Question

在使用Estimator类实现具有自定义数据的Tensorflow keras VGG16预训练模型时，它抛出错误“ ValueError：在Keras模型中找不到名称为” image“的输入。它需要与以下之一匹配以下内容：input_30 ”。

在此代码中，我没有将输入张量重整为（-1，224,224,3），而是将其形状更改为（224,224,3）。我在解析器函数中尝试了这两种形状-该函数将在数据集API部分中映射到该函数。

任何人都可以指出代码中的错误之处。如果有任何不必要的错误，请随时更改代码。

这是在Colab中完成的，因此，如果您要检查错误，我会给它一个link来检查错误。

import tensorflow as 
from keras.utils import to_categorical
import cv2 as cv
import glob
import sys
import os
import numpy as np
from tensorflow.keras.layers import Conv2D, GlobalAveragePooling2D
from tensorflow.keras.layers import Dense, Input
from tensorflow.keras.models import Model
from tensorflow.keras.applications.vgg16 import VGG16, preprocess_input
from sklearn.preprocessing import LabelEncoder

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]))

#Function to load image 
def load_image(addr):
    img = cv.imread(addr)
    if img is None:
        return None
    img = cv.resize(img, (224, 224), interpolation=cv.INTER_CUBIC)
    img = cv.cvtColor(img, cv.COLOR_BGR2RGB)
    return img

#Function to create TFRecords
def create_tfrecords(filename, address, labels):
    writer = tf.python_io.TFRecordWriter(filename)
    for i in range(len(address)):
        img = load_image(address[i])
        label = labels[i]

        if img is None:
            continue
        feature = {
        'image_raw': _bytes_feature(img.tostring()),
        'label': _int64_feature(label)}

        example = 
        tf.train.Example(features=tf.train.Features(feature=feature))
        writer.write(example.SerializeToString())

    writer.close()
    sys.stdout.flush()

#Creating labels from custom data
def create_labels():
    labels = []
    for i in os.listdir('training'):
        for l in enumerate(os.listdir('training/{}'.format(i))):
            labels.append(i)
    le = LabelEncoder()
    labels = le.fit_transform(labels)
    labels = to_categorical(np.array(labels))
    return labels

labels = create_labels()
#Generating image locations
train_path = 'training/*/*.jpg' #training/class/images
address = glob.glob(train_path)

#Splitting train and test data
x_train = address[0:int(0.8*len(address))]
y_train = labels[0:int(0.8*len(labels))]

x_test = address[int(0.8*len(address)):]
y_test = labels[int(0.8*len(labels)):]

create_tfrecords('train.tfrecords', x_train, y_train)
create_tfrecords('test.tfrecords', x_test, y_test)

#Keras pre-trainied model
base_model = VGG16(weights='imagenet', input_shape=(224,224,3), 
                                               include_top=False)

x = base_model.output
x = GlobalAveragePooling2D()(x)
x = Dense(1024, activation='relu')(x)
output = Dense(10, activation='softmax')(x)

model = Model(inputs=base_model.input, outputs=output)

for layer in base_model.layers:
    layer.trainable = False

optimizer = tf.keras.optimizers.Adam(lr=1e-5)  

model.compile(optimizer=optimizer, loss='categorical_crossentropy', metrics= 
                                                               ['accuracy'])

keras_model = tf.keras.estimator.model_to_estimator(keras_model=model)

#Initiating session
sess = tf.Session()
sess.run(tf.global_variables_initializer())

#Defining parser function to extract from the TFRecord files
def parser(record):
    keys_to_features = {
                    'image_raw': tf.FixedLenFeature([], tf.string),
                    'label': tf.FixedLenFeature([], tf.int64)}

    parsed = tf.parse_single_example(record, keys_to_features)
    image = tf.decode_raw(parsed['image_raw'], tf.uint8)
    image = tf.cast(image, tf.float32)
    image = tf.reshape(image, shape = [224, 224, 3])
    labels = tf.cast(parsed['label'], tf.int32)
    return image, labels

#Input Function
 def inp_fn(filename, train, batch_size=16, buffer_size=100):
     dataset = tf.data.TFRecordDataset(filenames=filename)
     dataset = dataset.map(parser)
     if train:
         dataset = dataset.shuffle(buffer_size=buffer_size)
         num_repeat = None
     else:
         num_repeat = 1
     dataset = dataset.repeat(num_repeat)
     dataset = dataset.batch(batch_size=batch_size)
     iterator = dataset.make_one_shot_iterator()
     images_batch, labels_batch = iterator.get_next()
     x = {'image': images_batch}
     y = labels_batch
     return x, y

#Train Input Function
def train_input_fn():
    return inp_fn(filename='train.tfrecords' , train=True)
#Test Input Function
def test_input_fn():
    return inp_fn(filename='test.tfrecords', train=False)

#Training and testing
keras_model.train(input_fn=train_input_fn, steps=1000)

result = keras_model.evaluate(input_fn=test_input_fn)

print('Result:', result)
print('Classification Accuracy : {:4f}'.format(result['accuracy']*100)) 
print('Classification loss: {:.4f}'.format(result['loss']))
sys.stdout.flush()

Answer 1

您将以下字典作为输入传递给模型：

x = {'image': images_batch}

Keras尝试将images_batch传递给名为image的输入张量。未命名的base_model.input并非如此。这是导致您的错误的原因。尝试将images_batch这样传递给模型，而不要将其包装在字典中（就像您正在为标签做的那样）：

x = images_batch

无法在Tensorflow估算器中训练Keras预训练模型

1 个答案: