keras自定义激活在特定条件下下降

keras custom activation to drop under certain conditions

我正尝试在我的自定义激活中删除小于 1 和大于 -1 的值,如下所示。

def ScoreActivationFromSigmoid(x, target_min=1, target_max=9) :
    condition = K.tf.logical_and(K.tf.less(x, 1), K.tf.greater(x, -1))
    case_true = K.tf.reshape(K.tf.zeros([x.shape[1] * x.shape[2]], tf.float32), shape=(K.tf.shape(x)[0], x.shape[1], x.shape[2]))
    case_false = x
    changed_x = K.tf.where(condition, case_true, case_false)

    activated_x = K.sigmoid(changed_x)
    score = activated_x * (target_max - target_min) + target_min
    return  score

数据类型有 3 个维度:batch_size x sequence_length x 特征数。

但是我遇到了这个错误

nvalidArgumentError: Inputs to operation activation_51/Select of type Select must have the same size and shape.  Input 0: [1028,300,64] != input 1: [1,300,64]
     [[{{node activation_51/Select}} = Select[T=DT_FLOAT, _class=["loc:@training_88/Adam/gradients/activation_51/Select_grad/Select_1"], _device="/job:localhost/replica:0/task:0/device:GPU:0"](activation_51/LogicalAnd, activation_51/Reshape, dense_243/add)]]
     [[{{node metrics_92/acc/Mean_1/_9371}} = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_473_metrics_92/acc/Mean_1", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]

我明白是什么问题了;自定义激活函数无法找到合适的输入批量大小。但是不知道怎么控制。

任何人都可以解决此问题或建议其他方法来替换某些条件下的某些元素值吗?

我在 运行 你的代码时得到的错误信息是:

ValueError: Cannot reshape a tensor with 19200 elements to shape [1028,300,64] (19737600 elements) for 'Reshape_8' (op: 'Reshape') with input shapes: [19200], [3] and with input tensors computed as partial shapes: input[1] = [1028,300,64].

问题应该是你不能将形状为 [x.shape[1] * x.shape[2]] 的张量重塑为 (K.tf.shape(x)[0] , x.shape[1], x.shape[2]).这是因为它们的元素数不同。

所以解决方案只是创建一个正确形状的零数组。 这一行:

case_true = K.tf.reshape(K.tf.zeros([x.shape[1] * x.shape[2]], tf.float32), shape=(K.tf.shape(x)[0], x.shape[1], x.shape[2]))

应替换为:

case_true = K.tf.reshape(K.tf.zeros([x.shape[0] * x.shape[1] * x.shape[2]], K.tf.float32), shape=(K.tf.shape(x)[0], x.shape[1], x.shape[2]))

或使用K.tf.zeros_like:

case_true = K.tf.zeros_like(x)

可行代码:

import keras.backend as K
import numpy as np

def ScoreActivationFromSigmoid(x, target_min=1, target_max=9) :
    condition = K.tf.logical_and(K.tf.less(x, 1), K.tf.greater(x, -1))
    case_true = K.tf.zeros_like(x)
    case_false = x
    changed_x = K.tf.where(condition, case_true, case_false)

    activated_x = K.tf.sigmoid(changed_x)
    score = activated_x * (target_max - target_min) + target_min
    return  score

with K.tf.Session() as sess:
    x = K.tf.placeholder(K.tf.float32, shape=(1028, 300, 64), name='x')
    score = sess.run(ScoreActivationFromSigmoid(x), feed_dict={'x:0':np.random.randn(1028, 300, 64)})

print(score)