我一直在尝试在Keras中开发自定义Spatial RNN层。它应该是具有（1 * 3）* [1,0,0]的自定义内核的Conv2D层。它应该找到每个像素与其左侧像素之间的关系。下面是代码：
class SpatialRNN2D_Left(tf.keras.layers.Layer):
def __init__(self, rnn_radius, direction='all'):
super().__init__()
self.padding = "same"
self.kernel_switch_left = np.array([[1, 0, 0]])
def build(self, input_shape):
""
Build the class based on the input shape and the direction parameter. The required kernels are built as well.
Arguments:
input_shape: 4D tensor with shape: `1 + (rows, cols, channels)`.
Raises:
Nothing at the moment. But shall be added.
""
self.num_channel = int(input_shape[-1])
kernel_switch_left = self.kernel_switch_left
kernel_switch_left = np.repeat(kernel_switch_left[:, :, np.newaxis], int(self.num_channel), axis=-1)
kernel_switch_left = np.repeat(kernel_switch_left[:, :, :, np.newaxis], int(self.num_channel), axis=-1)
kernel_switch_left = K.constant(kernel_switch_left, dtype=tf.float32)
self.kernel_left = self.add_weight(
shape=[kernel_switch_left.shape[0], kernel_switch_left.shape[1], self.num_channel, self.num_channel],
initializer=tf.keras.initializers.Ones(), trainable=True) * self.hex_filter_left
super().build(input_shape)
@tf.function
def call(self, input_tensor, **kwargs):
"""
Calls the tensor for forward pass operation.
Arguments:
input_tensor: Since at the moment the layer only works with batch of 1 the input_tensor should have shape of
a 4D tensor with shape: `1 + (rows, cols, channels)`.
Returns:
4D tensor representative of the forward pass of the Spatial RNN layer with
shape: `batch_shape=1 + (rows, cols, filters)`.
Raises:
Nothing at the moment. But shall be added.
"""
input_tensor = K.cast(tf.identity(input_tensor), tf.float32)
res_sum = tf.identity(input_tensor)
tensor = tf.identity(input_tensor)
conv = tf.keras.backend.conv2d(x=tensor, kernel=self.kernel_left, strides=[1], padding=self.padding)
tensor = tf.nn.relu(conv)
res_sum += tensor
return res_sum
def compute_output_shape(self, input_shape):
"""
Compute output shape.
Arguments:
input_shape: 4D tensor with shape: `1 + (rows, cols, channels)`.
Returns:
4D tensor with shape: `batch_shape=1 + (rows, cols, channels)
"""
return input_shape[0], input_shape[1], input_shape[2], self.num_channel
对于正向传递（预测）它工作正常，但是当我尝试训练模型时，出现“ ValueError：没有为任何变量提供渐变：['spatial_rn_n2d__left / Variable：0']。”。这是训练代码：
image1 = np.array(range(0, 50, 2)).reshape([1, 5, 5, 1])
image1 = np.concatenate((image1, image1 + 50), axis=-1)
image2 = np.array(range(100, 150, 2)).reshape([1, 5, 5, 1])
image2 = np.concatenate((image2, image2 + 50), axis=-1)
# Setting up label arrays & dataset
label1_ch1 = np.array([[0, 52, 158, 172, 186],
[10, 82, 228, 242, 256],
[20, 112, 298, 312, 326],
[30, 142, 368, 382, 396],
[40, 172, 438, 452, 466]]).reshape((1, 5, 5, 1))
label1_ch2 = np.array([[50, 102, 208, 222, 236],
[60, 132, 278, 292, 306],
[70, 162, 348, 362, 376],
[80, 192, 418, 432, 446],
[90, 222, 488, 502, 516]]).reshape((1, 5, 5, 1))
label1 = np.concatenate((label1_ch1, label1_ch2), axis=-1)
label2_ch1 = np.array([[100, 352, 858, 872, 886],
[110, 382, 928, 942, 956],
[120, 412, 998, 1012, 1026],
[130, 442, 1068, 1082, 1096],
[140, 472, 1138, 1152, 1166]]).reshape((1, 5, 5, 1))
label2_ch2 = np.array([[150, 402, 908, 922, 936],
[160, 432, 978, 992, 1006],
[170, 462, 1048, 1062, 1076],
[180, 492, 1118, 1132, 1146],
[190, 522, 1188, 1202, 1216]]).reshape((1, 5, 5, 1))
label2 = np.concatenate((label2_ch1, label2_ch2), axis=-1)
label_dataset = np.concatenate((label1, label2), axis=0)
tf.keras.backend.clear_session()
x_in = tf.keras.layers.Input((5, 5, image1.shape[-1]))
y_out = SpatialRNN2D_Left(rnn_radius=2, direction='left')(x_in)
model = tf.keras.Model(inputs=x_in, outputs=y_out)
model.summary()
def test_train():
image_dataset = np.concatenate((image1, image2), axis=0)
model.compile(optimizer='Adam', loss='binary_crossentropy')
model.fit(x=image_dataset, y=label_dataset, batch_size=1, epochs=10)
test_img1_output = model.predict(image1)
print(test_img1_output[0,:,:,0])
print(test_img1_output[0,:,:,1])
if __name__ == '__main__':
test_forward_pass()
test_train()
我想知道如何解决该错误，以便可以在单层模型中训练该层。如果我从构建函数中删除* self.hex_filter_left，它将训练得很好，但不是我想要的。我该如何解决错误？有没有更好的方法来获取我想要的图层？
下面是一些错误日志。
Traceback (most recent call last):
ValueError: in user code:
C:\Users\behrooz.bajestani\Anaconda3\envs\tfmd_py3.7_tf2\lib\site-packages\tensorflow\python\keras\engine\training.py:571 train_function *
outputs = self.distribute_strategy.run(
C:\Users\behrooz.bajestani\Anaconda3\envs\tfmd_py3.7_tf2\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:951 run **
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
C:\Users\behrooz.bajestani\Anaconda3\envs\tfmd_py3.7_tf2\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2290 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
C:\Users\behrooz.bajestani\Anaconda3\envs\tfmd_py3.7_tf2\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2649 _call_for_each_replica
return fn(*args, **kwargs)
C:\Users\behrooz.bajestani\Anaconda3\envs\tfmd_py3.7_tf2\lib\site-packages\tensorflow\python\keras\engine\training.py:541 train_step **
self.trainable_variables)
C:\Users\behrooz.bajestani\Anaconda3\envs\tfmd_py3.7_tf2\lib\site-packages\tensorflow\python\keras\engine\training.py:1804 _minimize
trainable_variables))
C:\Users\behrooz.bajestani\Anaconda3\envs\tfmd_py3.7_tf2\lib\site-packages\tensorflow\python\keras\optimizer_v2\optimizer_v2.py:521 _aggregate_gradients
filtered_grads_and_vars = _filter_grads(grads_and_vars)
C:\Users\behrooz.bajestani\Anaconda3\envs\tfmd_py3.7_tf2\lib\site-packages\tensorflow\python\keras\optimizer_v2\optimizer_v2.py:1219 _filter_grads
([v.name for _, v in grads_and_vars],))
ValueError: No gradients provided for any variable: ['spatial_rn_n2d__left/Variable:0'].
感谢您的支持和关注。