我正在尝试在 Google Colab 中训练 CNN（也尝试使用 Tesla v100），并将 keras 后端设置为 float16。
tf.keras.backend.set_floatx('float16')
但是在使用 Conv2D 编译模型时会引发错误。
model = tf.keras.models.Sequential([
tf.keras.layers.Conv2D(16,(3,3), activation='relu', input_shape=(300,300,3)),
tf.keras.layers.MaxPool2D(2,2),
tf.keras.layers.Dense(256, activation='relu'),
tf.keras.layers.Dropout(.5),
tf.keras.layers.Dense(128, activation='relu'),
tf.keras.layers.Dropout(.5),
tf.keras.layers.Dense(1, activation='sigmoid')
])
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['acc'])
错误信息：
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-9-c764c0cc3aa3> in <module>()
9 ])
10
---> 11 model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['acc'])
7 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/checkpointable/base.py in _method_wrapper(self, *args, **kwargs)
440 self._setattr_tracking = False # pylint: disable=protected-access
441 try:
--> 442 method(self, *args, **kwargs)
443 finally:
444 self._setattr_tracking = previous_value # pylint: disable=protected-access
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py in compile(self, optimizer, loss, metrics, loss_weights, sample_weight_mode, weighted_metrics, target_tensors, distribute, **kwargs)
447 else:
448 weighted_loss = training_utils.weighted_masked_objective(loss_fn)
--> 449 output_loss = weighted_loss(y_true, y_pred, sample_weight, mask)
450
451 if len(self.outputs) > 1:
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training_utils.py in weighted(y_true, y_pred, weights, mask)
674 score_array = math_ops.reduce_sum(score_array)
675 weights = math_ops.reduce_sum(weights)
--> 676 score_array = math_ops.div_no_nan(score_array, weights)
677 return K.mean(score_array)
678
/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/dispatch.py in wrapper(*args, **kwargs)
178 """Call target, and fall back on dispatchers if there is a TypeError."""
179 try:
--> 180 return target(*args, **kwargs)
181 except (TypeError, ValueError):
182 # Note: convert_to_eager_tensor currently raises a ValueError, not a
/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/math_ops.py in div_no_nan(x, y, name)
1025 raise TypeError("x and y must have the same dtype, got %r != %r" %
1026 (x_dtype, y_dtype))
-> 1027 return gen_math_ops.div_no_nan(x, y, name=name)
1028
1029
/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/gen_math_ops.py in div_no_nan(x, y, name)
3020 # Add nodes to the TensorFlow graph.
3021 _, _, _op = _op_def_lib._apply_op_helper(
-> 3022 "DivNoNan", x=x, y=y, name=name)
3023 _result = _op.outputs[:]
3024 _inputs_flat = _op.inputs
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/op_def_library.py in _apply_op_helper(self, op_type_name, name, **keywords)
608 _SatisfiesTypeConstraint(base_type,
609 _Attr(op_def, input_arg.type_attr),
--> 610 param_name=input_name)
611 attrs[input_arg.type_attr] = attr_value
612 inferred_from[input_arg.type_attr] = input_name
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/op_def_library.py in _SatisfiesTypeConstraint(dtype, attr_def, param_name)
58 "allowed values: %s" %
59 (param_name, dtypes.as_dtype(dtype).name,
---> 60 ", ".join(dtypes.as_dtype(x).name for x in allowed_list)))
61
62
TypeError: Value passed to parameter 'x' has DataType float16 not in list of allowed values: float32, float64
但是，当我删除卷积层时，它会毫无问题地编译模型。
model = tf.keras.models.Sequential([
tf.keras.layers.Dense(256, activation='relu'),
tf.keras.layers.Dropout(.5),
tf.keras.layers.Dense(128, activation='relu'),
tf.keras.layers.Dropout(.5),
tf.keras.layers.Dense(1, activation='sigmoid')
])
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['acc'])
因此机器显然可以使用 float16，是否需要对 Keras 做任何特殊的事情才能使 Conv2D 在 float16 中工作？