无法在Tensorflow估算器中训练Keras预训练模型

Question

While implementing a Tensorflow keras VGG16 pre-trained model with custom data using the Estimator class, it is throwing the error " ValueError: Cannot find input with name "image" in Keras Model. It needs to match one of the following: input_30 ".

In this code I haven't reshaped the input tensor into (-1, 224,224,3), instead, the shape is (224,224,3). I tried both shapes in the parser function - the function to be mapped to in the dataset API section.

Can anybody point out where is the mistake in the code. Feel free to change the code if there are any unnecessary mistakes.

This is done in Colab, so I am giving a link to it to check the error, in case you want to check it.

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

You are passing the following dictionary as input to your model:

x = {'image': images_batch}

Keras tries to to pass images_batch to an input tensor which is named image . This is not the case for base_model.input , which is unnamed. This is what is causing your error. Try passing images_batch as such to the model, without wrapping it in a dictionary (like you are alreading doing it for the labels):

x = images_batch