【深度学习 走进tensorflow2.0】tensorflow2.0 如何做图像分类模型训练和预测

无意中发现了一个巨牛的人工智能教程，忍不住分享一下给大家。教程不仅是零基础，通俗易懂，而且非常风趣幽默，像看小说一样！觉得太牛了，所以分享给大家。点这里可以跳转到教程。人工智能教程

创建一个数据集文件夹并命名（如 dataset）
在数据集文件中创建一个名称为 train 的子文件夹
在数据集文件中创建一个名称为 val 的子文件夹
在 train 文件夹中，为每个你要训练的对象创建文件夹并命名
在 val 文件夹中，为每个你要训练的对象创建文件夹并命名
把每个对象的图像放在 train 文件夹下对应名称的子文件夹，这些图像是用于训练模型的图像，为了训练出精准度较高的模型，我建议每个对象收集大约500张以上图像。

目录结构如下：

.
|-- train
|   |-- animal
|   |-- flower
|   |-- guitar
|   |-- houses
|   `-- plane
`-- val|-- animal|-- flower|-- guitar|-- houses`-- plane

使用tensorflow2.0 训练 残差神经网络resnet-50 。

# -*- coding: utf-8 -*-from __future__ import absolute_import, division, print_function, unicode_literals
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Conv2D, Flatten, Dropout, MaxPooling2D
from tensorflow.keras.preprocessing.image import ImageDataGeneratorimport json
import osfrom tensorflow.keras.applications.resnet50 import ResNet50batch_size = 32
epochs = 100
IMG_HEIGHT = 224
IMG_WIDTH = 224num_classes=5
image_input=224PATH = os.path.join('/home/dongli/tensorflow2.0/corpus/dataset/')train_dir = os.path.join(PATH, 'train')
validation_dir = os.path.join(PATH, 'val')train_animal_dir = os.path.join(train_dir, 'animal')
train_flower_dir = os.path.join(train_dir, 'flower')
train_guitar_dir = os.path.join(train_dir, 'guitar')
train_houses_dir = os.path.join(train_dir, 'houses')
train_plane_dir = os.path.join(train_dir, 'plane')validation_animal_dir = os.path.join(train_dir, 'animal')
validation_flower_dir = os.path.join(train_dir, 'flower')
validation_guitar_dir = os.path.join(train_dir, 'guitar')
validation_houses_dir = os.path.join(train_dir, 'houses')
validation_plane_dir = os.path.join(train_dir, 'plane')num_animal_tr = len(os.listdir(train_animal_dir))
num_flower_tr = len(os.listdir(train_flower_dir))
num_guitar_tr = len(os.listdir(train_guitar_dir))
num_houses_tr = len(os.listdir(train_houses_dir))
num_plane_tr = len(os.listdir(train_plane_dir))num_animal_val = len(os.listdir(validation_animal_dir))
num_flower_val = len(os.listdir(validation_flower_dir))
num_guitar_val = len(os.listdir(validation_guitar_dir))
num_houses_val = len(os.listdir(validation_houses_dir))
num_plane_val = len(os.listdir(validation_plane_dir))total_train = num_animal_tr+num_flower_tr+num_guitar_tr+num_houses_tr+num_plane_tr
total_val = num_animal_val + num_flower_val+num_guitar_val+num_houses_val+num_plane_valprint("Total training images:", total_train)
print("Total validation images:", total_val)# 训练集
# 对训练图像应用了重新缩放，45度旋转，宽度偏移，高度偏移，水平翻转和缩放增强。
image_gen_train = ImageDataGenerator(rescale=1./255,width_shift_range=0.1,height_shift_range=0.1)train_data_gen = image_gen_train.flow_from_directory(batch_size=batch_size,directory=train_dir,shuffle=True,target_size=(IMG_HEIGHT, IMG_WIDTH),class_mode='categorical')# 验证集image_gen_val = ImageDataGenerator(rescale=1./255)val_data_gen = image_gen_val.flow_from_directory(batch_size=batch_size,directory=validation_dir,target_size=(IMG_HEIGHT, IMG_WIDTH),class_mode='categorical')# 创建模型model=ResNet50(include_top=True, weights=None,classes=num_classes)
# 编译模型model.compile(optimizer='adam',loss='categorical_crossentropy',metrics=['accuracy'])# 模型总结
model.summary()# 模型保存格式定义model_class_dir='./flower_model/'
class_indices = train_data_gen.class_indices
class_json = {}
for eachClass in class_indices:class_json[str(class_indices[eachClass])] = eachClasswith open(os.path.join(model_class_dir, "model_class.json"), "w+") as json_file:json.dump(class_json, json_file, indent=4, separators=(",", " : "),ensure_ascii=True)json_file.close()
print("JSON Mapping for the model classes saved to ", os.path.join(model_class_dir, "model_class.json"))model_name = 'model_ex-{epoch:03d}_acc-{val_accuracy:03f}.h5'trained_model_dir='./flower_model/'
model_path = os.path.join(trained_model_dir, model_name)checkpoint = tf.keras.callbacks.ModelCheckpoint(filepath=model_path,monitor='val_accuracy',verbose=2,save_weights_only=True,save_best_only=True,mode='max',period=1)def lr_schedule(epoch):# Learning Rate Schedulelr =1e-3total_epochs =epochcheck_1 = int(total_epochs * 0.9)check_2 = int(total_epochs * 0.8)check_3 = int(total_epochs * 0.6)check_4 = int(total_epochs * 0.4)if epoch > check_1:lr *= 1e-4elif epoch > check_2:lr *= 1e-3elif epoch > check_3:lr *= 1e-2elif epoch > check_4:lr *= 1e-1return lr#lr_scheduler =tf.keras.callbacks.LearningRateScheduler(lr_schedule)lr_scheduler = tf.keras.callbacks.ReduceLROnPlateau(monitor='val_loss', factor=0.2,patience=5, min_lr=0.001)num_train = len(train_data_gen.filenames)
num_test = len(val_data_gen.filenames)print(num_train,num_test)# 模型训练
# 使用fit_generator方法ImageDataGenerator来训练网络。history = model.fit_generator(train_data_gen,steps_per_epoch=int(num_train / batch_size),epochs=epochs,validation_data=val_data_gen,validation_steps=int(num_test / batch_size),callbacks=[checkpoint,lr_scheduler])

模型保存

flower_model
|-- model_class.json
|-- model_ex-001_acc-0.197690.h5
|-- model_ex-001_acc-0.199728.h5
|-- model_ex-002_acc-0.222826.h5
|-- model_ex-003_acc-0.230299.h5
|-- model_ex-004_acc-0.338315.h5
|-- model_ex-005_acc-0.442255.h5
|-- model_ex-006_acc-0.618886.h5
|-- model_ex-007_acc-0.629755.h5
|-- model_ex-008_acc-0.698370.h5
|-- model_ex-011_acc-0.798234.h5
|-- model_ex-012_acc-0.819973.h5
|-- model_ex-018_acc-0.834239.h5
|-- model_ex-020_acc-0.852582.h5
|-- model_ex-023_acc-0.877038.h5
|-- model_ex-024_acc-0.884511.h5
|-- model_ex-029_acc-0.890625.h5
|-- model_ex-030_acc-0.908967.h5
|-- model_ex-035_acc-0.910326.h5
|-- model_ex-041_acc-0.930707.h5
|-- model_ex-051_acc-0.953804.h5
|-- model_ex-054_acc-0.958560.h5
`-- model_ex-095_acc-0.959239.h5

模型保存，如果模型保存了模型训练好的权重和图结构信息。采用load_model()导入、若需要只导入权重文件，采用load_weights()方式，需要重新构建一样的模型和编译模型，方能成功。

def create_model():base_model=ResNet50(include_top=True, weights=None,classes=class_num)model = tf.keras.Model(inputs=base_model.input, outputs=base_model.output)return model
# 重新构建模型
model=create_model()# 编译模型
model.compile(optimizer='adam',loss='categorical_crossentropy',metrics=['accuracy'])
# 导入权重文件
model.load_weights('./flower_model/model_ex-023_acc-0.864130.h5')

加载训练好的模型权重去预测新图片：

# -*- coding: utf-8 -*-
from __future__ import absolute_import, division, print_function, unicode_literals
import tensorflow as tf
from PIL import Image
import  numpy as np
from io import BytesIO
import json
import requests
CLASS_INDEX = None
import keras
input_image_size=224
class_num=5model_jsonPath='./flower_model/model_class.json'def preprocess_input(x):x *= (1./255)return xdef decode_predictions(preds, top=5, model_json=""):global CLASS_INDEXif CLASS_INDEX is None:CLASS_INDEX = json.load(open(model_json))results = []for pred in preds:top_indices = pred.argsort()[-top:][::-1]for i in top_indices:each_result = []each_result.append(CLASS_INDEX[str(i)])each_result.append(pred[i])results.append(each_result)return resultsprediction_results = []prediction_probabilities = []url='https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1573119512&di=95ad0908ab5e5ce22a674471f0e4d5d1&imgtype=jpg&er=1&src=http%3A%2F%2Fwww.sinaimg.cn%2Fjc%2Fp%2F2007-06-21%2FU2143P27T1D450794F3DT20070621164533.jpg'response=requests.get(url).content
image_input=responseimage_input = Image.open(BytesIO(image_input))
image_input = image_input.convert('RGB')
image_input = image_input.resize((input_image_size,input_image_size))
image_input = np.expand_dims(image_input, axis=0)
image_to_predict = image_input.copy()
image_to_predict = np.asarray(image_to_predict, dtype=np.float64)
image_to_predict = preprocess_input(image_to_predict)from tensorflow.keras.applications.resnet50 import ResNet50
from tensorflow import kerasdef create_model():base_model=ResNet50(include_top=True, weights=None,classes=class_num)model = tf.keras.Model(inputs=base_model.input, outputs=base_model.output)return modelmodel=create_model()# 编译模型
model.compile(optimizer='adam',loss='categorical_crossentropy',metrics=['accuracy'])model.load_weights('./flower_model/model_ex-023_acc-0.864130.h5')prediction = model.predict(x=image_to_predict)try:predictiondata = decode_predictions(prediction, top=int(class_num), model_json=model_jsonPath)for result in predictiondata:prediction_results.append(str(result[0]))prediction_probabilities.append(result[1] * 100)
except:raise ValueError("An error occured! Try again.")print(prediction_results[0],prediction_probabilities[0])

本文来自互联网用户投稿，文章观点仅代表作者本人，不代表本站立场，不承担相关法律责任。如若转载，请注明出处。 如若内容造成侵权/违法违规/事实不符，请点击【内容举报】进行投诉反馈！