我的模型输出是这样的，<tf.Tensor: shape=(3,), dtype=float32, numpy=array([0.92, 0.2 , 0.77], dtype=float32)>>，但我想把数组中的最大值改为1，其他值改为0。如果有两个或两个以上的最大值，则应将其更改为零数组。
例如:
[0.92, 0.2 , 0.77] -> [1.0,0.0,0.0],
[0.92, 0.92 , 0.77] -> [0.0,0.0,0.0]
我知道如何通过np来生成它。argmax，但我想按keras来做。层，因为总结了之后的输出，想在二进制模式下做吗?
我已经做了这样的自定义层，但不幸的是不能编译它
class Amplifier(tf.keras.layers.Layer):
def __init__(self):
super(Amplifier, self).__init__()
# pattern 2D matrix
self.f = tf.constant(
[[1., 0., 0.],
[0., 1., 0.],
[0., 0., 1.]], dtype='float32')
def call(self, inputs, training=None, mask=None):
# return index of max value
x = tf.math.argmax(
inputs,
axis=None,
output_type=tf.dtypes.int32,
name=None)
# get factor from f constant as 1D matrix form
y = tf.reshape(tf.slice(self.f, [x, 0], [1, 3]), [3])
# multiply input on the pattern matrix
return tf.math.multiply(inputs, y)
我得到这个错误:
ValueError:尝试将'begin'转换为张量，失败。错误:形状必须是等号的，但是是1和0将形状0与其他形状合并。for '{{节点放大器/切片/打包}}=包[N=2, T=DT_INT32，轴=0](放大器/ArgMax，放大器/切片/打包/1)'，输入形状:[3]，[].
我不知道如何避免这个错误
我想你问的是你是否可以让你的输出是tf.one_hot格式(正确吗?)。如果您只想报告这个输出，那么您可以使用argmax和one_hot的组合。如果你想让它成为你网络中梯度计算的一部分，你需要一个数值稳定的。试试这样做:
import tensorflow as tf
from tensorflow.keras import layers
from tensorflow.keras.layers import Dense
class OneHotLayer(layers.Layer):
def __init__(self, num_labels=3, do_numerical=False):
super().__init__()
# large constant used in masking softmax
self._inf = 1e9
# how many categories we have
self.num_labels = num_labels
# if we need our `one_hot` to be numerically stable
self.do_numerical = do_numerical
# dense layer; the last layer of our network
self.probs = Dense(self.num_labels, activation="softmax")
# this is a numerically stable `one_hot` method.
# it looks for the max across rows, subtracts that from
# the original tensor (across rows) and exponentiates.
# this will make the largest value 1.0. Then we create a
# mask and zero out all other values (again, across rows)
# leaving us with a binary matrix.
def _numerical_one_hot(self, x):
m = tf.math.reduce_max(x, axis=1, keepdims=True)
e = tf.math.exp(x - m)
mask = tf.cast(tf.math.not_equal(e, 1.0), tf.float32)
x = x - self._inf * mask
return tf.nn.softmax(x, axis=1)
def call(self, x):
# do forward pass through last layer
x = self.probs(x)
# do we need numerical stability? If we do use the
# op we created. If not, then take the argmax across
# rows and then use `tf.one_hot`; return both
ohx = self._numerical_one_hot(x)
if self.do_numerical
else tf.one_hot(tf.math.argmax(x, axis=1), self.num_labels)
return x, ohx
:
# fake data
X = tf.random.normal([8, 10])
y = tf.random.uniform(
shape=[8,],
minval=0,
maxval=3,
dtype=tf.int64)
y = tf.one_hot(y, 3)
试验数值稳定性网络:
# network with stable one_hot
x_in = tf.keras.Input((10,))
x = Dense(25)(x_in)
x_probs, x_indices = OneHotLayer(3, True)(x)
# ^
# ------------------------------------|
# model
model = tf.keras.Model(x_in, [x_probs, x_indices])
probs, idxs = model(X)
# ^^^ this can be used in loss calc if you need it
print(probs)
# tf.Tensor(
# [[0.12873407 0.83047885 0.04078702]
# [0.22919412 0.1288479 0.641958 ]
# [0.27402356 0.35891128 0.36706516]
# [0.1328154 0.3546107 0.51257384]
# [0.5309519 0.10788985 0.36115825]
# [0.35019153 0.272698 0.37711048]
# [0.35740596 0.23807809 0.4045159 ]
# [0.13749316 0.72042704 0.14207976]],
# shape=(8, 3), # dtype=float32)
print(idxs)
# tf.Tensor(
# [[0. 1. 0.]
# [0. 0. 1.]
# [0. 0. 1.]
# [0. 0. 1.]
# [1. 0. 0.]
# [0. 0. 1.]
# [0. 0. 1.]
# [0. 1. 0.]],
# shape=(8, 3), dtype=float32)
测试内置单热网络:
# network using argmax and built-in one_hot
x_in = tf.keras.Input((10,))
x = Dense(25)(x_in)
x_probs, x_indices = OneHotLayer(3, False)(x)
# ^
# ------------------------------------|
# model
model = tf.keras.Model(x_in, [x_probs, x_indices])
probs, idxs = model(X)
print(probs)
# tf.Tensor(
# [[0.28931475 0.33777648 0.3729088 ]
# [0.25985113 0.532114 0.20803489]
# [0.4226228 0.21078317 0.36659405]
# [0.460703 0.3534157 0.18588138]
# [0.6028035 0.26571727 0.13147917]
# [0.1994377 0.4208928 0.37966955]
# [0.39812535 0.33319235 0.26868224]
# [0.13242716 0.47491995 0.3926528 ]],
# shape=(8, 3), dtype=float32)
print(idxs)
# tf.Tensor(
# [[0. 0. 1.]
# [0. 1. 0.]
# [1. 0. 0.]
# [1. 0. 0.]
# [1. 0. 0.]
# [0. 1. 0.]
# [1. 0. 0.]
# [0. 1. 0.]],
# shape=(8, 3), dtype=float32)