一般来说是ML和TensorFlow的新手。我尝试在train_step函数中运行此行（t_loss = loss_object（标签，预测））时遇到此问题。
我觉得我缺少了一些小巧而愚蠢的东西！检查了其他解决方案，并且从TF的较旧版本或语法和结构中可以得到的信息有所不同。下面的代码段是可执行的。只是觉得像谷歌搜索后我不够了解。任何帮助表示赞赏。
收到错误
ValueError: Shape mismatch: The shape of labels (received (30,)) should equal the shape of logits except for the last dimension (received (2, 10)).
我正在跟踪本文，并在可能的情况下添加我自己的内容。GCP TF sample writeup'
import tensorflow as tf
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from __future__ import unicode_literals
from tensorflow.keras.layers import Dense, Flatten, Conv2D
from tensorflow.keras import Model
from tensorflow.keras import backend as K;
import nltk
import numpy as np
import pandas as pd
from sklearn.preprocessing import LabelEncoder
from nltk.stem.lancaster import LancasterStemmer
from nltk.stem.porter import PorterStemmer
from nltk.corpus import stopwords
#try sklearn
from sklearn.model_selection import train_test_split
EPOCHS = 10
# staging and vars
data=pd.read_csv('../rando.csv')
data = data[pd.notnull(data['utext'])]
data=data[data.type != 'None']
# encode unique values of the types
le = LabelEncoder()
data['type'] = le.fit_transform(data['type'])
training_data = []
testTrain_data = []
# create a dictionary of data based on type
for index,row in data.iterrows():
training_data.append({"class":row["type"], "sentence":row["fulltext"]})
words = []
classes = []
documents= []
not_required= ['?']
# create our training data
training = []
output = []
lanStemmer = LancasterStemmer()
def stemDocWord(words=words, classes=classes):
# loop through each sentence in our training data
for pattern in training_data:
# tokenize each word in the sentence
w = nltk.word_tokenize(pattern['sentence'])
# add to our words list
words.extend(w)
documents.append((w, pattern['class']))
# add to our classes list
if pattern['class'] not in classes:
classes.append(pattern['class'])
# stem and lower each word and remove duplicates
stemmer = PorterStemmer()
words = [stemmer.stem(w.lower()) for w in words if w not in not_required]
words = list(set(words))
# remove duplicates
classes = list(set(classes))
print(len(documents), "documents")
def listWordTokensForPattern():
# create an empty array for our output
output_empty = [0] * len(classes)
# training set, bag of words for each sentence
for doc in documents:
# initialize our bag of words
bag = []
# list of tokenized words for the pattern
pattern_words = doc[0]
# stem each word
pattern_words = [lanStemmer.stem(word.lower()) for word in pattern_words]
# create our bag of words array
for w in words:
bag.append(1) if w in pattern_words else bag.append(0)
training.append(bag)
# output is a '0' for each tag and '1' for current tag
output_row = list(output_empty)
output_row[classes.index(doc[1])] = 1
output.append(output_row)
print("# output", len(output))
print("# training", len(training))
# og training function
stemDocWord()
listWordTokensForPattern()
X = np.array(training)
y = np.array(output)
print(X.shape)
x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=23)
x_train, x_test = x_train / 255.0, x_test / 255.0
# Add a channels dimension e.g. (60000, 28, 28) => (60000, 28, 28, 1)
x_train = x_train[..., tf.newaxis, tf.newaxis]
x_test = x_test[..., tf.newaxis, tf.newaxis]
train_ds = tf.data.Dataset.from_tensor_slices((x_train, y_train)).shuffle(100).batch(2)
test_ds = tf.data.Dataset.from_tensor_slices((x_test, y_test)).batch(2)
print(x_train)
print(K.image_data_format())
# inputs_ = tf.compat.v1.placeholder(tf.float32, [None, 32, 32, 3])
# inputs_ = tf.Variable(tf.ones(shape=(0 ,32, 32, 3)), name="inputs_")
class CustomModel(Model):
def __init__(self):
super(CustomModel, self).__init__()
self.conv1 = Conv2D(2, 1,activation='relu')#, input_shape=x_train.shape)#x_train.shape())
self.flatten = Flatten()
self.d1 = Dense(128, activation='relu')
self.d2 = Dense(10, activation='softmax')
def call(self, x):
x = self.conv1(x)
x = self.flatten(x)
x = self.d1(x)
return self.d2(x)
model = CustomModel()
loss_object = tf.keras.losses.SparseCategoricalCrossentropy(reduction='none')
optimizer = tf.keras.optimizers.Adam()
train_loss = tf.keras.metrics.Mean(name='train_loss')
train_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='train_accuracy')
test_loss = tf.keras.metrics.Mean(name='test_loss')
test_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='test_accuracy')
@tf.function
def train_step(images, labels):
with tf.GradientTape() as tape:
predictions = model(images)
loss = loss_object(labels, predictions)
gradients = tape.gradient(loss, model.trainable_variables)
optimizer.apply_gradients(zip(gradients, model.trainable_variables))
train_loss(loss)
train_accuracy(labels, predictions)
@tf.function
def test_step(images, labels):
predictions = model(images)
t_loss = loss_object(labels, predictions)
test_loss(t_loss)
test_accuracy(labels, predictions)
for epoch in range(EPOCHS):
for images, labels in train_ds:
train_step(images, labels)
for test_images, test_labels in test_ds:
test_step(test_images, test_labels)
template = 'Epoch {}, Loss: {}, Accuracy: {}, Test Loss: {}, Test Accuracy: {}'
print (template.format(epoch+1,
train_loss.result(),
train_accuracy.result()*100,
test_loss.result(),
test_accuracy.result()*100))
# Save the weights
model.save_weights('fashion_mnist_weights')
CSV文件看起来与此类似
utext，fulltext，type
t1，“一些随机句子”，type1
t2，“其他随机句子”，type2
t3，“一些随机文本”，type3
以下是我对我的第一条评论的看法：
WARNING:tensorflow:Entity <function train_step at 0x000001E9480B11E0> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, 'export AUTOGRAPH_VERBOSITY=10') and attach the full output. Cause: converting <function train_step at 0x000001E9480B11E0>: AttributeError: module 'gast' has no attribute 'Str'
WARNING:tensorflow:Entity <bound method CustomModel.call of <__main__.CustomModel object at 0x000001E947C9D358>> could not be transformed and will be executed as-is. Please report this to
the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, 'export AUTOGRAPH_VERBOSITY=10') and attach the full output. Cause: converting <bound method CustomModel.call of <__main__.CustomModel object at 0x000001E947C9D358>>: AssertionError: Bad argument number for Name: 3, expecting 4
2020-02-29 12:14:46.018316: W tensorflow/core/framework/cpu_allocator_impl.cc:81] Allocation of 2683371520 exceeds 10% of system memory.
2020-02-29 12:14:47.459793: W tensorflow/core/framework/cpu_allocator_impl.cc:81] Allocation of 2683371520 exceeds 10% of system memory.
2020-02-29 12:14:47.869789: W tensorflow/core/framework/cpu_allocator_impl.cc:81] Allocation of 2683371520 exceeds 10% of system memory.
已解决，问题是我的训练x是单编码的，所以我的损失方法不正确。只需将keras模块更改为非稀疏和宾果游戏。