我是ML的新手，正在尝试Keras模型。我想了解tf.Estimator的Keras模型，因此将各种示例中的代码拼凑在一起。该代码包含三个关键部分-第一部分通过从文件夹中读取一组图像来创建TFRecord文件，第二部分从TFRecord文件中读取并提供给input_fn，第三部分是Keras VGG16和一个简单的全连接层的模型。
虽然代码的前两个部分可以正常工作，但出现此错误-
'ValueError: logits and labels must have the same shape ((?, 1) vs (?,))'
。正如在另一个类似问题的答案中所引用的那样，我尝试了expand-dim甚至将我的labels重塑为(?, 1)，但这给了我一些其他错误。
我不确定这段代码有什么问题以及
的原因'ValueError: logits and labels must have the same shape ((?, 1) vs (?,))'.
请帮助您确定错误并提出解决方案。提前致谢。我已经从下面的笔记本中复制粘贴了我的代码。
**Cell1 contents**
from random import shuffle
import glob
import sys
import cv2
import numpy as np
#import skimage.io as io
import tensorflow as tf
def _int64_feature(value):
return tf.train.Feature(int64_list=tf.train.Int64List(value=[value]))
def _bytes_feature(value):
return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))
def load_image(addr):
# read an image and resize to (224, 224)
# cv2 load images as BGR, convert it to RGB
img = cv2.imread(addr)
if img is None:
return None
img = cv2.resize(img, (224, 224), interpolation=cv2.INTER_CUBIC)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
return img
def createDataRecord(out_filename, addrs, labels):
# open the TFRecords file
#writer = tf.python_io.TFRecordWriter(out_filename)
options = tf.python_io.TFRecordOptions(tf.python_io.TFRecordCompressionType.GZIP)
writer = tf.python_io.TFRecordWriter(out_filename, options=options)
for i in range(len(addrs)):
# print how many images are saved every 1000 images
if not i % 1000:
print('Train data: {}/{}'.format(i, len(addrs)))
sys.stdout.flush()
# Load the image
img = load_image(addrs[i])
label = labels[i]
if img is None:
continue
# Create a feature
feature = {
'image': _bytes_feature(img.tostring()),
'label': _int64_feature(label)
}
# Create an example protocol buffer
example = tf.train.Example(features=tf.train.Features(feature=feature))
# Serialize to string and write on the file
writer.write(example.SerializeToString())
writer.close()
sys.stdout.flush()
**Cell2 contents**
cat_dog_train_path = 'dataset-mix/*/*.jpg'
# read addresses and labels from the 'train' folder
addrs = glob.glob(cat_dog_train_path)
labels = [0 if 'A' in addr else 1 for addr in addrs] # 0 = A, 1 = B
# to shuffle data
c = list(zip(addrs, labels))
shuffle(c)
addrs, labels = zip(*c)
#print("addrs: " + str(addrs))
#print("labels: " + str(labels))
# Divide the data into 60% train, 20% validation, and 20% test
train_addrs = addrs[0:int(0.6*len(addrs))]
train_labels = labels[0:int(0.6*len(labels))]
val_addrs = addrs[int(0.6*len(addrs)):int(0.8*len(addrs))]
val_labels = labels[int(0.6*len(addrs)):int(0.8*len(addrs))]
test_addrs = addrs[int(0.8*len(addrs)):]
test_labels = labels[int(0.8*len(labels)):]
print("train_addrs: " + str(train_addrs))
print("train_labels: " + str(train_labels))
createDataRecord('train-zipped.tfrecords', train_addrs, train_labels)
createDataRecord('val-zipped.tfrecords', val_addrs, val_labels)
createDataRecord('test-zipped.tfrecords', test_addrs, test_labels)
------
**second part**
**Cell3 contents**
import tensorflow as tf
import cv2
import sys
import numpy as np
sess = tf.Session()
sess.run(tf.global_variables_initializer())
def parser(record):
keys_to_features = {
"image": tf.FixedLenFeature([], tf.string),
"label": tf.FixedLenFeature([], tf.int64)
}
parsed = tf.parse_single_example(record, keys_to_features)
image = tf.decode_raw(parsed["image"], tf.uint8)
image = tf.cast(image, tf.float32)
image = tf.reshape(image, shape=[224, 224, 3])
label = tf.cast(parsed["label"], tf.int32)
#return {'image': image}, label
print("image.shape: " + str(np.shape(image)))
print("label.shape before: " + str(np.shape(label)) + "; label: " + str(label))
#label = np.array(label)
#print("label.shape after making np.array: " + str(np.shape(label)))
#label = np.expand_dims(label, axis=1)
#label = np.reshape(label, (-1, 1))
print("labels1.shape after expand_dims" + str(np.shape(label)))
return {'vgg16_input': image}, label
def input_fn(filenames=["train-zipped.tfrecords"]):
#To create a TFRecordDataset to read the compressed files:
dataset = tf.data.TFRecordDataset(filenames=filenames, compression_type='GZIP', num_parallel_reads=40)
dataset = dataset.apply(
tf.contrib.data.shuffle_and_repeat(1024, 1)
)
dataset = dataset.apply(
tf.contrib.data.map_and_batch(parser, 32)
)
#dataset = dataset.map(parser, num_parallel_calls=12)
#dataset = dataset.batch(batch_size=1000)
#print("dataset: " + str(dataset.make_one_shot_iterator().get_next()))
dataset = dataset.prefetch(buffer_size=2)
return dataset
def train_input_fn():
return input_fn(filenames=["train-zipped.tfrecords", "test-zipped.tfrecords"])
def val_input_fn():
return input_fn(filenames=["val-zipped.tfrecords"])
dat_set = train_input_fn()
item1 = dat_set.make_one_shot_iterator().get_next()[1]
res = sess.run(item1)
print("dataset: " + str(np.shape(res)))
#train_dataset = train_input_fn("train-zipped.tfrecords", "test-zipped.tfrecords")
#val_dataset = val_input_fn("val-zipped.tfrecords")
#print("classes: {0};\n shapes: {1};\n types: {2}\n".format(train_dataset.output_classes,
# train_dataset.output_shapes, train_dataset.output_types))
-----------
**third part**
**Cell4 contents**
def make_keras_estimator():
from tensorflow.python.keras.applications.vgg16 import VGG16
from tensorflow.python.keras import models
from tensorflow.python.keras import layers
import os
conv_base = VGG16(weights='imagenet',
include_top=False,
input_shape=(224, 224, 3))
conv_base.trainable = False
model = models.Sequential()
model.add(conv_base)
model.add(layers.Flatten())
model.add(layers.Dense(256, activation='relu'))
model.add(layers.Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer=tf.keras.optimizers.RMSprop(lr=2e-5),
metrics=['acc'])
model_dir = os.path.join(os.getcwd(), "model-keras-mix")
os.makedirs(model_dir, exist_ok=True)
print("model_dir: ",model_dir)
model.summary()
print("input_names" + str(model.input_names ))
model_est = tf.keras.estimator.model_to_estimator(keras_model=model,
model_dir=model_dir)
return model_est
**Cell5 contents**
model_keras = make_keras_estimator()
train_spec = tf.estimator.TrainSpec(input_fn=train_input_fn, max_steps=10)
eval_spec = tf.estimator.EvalSpec(input_fn=val_input_fn)
import time
start_time = time.time()
tf.estimator.train_and_evaluate(model_keras, train_spec, eval_spec)
print("--- %s seconds ---" % (time.time() - start_time))
答案 0 :(得分：0)
我认为错误消息指示标签应为形状（1，），而不仅仅是标量。
'ValueError：logits和标签的形状必须相同（（？，1）vs （？，））'
我建议的解决方案是在功能标签的“标签”中添加“ 1”。
def parser(record):
keys_to_features = {
"image": tf.FixedLenFeature([], tf.string),
"label": tf.FixedLenFeature([1], tf.int64) # add the 1 in this line
}
......
此外，由于模型输出（Sigmoid）为float32，我认为您应该将标签转换为float32而不是int32。
label = tf.cast(parsed["label"], tf.float32)