In[0] 和 In[1] 必须具有兼容的批次尺寸：[64,32,32,128] 与 [128,32,32,64]
Posted
技术标签:
【中文标题】In[0] 和 In[1] 必须具有兼容的批次尺寸：[64,32,32,128] 与 [128,32,32,64]【英文标题】：In[0] and In[1] must have compatible batch dimensions: [64,32,32,128] vs. [128,32,32,64] 【发布时间】：2020-12-13 16:19:25 【问题描述】：我正在使用 tensorflow 和 keras(TensorFlow(+Keras2) 和 Python3（CUDA 10.0 和 Intel MKL-DNN）），我遇到了批处理尺寸不兼容的问题，但我不知道哪个部分出了问题。我将不胜感激任何帮助和建议。我使用的数据是 MNIST 和 USPS。 错误是这样的
Traceback (most recent call last):
File "/home/ubuntu/anaconda3/envs/tensorflow_p36/lib/python3.6/site-packages/tensorflow_core/python/client/session.py", line 1365, in _do_call
return fn(*args)
File "/home/ubuntu/anaconda3/envs/tensorflow_p36/lib/python3.6/site-packages/tensorflow_core/python/client/session.py", line 1350, in _run_fn
target_list, run_metadata)
File "/home/ubuntu/anaconda3/envs/tensorflow_p36/lib/python3.6/site-packages/tensorflow_core/python/client/session.py", line 1443, in _call_tf_sessionrun
run_metadata)
tensorflow.python.framework.errors_impl.InvalidArgumentError: 2 root error(s) found.
(0) Invalid argument: In[0] and In[1] must have compatible batch dimensions: [64,32,32,128] vs. [128,32,32,64]
[[node MatMul]]
[[Mean/_67]]
(1) Invalid argument: In[0] and In[1] must have compatible batch dimensions: [64,32,32,128] vs. [128,32,32,64]
[[node MatMul]]
0 successful operations.
0 derived errors ignored.
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "Deep_CORAL_Keras_MNIST.py", line 343, in <module>
model.fit(Xs, ys, Xt, yt)
File "Deep_CORAL_Keras_MNIST.py", line 255, in fit
feed_dict=feed_dict)
File "/home/ubuntu/anaconda3/envs/tensorflow_p36/lib/python3.6/site-packages/tensorflow_core/python/client/session.py", line 956, in run
run_metadata_ptr)
File "/home/ubuntu/anaconda3/envs/tensorflow_p36/lib/python3.6/site-packages/tensorflow_core/python/client/session.py", line 1180, in _run
feed_dict_tensor, options, run_metadata)
File "/home/ubuntu/anaconda3/envs/tensorflow_p36/lib/python3.6/site-packages/tensorflow_core/python/client/session.py", line 1359, in _do_run
run_metadata)
File "/home/ubuntu/anaconda3/envs/tensorflow_p36/lib/python3.6/site-packages/tensorflow_core/python/client/session.py", line 1384, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: 2 root error(s) found.
(0) Invalid argument: In[0] and In[1] must have compatible batch dimensions: [64,32,32,128] vs. [128,32,32,64]
[[node MatMul (defined at /home/ubuntu/anaconda3/envs/tensorflow_p36/lib/python3.6/site-packages/tensorflow_core/python/framework/ops.py:1748) ]]
[[Mean/_67]]
(1) Invalid argument: In[0] and In[1] must have compatible batch dimensions: [64,32,32,128] vs. [128,32,32,64]
[[node MatMul (defined at /home/ubuntu/anaconda3/envs/tensorflow_p36/lib/python3.6/site-packages/tensorflow_core/python/framework/ops.py:1748) ]]
0 successful operations.
0 derived errors ignored.
下面是代码
import tensorflow as tf
import numpy as np
import pandas as pd
from sklearn.metrics import log_loss
from tensorflow.python.framework import ops
from keras import backend as K
from keras.layers import Dense, Dropout, Activation, GaussianNoise, Flatten
from keras.layers import Conv2D, MaxPooling2D, MaxPool2D
from keras.layers.normalization import BatchNormalization
from keras.layers.advanced_activations import PReLU, ELU, LeakyReLU
K.set_image_data_format('channels_last')
N_CLASS = 10
def shuffle_aligned_list(data):
"""Shuffle arrays in a list by shuffling each array identically."""
idx = data[0].shape[0]
p = np.random.permutation(idx)
return [d[p] for d in data]
def batch_gen(data, batch_size, shuffle=True):
"""Generate batches of data.
Given a list of array-like objects, generate batches of a given
size by yielding a list of array-like objects corresponding to the
same slice of each input.
"""
if shuffle:
data = shuffle_aligned_list(data)
batch_count = 0
while True:
if batch_count * batch_size + batch_size >= len(data[0]):
batch_count = 0
if shuffle:
data = shuffle_aligned_list(data)
start = batch_count * batch_size
end = start + batch_size
batch_count += 1
yield [d[start:end] for d in data]
def val_batch_gen(data, batch_size):
"""Generate batches of data.
Given a list of array-like objects, generate batches of a given
size by yielding a list of array-like objects corresponding to the
same slice of each input.
"""
batch_count = 0
# while True:
nbatch = len(data[0]) // batch_size
if nbatch * batch_size < len(data[0]): nbatch += 1
for i in range(nbatch):
start = batch_count * batch_size
end = start + batch_size
batch_count += 1
yield [d[start:end] for d in data]
class DeepCoralNet(object):
def __init__(self, nfeatures=50, arch=[8, 'act'], coral_layer_idx=[1],
batch_size=16, supervised=False, confusion=1e4, confusion_incr=50, confusion_max=1e9,
val_data=None, validate_every=1,
activations='relu', epochs=1000, optimizer=None, noise=0.0, droprate=0.0, verbose=False):
self.batch_size = batch_size
self.epochs = epochs
self.validate_every = validate_every
self.supervised = supervised
self.verbose = verbose
if val_data is None:
self.validate_every = 0
else:
self.Xval = val_data[0]
self.yval = val_data[1]
self._build_model(nfeatures, arch, supervised, confusion, confusion_incr,
confusion_max, activations, noise, droprate, coral_layer_idx, optimizer)
self.sess = tf.Session()
K.set_session(self.sess)
self.sess.run(tf.global_variables_initializer())
def _coral_loss(self, layer_a, layer_b):
d = tf.cast(tf.shape(layer_a)[1], tf.float32)
# Source covariance
xm = layer_a - tf.reduce_mean(layer_a, 0, keep_dims=True)
xc = tf.matmul(tf.transpose(xm), xm) / self.batch_size
# Target covariance
xmt = layer_b - tf.reduce_mean(layer_b, 0, keep_dims=True)
xct = tf.matmul(tf.transpose(xmt), xmt) / self.batch_size
coral_loss = tf.reduce_sum(tf.multiply((xc - xct), (xc - xct)))
coral_loss /= 4 * d * d
return coral_loss
def _build_model(self, nfeatures, architecture, supervised, confusion, confusion_incr, confusion_max,
activations, noise, droprate, coral_layer_idx, optimizer):
# self.inp_a = tf.placeholder(tf.float32, shape=(None, nfeatures))
# self.inp_b = tf.placeholder(tf.float32, shape=(None, nfeatures))
self.inp_a = tf.placeholder(tf.float32, shape=(None, 32, 32, 3))
self.inp_b = tf.placeholder(tf.float32, shape=(None, 32, 32, 3))
self.labels_a = tf.placeholder(tf.float32, shape=(None, N_CLASS))
self.lr = tf.placeholder(tf.float32, [], name='lr')
nlayers = len(architecture)
layers_a = [self.inp_a]
layers_b = [self.inp_b]
for i, nunits in enumerate(architecture):
# print
# nunits,
# if i in coral_layer_idx: print
# '(CORAL)'
# else: print
if isinstance(nunits, int):
shared_layer = Dense(nunits, activation='linear')
elif nunits == 'noise':
shared_layer = GaussianNoise(noise)
elif nunits == 'bn':
shared_layer = BatchNormalization()
elif nunits == 'drop':
shared_layer = Dropout(droprate)
elif nunits == 'act':
if activations == 'prelu':
shared_layer = PReLU()
elif activations == 'elu':
shared_layer = ELU()
elif activations == 'leakyrelu':
shared_layer = LeakyReLU()
else:
shared_layer = Activation(activations)
elif nunits == 'block1_conv1':
shared_layer =Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv1')
elif nunits == 'block1_conv2':
shared_layer += Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv2')
elif nunits == 'block1_pool':
shared_layer += MaxPool2D((2, 2), strides=(2, 2), name='block1_pool')
layers_a += [shared_layer(layers_a[-1])]
layers_b += [shared_layer(layers_b[-1])]
layers_a += [Flatten()(layers_a[-1])]
layers_b += [Flatten()(layers_b[-1])]
output_layer = Dense(N_CLASS, activation='linear')
y_logits = output_layer(layers_a[-1])
b_logits = output_layer(layers_b[-1])
self.y_clf = Activation('sigmoid')(y_logits)
# Sum the losses from both branches...
self.xe_loss = tf.reduce_mean(
tf.nn.sigmoid_cross_entropy_with_logits(labels=self.labels_a, logits=y_logits))
self.coral_losses = []
for idx in coral_layer_idx:
self.coral_losses += [self._coral_loss(layers_a[idx], layers_b[idx])]
self.coral_losses += [self._coral_loss(y_logits, b_logits)]
self.domain_loss = tf.reduce_sum(self.coral_losses)
self.confusion = tf.Variable(float(confusion), trainable=False, dtype=tf.float32)
conf_incr = tf.cond(self.confusion < confusion_max, lambda: float(confusion_incr), lambda: 0.)
self.increment_confusion = tf.assign(self.confusion, self.confusion + conf_incr)
self.domain_loss = self.confusion * self.domain_loss
self.total_loss = tf.add(self.domain_loss, self.xe_loss)
if supervised:
self.labels_b = tf.placeholder(tf.float32, shape=(None, 1))
self.bloss = tf.reduce_mean(
tf.nn.sigmoid_cross_entropy_with_logits(labels=self.labels_b, logits=b_logits))
self.total_loss = tf.add(self.total_loss, self.bloss)
if optimizer is None:
self.train_step = tf.train.MomentumOptimizer(self.lr, 0.9)
else:
self.train_step = optimizer
self.train_step = self.train_step.minimize(self.total_loss)
def predict_proba(self, X, batch_size=None):
if batch_size is None: batch_size = self.batch_size
yprobs = np.zeros((X.shape[0]), N_CLASS, dtype=float)
idx = np.arange(X.shape[0])
vbatch = val_batch_gen([idx, X], batch_size)
for i, (thisidx, thisX) in enumerate(vbatch):
yprobs[thisidx] = self.sess.run(self.y_clf,
feed_dict=self.inp_a: thisX, K.learning_phase(): 0).flatten()
return yprobs
def evaluate(self, X, y, batch_size=None):
yprobs = self.predict_proba(X, batch_size)
acc = np.mean(np.equal(np.argmax(self.predict_proba(X, batch_size).astype("float32"), axis=1),
np.argmax(y, axis=1)))
return log_loss(y, yprobs), acc
def fit(self, Xs, ys, Xt, yt=None, Xval=None, yval=None,
epochs=None, batch_size=None, verbose=None):
if epochs is None: epochs = self.epochs
if batch_size is None: batch_size = self.batch_size
if Xval is None:
Xval = self.Xval
yval = self.yval
if verbose is None: verbose = self.verbose
S_batches = batch_gen([Xs, ys], batch_size=batch_size)
if yt is None: yt = np.ones(Xt.shape[0])
T_batches = batch_gen([Xt, yt], batch_size=batch_size)
self.history = 'source_loss': [], 'target_loss': [], 'val_loss': [], 'domain_loss': []
for i in range(epochs):
p = i / float(epochs)
lr = 0.01 / (1 + 10. * p) ** 0.75
Xsource, ysource = next(S_batches)#.next()
Xtarget, ytarget = next(T_batches)#.next()
feed_dict = self.inp_a: Xsource, self.inp_b: Xtarget,
# self.labels_a: ysource.reshape(-1, 1), K.learning_phase(): 1,
self.labels_a: ysource, K.learning_phase(): 1,
self.lr: lr
if self.supervised:
feed_dict[self.labels_b] = ytarget #.reshape(-1, 1)
# train
_, _, confusion, xeloss, dloss, tloss = self.sess.run([
self.train_step,
self.increment_confusion,
self.confusion,
self.xe_loss,
self.domain_loss,
self.total_loss],
feed_dict=feed_dict)
if self.validate_every > 0 and i % self.validate_every == 0:
if i == 0:
print ('Epoch confusion dloss tloss sloss tloss vloss')
self.history['source_loss'] += [self.evaluate(Xs, ys)]
self.history['target_loss'] += [self.evaluate(Xt, yt)]
self.history['val_loss'] += [self.evaluate(Xval, yval)]
self.history['domain_loss'] += [dloss]
print (':04d :.2f :.4E :.4f :.5f :.5f :.5f '.format(i, confusion, dloss, tloss,
self.history['source_loss'][-1],
self.history['target_loss'][-1],
self.history['val_loss'][-1]))
print(':04d :.2f :.4E :.4f :.5f :.5f :.5f '.format(i, self.evaluate(Xs, ys)[1],
self.evaluate(Xt, yt)[1],
self.evaluate(Xval, yval)[1]))
# input data
from tensorflow.examples.tutorials.mnist import input_data
def return_mnist(path_train, path_test):
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
mnist_train = np.reshape(np.load(path_train), (55000, 32, 32, 1))
mnist_train = np.reshape(mnist_train, (55000, 32, 32, 1))
mnist_train = mnist_train.astype(np.float32)
mnist_test = np.reshape(np.load(path_test), (10000, 32, 32, 1)).astype(
np.float32)
mnist_test = np.reshape(mnist_test, (10000, 32, 32, 1))
mnist_train = np.concatenate([mnist_train, mnist_train, mnist_train], 3)
mnist_test = np.concatenate([mnist_test, mnist_test, mnist_test], 3)
return mnist_train, mnist_test, mnist.train.labels, mnist.test.labels
path_mnist_train = '/home/miles/atda-master/train_mnist_32x32.npy'
path_mnist_test = '/home/miles/atda-master/test_mnist_32x32.npy'
import cv2
import pickle as pkl
def __resize_array_images(array_images, size):
new_array = []
for i in range(len(array_images)):
img = cv2.resize( array_images[i], (size, size), interpolation = cv2.INTER_CUBIC )
new_array.append( img )
return np.array(new_array)
path = '/home/miles/atda-master/usps.h5'
import h5py
with h5py.File(path, 'r') as hf:
train = hf.get('train')
X_tr = train.get('data')[:]
y_tr = train.get('target')[:]
test = hf.get('test')
X_te = test.get('data')[:]
y_te = test.get('target')[:]
X_tr = np.reshape(X_tr, [X_tr.shape[0], 16, 16, 1])
X_tr = __resize_array_images(X_tr, 32)
X_tr = np.expand_dims(X_tr, -1)
X_tr = np.concatenate([X_tr, X_tr, X_tr], 3)
X_te = np.reshape(X_te, [X_te.shape[0], 16, 16, 1])
X_te = __resize_array_images(X_te, 32)
X_te = np.expand_dims(X_te, -1)
X_te = np.concatenate([X_te, X_te, X_te], 3)
y_tr = tf.keras.utils.to_categorical(y_tr, 10)
y_te = tf.keras.utils.to_categorical(y_te, 10)
Xt = X_tr
yt = y_tr
Xv = X_te
yv = y_te
_, mnist_test , _, mnist_test_label = return_mnist(path_mnist_train, path_mnist_test)
from sklearn.model_selection import train_test_split
Xs, _, ys, _ = train_test_split(
mnist_test, mnist_test_label, test_size=0.3)
opt = tf.train.MomentumOptimizer(1e-3, 0.9)
K.set_image_data_format('channels_last')
model = DeepCoralNet(nfeatures=Xs.shape[1],arch=['block1_conv1'], val_data=(Xv, yv),epochs=10000, batch_size=128, validate_every=100,
optimizer=opt, activations='leakyrelu')
model.fit(Xs, ys, Xt, yt)
vloss_grl = model.evaluate(Xv, yv)
【问题讨论】：
问题出现在哪一行？ 错误告诉你需要做什么：确保In[0]和In[1]具有相同的尺寸。
另外，请将您的代码压缩为minimal reproducible example。 SO 上的人都是志愿者，你期望每个人都花时间阅读不相关的代码是不合理的。
谢谢。我只是不明白为什么输入有不同的尺寸。这个错误发生在哪里
【参考方案1】：
您在matmul 之前执行transpose 操作。即tf.matmul(tf.transpose(xm), xm) 在您的代码中，这就是您的维度被洗牌的原因。能否请您参考这个tf.linalg.matmul tensorflow 文档。
重现问题的代码：
import tensorflow as tf
a = tf.constant([1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], shape=[2, 3, 2])
print(a)
b = tf.constant([1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], shape=[2, 3, 2])
print(b)
x = tf.matmul(a, b)
print(x)
输出 -
tf.Tensor(
[[[ 1 2]
[ 3 4]
[ 5 6]]
[[ 7 8]
[ 9 10]
[11 12]]], shape=(2, 3, 2), dtype=int32)
tf.Tensor(
[[[ 1 2]
[ 3 4]
[ 5 6]]
[[ 7 8]
[ 9 10]
[11 12]]], shape=(2, 3, 2), dtype=int32)
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
<ipython-input-18-8f20ea7be877> in <module>()
7 print(b)
8
----> 9 x = tf.matmul(a, b)
10 print(x)
4 frames
/usr/local/lib/python3.6/dist-packages/six.py in raise_from(value, from_value)
InvalidArgumentError: In[0] mismatch In[1] shape: 2 vs. 3: [2,3,2] [2,3,2] 0 0 [Op:BatchMatMulV2]
在任何转置之后，输入必须是秩 >= 2 的张量，其中内部 2 维指定有效的矩阵乘法维数。
固定代码：
import tensorflow as tf
a = tf.constant([1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], shape=[2, 3, 2])
print(a)
b = tf.constant([1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], shape=[2, 2, 3])
print(b)
x = tf.matmul(a, b)
print(x)
输出 -
tf.Tensor(
[[[ 1 2]
[ 3 4]
[ 5 6]]
[[ 7 8]
[ 9 10]
[11 12]]], shape=(2, 3, 2), dtype=int32)
tf.Tensor(
[[[ 1 2 3]
[ 4 5 6]]
[[ 7 8 9]
[10 11 12]]], shape=(2, 2, 3), dtype=int32)
tf.Tensor(
[[[ 9 12 15]
[ 19 26 33]
[ 29 40 51]]
[[129 144 159]
[163 182 201]
[197 220 243]]], shape=(2, 3, 3), dtype=int32)
【讨论】：
你能帮忙***.com/questions/68225332/…吗？以上是关于In[0] 和 In[1] 必须具有兼容的批次尺寸：[64,32,32,128] 与 [128,32,32,64]的主要内容，如果未能解决你的问题，请参考以下文章
AJAX 到 MySQL WHERE IN ($_GET) 请求。排除某些结果