_y_sample_weight 内部的检查，一切都可以正常工作。 （在这一步之后你的标签丢失了，并且数据以某种方式在 evaluate 中得到修复，所以你在没有合理标签的情况下进行训练，这似乎是一个错误，但文档明确指出要传递元组）
以下代码给出了正确的验证精度和损失：
model.fit(X_train, y_train, validation_data=(X_train.to_numpy(), y_train.to_numpy()),
epochs=10, batch_size=64)
Epoch 1/10
8/8 [==============================] - 0s 7ms/step - loss: 0.5832 - accuracy: 0.6696 - val_loss: 0.6892 - val_accuracy: 0.6674
Epoch 2/10
8/8 [==============================] - 0s 7ms/step - loss: 0.6385 - accuracy: 0.6804 - val_loss: 0.8984 - val_accuracy: 0.5565
Epoch 3/10
8/8 [==============================] - 0s 7ms/step - loss: 0.6822 - accuracy: 0.6391 - val_loss: 0.6556 - val_accuracy: 0.6739
Epoch 4/10
8/8 [==============================] - 0s 6ms/step - loss: 0.6276 - accuracy: 0.6609 - val_loss: 1.0691 - val_accuracy: 0.5630
Epoch 5/10
8/8 [==============================] - 0s 7ms/step - loss: 0.7048 - accuracy: 0.6239 - val_loss: 0.6474 - val_accuracy: 0.6326
Epoch 6/10
8/8 [==============================] - 0s 7ms/step - loss: 0.6545 - accuracy: 0.6500 - val_loss: 0.6659 - val_accuracy: 0.6043
Epoch 7/10
8/8 [==============================] - 0s 7ms/step - loss: 0.5796 - accuracy: 0.6913 - val_loss: 0.6891 - val_accuracy: 0.6435
Epoch 8/10
8/8 [==============================] - 0s 7ms/step - loss: 0.5915 - accuracy: 0.6891 - val_loss: 0.5307 - val_accuracy: 0.7152
Epoch 9/10
8/8 [==============================] - 0s 7ms/step - loss: 0.5571 - accuracy: 0.7000 - val_loss: 0.5465 - val_accuracy: 0.6957
Epoch 10/10
8/8 [==============================] - 0s 7ms/step - loss: 0.7133 - accuracy: 0.6283 - val_loss: 0.7046 - val_accuracy: 0.6413
因此，由于这似乎是一个 bug，我刚刚在 Tensorflow Github repo:
打开了一个相关问题