如何将我自己的数据集添加到 MobileNet 模型？

Question

我正在尝试通过将我自己的数据集加载到 MobileNet 模型来进行预测。根据本教程，数据集（ cats_vs_dogs ）是从 TensorFlow 数据集加载的，如下所示

splits = tfds.Split.ALL.subsplit(weighted=(80, 20))

splits, info = tfds.load('cats_vs_dogs', with_info=True, as_supervised=True, split = splits)

(train_examples, validation_examples) = splits

num_examples = info.splits['train'].num_examples
num_classes = info.features['label'].num_classes

如何更改上面的代码以加载我自己的 cat vs dog 数据集？

Answer 1

请将以上 5 行代码替换为以下代码以读取您自己的数据，其余代码应与您的网络相同。

#Connect to dataset folders
train_dir  = '/content/drive/My Drive/Dogs_Vs_Cats/train'
test_dir = '/content/drive/My Drive/Dogs_Vs_Cats/test'

#Create data generator for training and testing
train_datagen = ImageDataGenerator(**datagen_kwargs)
test_datagen = ImageDataGenerator(**datagen_kwargs)

train_data = train_datagen.flow_from_directory(
    train_dir,
    target_size = (img_width, img_height),
    batch_size = batch_size,
    class_mode = 'binary')

test_data = test_datagen.flow_from_directory(
    test_dir,
    target_size = (img_width, img_height),
    batch_size = batch_size,
    class_mode = 'binary')

请参考以下使用自己的数据集的端到端实现：

%tensorflow_version 1.x   
import os
import numpy as np
from keras import layers
import pandas as pd
from tensorflow.keras.layers import Input, Dense, Activation, ZeroPadding2D, BatchNormalization, Flatten, Conv2D
from tensorflow.keras.layers import AveragePooling2D, MaxPooling2D, Dropout, GlobalMaxPooling2D, GlobalAveragePooling2D
from tensorflow.keras.models import Sequential
from tensorflow.keras import regularizers, optimizers
from tensorflow.keras.preprocessing import image
from tensorflow.keras.preprocessing.image import ImageDataGenerator

import keras.backend as K

K.set_image_data_format('channels_last')

from google.colab import drive
drive.mount('/content/drive')

train_dir  = '/content/drive/My Drive/Dogs_Vs_Cats/train'
test_dir = '/content/drive/My Drive/Dogs_Vs_Cats/test'

img_width, img_height = 300, 281
input_shape = img_width, img_height, 3

train_samples = 2000
test_samples = 1000
epochs = 30
batch_size = 32

train_datagen = ImageDataGenerator(
    rescale = 1. /255,
    shear_range = 0.2,
    zoom_range = 0.2,
    horizontal_flip = True)

test_datagen = ImageDataGenerator(
    rescale = 1. /255)

train_data = train_datagen.flow_from_directory(
    train_dir,
    target_size = (img_width, img_height),
    batch_size = batch_size,
    class_mode = 'binary')

test_data = test_datagen.flow_from_directory(
    test_dir,
    target_size = (img_width, img_height),
    batch_size = batch_size,
    class_mode = 'binary')


model = Sequential()

model.add(Conv2D(32, (7, 7), strides = (1, 1), input_shape = input_shape))
model.add(BatchNormalization(axis = 3))
model.add(Activation('relu'))
model.add(MaxPooling2D((2, 2)))

model.add(Conv2D(64, (7, 7), strides = (1, 1)))
model.add(BatchNormalization(axis = 3))
model.add(Activation('relu'))
model.add(MaxPooling2D((2, 2)))

model.add(Flatten())
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))

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

model.build(input_shape)
model.summary() 


model.fit_generator(
        train_data,
        steps_per_epoch = train_samples//batch_size,
        epochs = epochs,
        validation_data = test_data,
        verbose = 1,
        validation_steps = test_samples//batch_size)