一、資料集準備

訓練資料花朵圖片下載：地址

圖片下載好後劃分資料集，分為訓練集和驗證集，訓練集每類圖片500張，驗證集每類圖片100張。

這是我資料集的樹圖：

二、訓練模型

環境：Ubuntu,Anaconda2,python2.7,tensorflow,keras

# --coding:utf-8--
import os
import sys
import glob
import argparse
import matplotlib.pyplot as plt

from keras import __version__
from keras.applications.inception_v3 import InceptionV3, preprocess_input
#from keras.applications.inception_v3_matt import InceptionV3, preprocess_input

from keras.models import Model
from keras.layers import Dense, GlobalAveragePooling2D
from keras.preprocessing.image import ImageDataGenerator
from keras.optimizers import SGD

def get_nb_files(directory):
  """Get number of files by searching directory recursively"""
  if not os.path.exists(directory):
    return 0
  cnt = 0
  for r, dirs, files in os.walk(directory):
    for dr in dirs:
      cnt += len(glob.glob(os.path.join(r, dr + "/*")))
  return cnt
#train_num = get_nb_files('/home/pandafish/AnacondaProjects/Inceptionv3/dataset_my/train')  2500
#print(train_num)
#input('wait...')

# 資料準備
IM_WIDTH, IM_HEIGHT = 299, 299 #InceptionV3指定的圖片尺寸
FC_SIZE = 1024                # 全連線層的節點個數
NB_IV3_LAYERS_TO_FREEZE = 172  # 凍結層的數量


train_dir = '/home/pandafish/AnacondaProjects/Inceptionv3/dataset_my/train'  # 訓練集資料
val_dir = '/home/pandafish/AnacondaProjects/Inceptionv3/dataset_my/validate' # 驗證集資料
output_model_file = '/home/pandafish/AnacondaProjects/Inceptionv3/weight/InceptionV3.model'
nb_classes= 5
nb_epoch = 3
batch_size = 16

nb_train_samples = get_nb_files(train_dir)      # 訓練樣本個數
nb_classes = len(glob.glob(train_dir + "/*"))  # 分類數
nb_val_samples = get_nb_files(val_dir)       #驗證集樣本個數
nb_epoch = int(nb_epoch)                # epoch數量
batch_size = int(batch_size)           

#　圖片生成器
train_datagen =  ImageDataGenerator(
  preprocessing_function=preprocess_input,
  rotation_range=30,
  width_shift_range=0.2,
  height_shift_range=0.2,
  shear_range=0.2,
  zoom_range=0.2,
  horizontal_flip=True
)
test_datagen = ImageDataGenerator(
  preprocessing_function=preprocess_input,
  rotation_range=30,
  width_shift_range=0.2,
  height_shift_range=0.2,
  shear_range=0.2,
  zoom_range=0.2,
  horizontal_flip=True
)

# 訓練資料與測試資料
train_generator = train_datagen.flow_from_directory(
train_dir,
target_size=(IM_WIDTH, IM_HEIGHT),
batch_size=batch_size,class_mode='categorical')

validation_generator = test_datagen.flow_from_directory(
val_dir,
target_size=(IM_WIDTH, IM_HEIGHT),
batch_size=batch_size,class_mode='categorical')

# 新增新層
def add_new_last_layer(base_model, nb_classes):
  """
  新增最後的層
  輸入
  base_model和分類數量
  輸出
  新的keras的model
  """
  x = base_model.output
  x = GlobalAveragePooling2D()(x)
  x = Dense(FC_SIZE, activation='relu')(x) #new FC layer, random init
  predictions = Dense(nb_classes, activation='softmax')(x) #new softmax layer
  model = Model(input=base_model.input, output=predictions)
  return model
# 凍上NB_IV3_LAYERS之前的層
def setup_to_finetune(model):
  """Freeze the bottom NB_IV3_LAYERS and retrain the remaining top layers.

  note: NB_IV3_LAYERS corresponds to the top 2 inception blocks in the inceptionv3 arch

  Args:
    model: keras model
  """
  for layer in model.layers[:NB_IV3_LAYERS_TO_FREEZE]:
     layer.trainable = False
  for layer in model.layers[NB_IV3_LAYERS_TO_FREEZE:]:
     layer.trainable = True
  model.compile(optimizer=SGD(lr=0.0001, momentum=0.9), loss='categorical_crossentropy', metrics=['accuracy'])

# 設定網路結構
model = InceptionV3(weights='imagenet', include_top=False)
model = add_new_last_layer(model, nb_classes)
setup_to_finetune(model)

# 模式二訓練
history_ft = model.fit_generator(
train_generator,
samples_per_epoch=nb_train_samples,
nb_epoch=nb_epoch,
validation_data=validation_generator,
nb_val_samples=nb_val_samples,
class_weight='auto1')

# 模型儲存
model.save(output_model_file)

# 畫圖
def plot_training(history):
  acc = history.history['acc']
  val_acc = history.history['val_acc']
  loss = history.history['loss']
  val_loss = history.history['val_loss']
  epochs = range(len(acc))
  plt.plot(epochs, acc, 'r.')
  plt.plot(epochs, val_acc, 'r')
  plt.title('Training and validation accuracy')
  plt.figure()
  plt.plot(epochs, loss, 'r.')
  plt.plot(epochs, val_loss, 'r-')
  plt.title('Training and validation loss')
  plt.show()

# 訓練的acc_loss圖
plot_training(history_ft)




 

三、測試圖片

     模型我只訓練了一個epoch，肯定是欠擬合的，主要是看看程式能否跑通。

# --coding:utf-8--
# 定義層
import sys
import argparse
import numpy as np
from PIL import Image
from io import BytesIO
import matplotlib.pyplot as plt

from keras.preprocessing import image
from keras.models import load_model
from keras.applications.inception_v3 import preprocess_input

# 狂階圖片指定尺寸
target_size = (229, 229) #fixed size for InceptionV3 architecture

# 預測函式
# 輸入：model，圖片，目標尺寸
# 輸出：預測predict
def predict(model, img, target_size):
  """Run model prediction on image
  Args:
    model: keras model
    img: PIL format image
    target_size: (w,h) tuple
  Returns:
    list of predicted labels and their probabilities
  """
  if img.size != target_size:
    img = img.resize(target_size)

  x = image.img_to_array(img)
  x = np.expand_dims(x, axis=0)
  x = preprocess_input(x)
  preds = model.predict(x)
  return preds[0]

# 畫圖函式
# 預測之後畫圖，這裡預設是貓狗，當然可以修改label

labels = ("daisy", "dandelion","roses","sunflowers","tulips")
def plot_preds(image, preds,labels):
  """Displays image and the top-n predicted probabilities in a bar graph
  Args:
    image: PIL image
    preds: list of predicted labels and their probabilities
  """
  plt.imshow(image)
  plt.axis('off')
  plt.figure()
  plt.barh([0, 1,2,3,4], preds, alpha=0.5)
  plt.yticks([0, 1,2,3,4], labels)
  plt.xlabel('Probability')
  plt.xlim(0,1.01)
  plt.tight_layout()
  plt.show()

# 載入模型
model = load_model('weight.model')

# 本地圖片
img = Image.open('sunflower.jpg')
preds = predict(model, img, target_size)
plot_preds(img, preds,labels)



 

測試結果