Python 为卷积神经网络生成客户层，但TypeError提醒：float（）参数必须是字符串或数字，而不是'；尺寸'；
代码如下（部分省略了客户层模型）： 代码给了我一个错误：Python 为卷积神经网络生成客户层，但TypeError提醒：float（）参数必须是字符串或数字，而不是'；尺寸'；,python,tensorflow,keras,deep-learning,neural-network,Python,Tensorflow,Keras,Deep Learning,Neural Network,代码如下（部分省略了客户层模型）： 代码给了我一个错误： TypeError Traceback (most recent call last) <ipython-input-3-44798d695c82> in <module>() 190 # Add our STFTLayer as the first layer with patch_size 4 and stride 1 19
TypeError Traceback (most recent call last)
<ipython-input-3-44798d695c82> in <module>()
190 # Add our STFTLayer as the first layer with patch_size 4 and stride 1
191 model.add(STFTLayer(4,1,input_shape=(28,28,1),name='STFTLayer'))
--> 192 model.add(Conv2D(32, (1, 1)))
193 #model.add(Conv2D(32, (1, 1), input_shape=(28,28,1)))
194 model.add(Activation('relu'))
5 frames
/usr/local/lib/python3.6/dist-packages/keras/engine/sequential.py in add(self, layer)
180 self.inputs = network.get_source_inputs(self.outputs[0])
181 elif self.outputs:
--> 182 output_tensor = layer(self.outputs[0])
183 if isinstance(output_tensor, list):
184 raise TypeError('All layers in a Sequential model '
/usr/local/lib/python3.6/dist-packages/keras/engine/base_layer.py in __call__(self, inputs, **kwargs)
423 'You can build it manually via: '
424 '`layer.build(batch_input_shape)`')
--> 425 self.build(unpack_singleton(input_shapes))
426 self.built = True
427
/usr/local/lib/python3.6/dist-packages/keras/layers/convolutional.py in build(self, input_shape)
139 name='kernel',
140 regularizer=self.kernel_regularizer,
--> 141 constraint=self.kernel_constraint)
142 if self.use_bias:
143 self.bias = self.add_weight(shape=(self.filters,),
/usr/local/lib/python3.6/dist-packages/keras/legacy/interfaces.py in wrapper(*args, **kwargs)
89 warnings.warn('Update your `' + object_name + '` call to the ' +
90 'Keras 2 API: ' + signature, stacklevel=2)
---> 91 return func(*args, **kwargs)
92 wrapper._original_function = func
93 return wrapper
/usr/local/lib/python3.6/dist-packages/keras/engine/base_layer.py in add_weight(self, name, shape, dtype, initializer, regularizer, trainable, constraint)
241 if dtype is None:
242 dtype = self.dtype
--> 243 weight = K.variable(initializer(shape, dtype=dtype),
244 dtype=dtype,
245 name=name,
/usr/local/lib/python3.6/dist-packages/keras/initializers.py in __call__(self, shape, dtype)
207 scale /= max(1., fan_out)
208 else:
--> 209 scale /= max(1., float(fan_in + fan_out) / 2)
210 if self.distribution == 'normal':
211 # 0.879... = scipy.stats.truncnorm.std(a=-2, b=2, loc=0., scale=1.)
TypeError: float() argument must be a string or a number, not 'Dimension'
总之，使用导入keras的第一个代码版本不适用于我的客户层，但第二个代码版本适用于导入tensorflow.keras。我希望第一个代码版本也适用于匹配其他人的代码。需要你的帮助，谢谢 通过定义非训练参数函数并使用keras.layers.Lambda、tensorflow 1.x版构建顺序模型层，解决了自定义层问题
TypeError Traceback (most recent call last)
<ipython-input-3-44798d695c82> in <module>()
190 # Add our STFTLayer as the first layer with patch_size 4 and stride 1
191 model.add(STFTLayer(4,1,input_shape=(28,28,1),name='STFTLayer'))
--> 192 model.add(Conv2D(32, (1, 1)))
193 #model.add(Conv2D(32, (1, 1), input_shape=(28,28,1)))
194 model.add(Activation('relu'))
5 frames
/usr/local/lib/python3.6/dist-packages/keras/engine/sequential.py in add(self, layer)
180 self.inputs = network.get_source_inputs(self.outputs[0])
181 elif self.outputs:
--> 182 output_tensor = layer(self.outputs[0])
183 if isinstance(output_tensor, list):
184 raise TypeError('All layers in a Sequential model '
/usr/local/lib/python3.6/dist-packages/keras/engine/base_layer.py in __call__(self, inputs, **kwargs)
423 'You can build it manually via: '
424 '`layer.build(batch_input_shape)`')
--> 425 self.build(unpack_singleton(input_shapes))
426 self.built = True
427
/usr/local/lib/python3.6/dist-packages/keras/layers/convolutional.py in build(self, input_shape)
139 name='kernel',
140 regularizer=self.kernel_regularizer,
--> 141 constraint=self.kernel_constraint)
142 if self.use_bias:
143 self.bias = self.add_weight(shape=(self.filters,),
/usr/local/lib/python3.6/dist-packages/keras/legacy/interfaces.py in wrapper(*args, **kwargs)
89 warnings.warn('Update your `' + object_name + '` call to the ' +
90 'Keras 2 API: ' + signature, stacklevel=2)
---> 91 return func(*args, **kwargs)
92 wrapper._original_function = func
93 return wrapper
/usr/local/lib/python3.6/dist-packages/keras/engine/base_layer.py in add_weight(self, name, shape, dtype, initializer, regularizer, trainable, constraint)
241 if dtype is None:
242 dtype = self.dtype
--> 243 weight = K.variable(initializer(shape, dtype=dtype),
244 dtype=dtype,
245 name=name,
/usr/local/lib/python3.6/dist-packages/keras/initializers.py in __call__(self, shape, dtype)
207 scale /= max(1., fan_out)
208 else:
--> 209 scale /= max(1., float(fan_in + fan_out) / 2)
210 if self.distribution == 'normal':
211 # 0.879... = scipy.stats.truncnorm.std(a=-2, b=2, loc=0., scale=1.)
TypeError: float() argument must be a string or a number, not 'Dimension'
from __future__ import absolute_import, division, print_function
# TensorFlow and tf.keras
import tensorflow as tf
from tensorflow.keras import layers, models
import os
# Helper libraries
import numpy as np
import urllib.request
import gzip
# Custom layers starts here.
class STFTLayer(layers.Layer):
def __init__(self, patch_size, stride, **kwargs):
super(STFTLayer, self).__init__(**kwargs)
self.patch_size = patch_size
self.stride = stride
# TensorFlow uses this function internally to get the right
# shape for next layer in the model
# DO NOT EDIT
def compute_output_shape(self, input_shape):
mock_shape = (1, input_shape[1], input_shape[2], input_shape[3])
mock_data = tf.zeros(mock_shape)
mock_patches = tf.image.extract_image_patches(mock_data,
sizes=[1,self.patch_size,self.patch_size,1],strides=[1,self.stride,self.stride,1],rates=[1,1,1,1],padding='VALID')
op_shape = mock_patches.shape
return (input_shape[0], op_shape[1], op_shape[2], op_shape[3])
# TensorFlow uses the this function to save the layer when
# model.save is called
# DO NOT EDIT
def get_config(self):
config = super(STFTLayer,self).get_config()
config['patch_size'] = self.patch_size
config['stride'] = self.stride
return config
# Change this function to change how the sampler vectors look
def call(self, inputs):
# Get patches from the input batch of images
# code omitted here
###
return op
# Main code for modeling begins here
# Load MNIST datasets
def extract_data(filename, num_images):
with gzip.open(filename) as bytestream:
bytestream.read(16)
buf = bytestream.read(num_images*28*28)
data = np.frombuffer(buf, dtype=np.uint8).astype(np.float32)
data = (data / 255) - 0.5
data = data.reshape(num_images, 28, 28, 1)
return data
def extract_labels(filename, num_images):
with gzip.open(filename) as bytestream:
bytestream.read(8)
buf = bytestream.read(1 * num_images)
labels = np.frombuffer(buf, dtype=np.uint8)
return (np.arange(10) == labels[:, None]).astype(np.float32)
class MNIST:
def __init__(self):
if not os.path.exists("data"):
os.mkdir("data")
files = ["train-images-idx3-ubyte.gz",
"t10k-images-idx3-ubyte.gz",
"train-labels-idx1-ubyte.gz",
"t10k-labels-idx1-ubyte.gz"]
for name in files:
urllib.request.urlretrieve('http://yann.lecun.com/exdb/mnist/' + name, "data/"+name)
train_data = extract_data("data/train-images-idx3-ubyte.gz", 60000)
train_labels = extract_labels("data/train-labels-idx1-ubyte.gz", 60000)
self.test_data = extract_data("data/t10k-images-idx3-ubyte.gz", 10000)
self.test_labels = extract_labels("data/t10k-labels-idx1-ubyte.gz", 10000)
VALIDATION_SIZE = 5000
self.validation_data = train_data[:VALIDATION_SIZE, :, :, :]
self.validation_labels = train_labels[:VALIDATION_SIZE]
self.train_data = train_data[VALIDATION_SIZE:, :, :, :]
self.train_labels = train_labels[VALIDATION_SIZE:]
print(MNIST().train_data.shape)
print(MNIST().validation_data.shape)
train_images = MNIST().train_data
train_labels = MNIST().train_labels
test_images = MNIST().validation_data
test_labels = MNIST().validation_labels
MODEL_PATH = '/home/bo/Documents/Weibo/STFT_model/models/custom_layers'
# If saved model exists, load it
# If any changes are made to STFTLayer logic, remember
# to delete existing saved model file
if not os.path.isdir('/home/bo/Documents/Weibo/STFT_model/models/'):
os.makedirs('/home/bo/Documents/Weibo/STFT_model/models/')
if os.path.exists(MODEL_PATH):
model = keras.models.load_model(MODEL_PATH, custom_objects={'STFTLayer': STFTLayer})
model.summary()
# Otherwise create new model.
else:
model = models.Sequential()
# Add our STFTLayer as the first layer with patch_size 4 and stride 1
model.add(STFTLayer(4,1,input_shape=(28,28,1),name='STFTLayer'))
model.add(layers.Conv2D(32, (1, 1), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (1, 1), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (1, 1), activation='relu'))
model.add(layers.Flatten())
model.add(layers.Dense(64, activation='relu'))
#model.add(layers.Dense(10, activation='softmax'))
model.add(layers.Dense(10))
model.summary()
def fn(correct, predicted):
return tf.nn.softmax_cross_entropy_with_logits(labels=correct,
logits=predicted/1)
sgd = tf.keras.optimizers.SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss=fn,
optimizer='adamax',
metrics=['accuracy'])
model.fit(train_images, train_labels,
batch_size=128,
validation_data=(test_images, test_labels),
nb_epoch=10,
shuffle=True)
#model.compile(optimizer='adamax',loss='categorical_crossentropy',metrics=['accuracy'])
# Train model
#model.fit(train_images, train_labels, epochs=10, batch_size=128, shuffle=True)
# Save the model
model.save(MODEL_PATH)
test_loss, test_acc = model.evaluate(test_images, test_labels)