沒練過這個專案，怎麼做AI工程師？
阿新 • • 發佈：2018-11-24
從年初起，幾家國際大廠的開發者大會，無論是微軟Build、Facebook F8還是稍後的Google I/O，莫不把“AI優先”的大旗扯上雲霄。
如果這一波AI大潮只是空喊幾句口號，空提幾個戰略，空有幾家炙手可熱的創業公司，那當然成不了什麼大氣候。但風浪之下，我們看到的卻是，Google一線的各大業務紛紛改用深度學習，落伍移動時代的微軟則已拉起一支近萬人的AI隊伍。而國內一線大廠的情況，更是把AI牢牢把握住，試圖再創高峰。
今天本文將分享一篇AI入門實戰的專案經驗分享，手把手帶你進入AI的世界，讓你消除對AI技術壁壘過高的恐懼~
【AI專案實戰】多標籤影象分類競賽小試牛刀
初次拿到這個題目，想了想做過了貓狗大戰這樣的二分類，也做過cifar-10這樣的多分類，類似本次比賽的題目多標籤影象分類的確沒有嘗試過。6941個標籤，每張圖片可能沒有標籤也可能存在6941個標籤，即各個標籤之間是不存在互斥關係的，所以最終分類的損失函式不能用softmax而必須要用sigmoid。然後把分類層預測6941個神經元，每個神經元用sigmoid函式返回是否存在某個標籤即可。
來蹚下整個流程看看，在jupyter notebook上做得比較亂，但是整個流程還是可以看出來的。深度學習模型用的Keras。
先匯入train_csv資料，這裡用的是最初版的訓練csv檔案，img_path裡存在地址，後面做了處理。
code
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
from glob import
from tqdm import tqdm
import cv2
from PIL import Image
train_path = 'visual_china_train.csv'
train_df = pd.read_csv(train_path)
train_df.head()code
train_df.shape
#(35000, 2)可以看到總共有35000張訓練圖片，第一列為圖片名稱（帶地址，需處理），第二列為圖片對應標籤。
來看下是不是的確只有6941個標籤：
code
tags = []
for i in range(train_df['tags'].shape[0]):
for tag in train_df['tags'].iloc[i].split(','):
tags.append(tag)
tags = set(tags)
len(tags)
#6941事實證明標籤總數無誤，可以放心大膽地繼續進行下去了。
然後我處理了下圖片名稱，並存到了img_paths列表裡。
code
#如果使用的是官方後來更新的visual_china_train.csv，可以直接使用最後一行程式碼
for i in range(35000):
train_df['img_path'].iloc[i] = train_df['img_path'].iloc[i].split('/')[-1]
img_paths = list(train_df['img_path'])定義三個函式，其中：
hash_tag函式讀入valid_tags.txt檔案，並存入字典，形成索引和標籤的對照。
load_ytrain函式讀入tag_train.npz檔案，並返回訓練集的y_train，形式為ndarray，shape為(35000, 6941)，即35000張圖片和對應標籤的one-hot編碼。
arr2tag函式將預測結果的y_pred轉變成對應的中文標籤。（實際上最後還需要做下處理）
code
def hash_tag(filepath):
fo = open(filepath, "r",encoding='utf-8')
hash_tag = {}
i = 0
for line in fo.readlines(): #依次讀取每行
line = line.strip() #去掉每行頭尾空白
hash_tag[i] = line
i += 1
return hash_tag
def load_ytrain(filepath):
y_train = np.load(filepath)
y_train = y_train['tag_train']
return y_train
def arr2tag(arr):
tags = []
for i in range(arr.shape[0]):
tag = []
index = np.where(arr[i] > 0.5)
index = index[0].tolist()
tag = [hash_tag[j] for j in index]
tags.append(tag)
return tags讀入valid_tags.txt，並生成索引和標籤的對映。
code
filepath = "valid_tags.txt"
hash_tag = hash_tag(filepath)
hash_tag[1]
#'0到1個月'載入y_train
code
y_train = load_ytrain('tag_train.npz')
y_train.shape
#(35000, 6941)
前期準備工作差不多做完了，開始匯入訓練集。此處有個坑，即原始訓練集中存在CMYK格式的圖片，傳統圖片處理一般為RGB格式，所以使用Image庫中的convert函式對非RGB格式的圖片進行轉換。
code
nub_train = 5000 #可修改，前期嘗試少量資料驗證模型
X_train = np.zeros((nub_train,224,224,3),dtype=np.uint8)
i = 0
for img_path in img_paths[:nub_train]:
img = Image.open('train/' + img_path)
if img.mode != 'RGB':
img = img.convert('RGB')
img = img.resize((224,224))
arr = np.asarray(img)
X_train[i,:,:,:] = arr
i += 1訓練集匯入完成，來看圖片的樣子，判斷下圖片有沒有讀入錯誤之類的問題。
code
fig,axes = plt.subplots(6,6,figsize=(20, 20))
j = 0
for i,img in enumerate(X_train[:36]):
axes[i//6,j%6].imshow(img)
j+=1看樣子還不錯，go on！ 訓練集的X_train、y_train都拿到了，分割出驗證集。這裡要說明一下，官方的y_train裡圖片名稱與X_train裡圖片名稱是對應的所以可以直接分割。
code
from sklearn.model_selection import train_test_split
X_train2,X_val,y_train2,y_val = train_test_split(X_train, y_train[:nub_train], test_size=0.2, random_state=2018)資料準備完成，開始搭建模型。咳咳，先從簡單的入手哈，此模型仿tinymind上一次的漢字書法識別大賽中“真的學不會”大佬的結構來搭的，又加了些自己的東西，反正簡單模型試試水嘛。
code
from keras.layers import *
from keras.models import *
from keras.optimizers import *
from keras.callbacks import *
def bn_prelu(x):
x = BatchNormalization()(x)
x = PReLU()(x)
return x
def build_model(out_dims, input_shape=(224, 224, 3)):
inputs_dim = Input(input_shape)
x = Lambda(lambda x: x / 255.0)(inputs_dim) #在模型裡進行歸一化預處理
x = Conv2D(16, (3, 3), strides=(2, 2), padding='same')(x)
x = bn_prelu(x)
x = Conv2D(16, (3, 3), strides=(1, 1), padding='same')(x)
x = bn_prelu(x)
x = MaxPool2D(pool_size=(2, 2))(x)
x = Conv2D(32, (3, 3), strides=(1, 1), padding='same')(x)
x = bn_prelu(x)
x = Conv2D(32, (3, 3), strides=(1, 1), padding='same')(x)
x = bn_prelu(x)
x = MaxPool2D(pool_size=(2, 2))(x)
x = Conv2D(64, (3, 3), strides=(1, 1), padding='same')(x)
x = bn_prelu(x)
x = MaxPool2D(pool_size=(2, 2))(x)
x = Conv2D(128, (3, 3), strides=(1, 1), padding='same')(x)
x = bn_prelu(x)
x = GlobalAveragePooling2D()(x)
dp_1 = Dropout(0.5)(x)
fc2 = Dense(out_dims)(dp_1)
fc2 = Activation('sigmoid')(fc2) #此處注意，為sigmoid函式
model = Model(inputs=inputs_dim, outputs=fc2)
return model
看下模型結構：
code
model = build_model(6941)
model.summary()_________________________________________________________________Layer (type) Output Shape Param # =================================================================input_1 (InputLayer) (None, 224, 224, 3) 0 _________________________________________________________________lambda_1 (Lambda) (None, 224, 224, 3) 0 _________________________________________________________________conv2d_1 (Conv2D) (None, 112, 112, 16) 448 _________________________________________________________________batch_normalization_1 (Batch (None, 112, 112, 16) 64 _________________________________________________________________p_re_lu_1 (PReLU) (None, 112, 112, 16) 200704 _________________________________________________________________conv2d_2 (Conv2D) (None, 112, 112, 16) 2320 _________________________________________________________________batch_normalization_2 (Batch (None, 112, 112, 16) 64 _________________________________________________________________p_re_lu_2 (PReLU) (None, 112, 112, 16) 200704 _________________________________________________________________max_pooling2d_1 (MaxPooling2 (None, 56, 56, 16) 0 _________________________________________________________________conv2d_3 (Conv2D) (None, 56, 56, 32) 4640 _________________________________________________________________batch_normalization_3 (Batch (None, 56, 56, 32) 128 _________________________________________________________________p_re_lu_3 (PReLU) (None, 56, 56, 32) 100352 _________________________________________________________________conv2d_4 (Conv2D) (None, 56, 56, 32) 9248 _________________________________________________________________batch_normalization_4 (Batch (None, 56, 56, 32) 128 _________________________________________________________________p_re_lu_4 (PReLU) (None, 56, 56, 32) 100352 _________________________________________________________________max_pooling2d_2 (MaxPooling2 (None, 28, 28, 32) 0 _________________________________________________________________conv2d_5 (Conv2D) (None, 28, 28, 64) 18496 _________________________________________________________________batch_normalization_5 (Batch (None, 28, 28, 64) 256 _________________________________________________________________p_re_lu_5 (PReLU) (None, 28, 28, 64) 50176 _________________________________________________________________max_pooling2d_3 (MaxPooling2 (None, 14, 14, 64) 0 _________________________________________________________________conv2d_6 (Conv2D) (None, 14, 14, 128) 73856 _________________________________________________________________batch_normalization_6 (Batch (None, 14, 14, 128) 512 _________________________________________________________________p_re_lu_6 (PReLU) (None, 14, 14, 128) 25088 _________________________________________________________________global_average_pooling2d_1 ( (None, 128) 0 _________________________________________________________________dropout_1 (Dropout) (None, 128) 0 _________________________________________________________________dense_1 (Dense) (None, 6941) 895389 _________________________________________________________________activation_1 (Activation) (None, 6941) 0 =================================================================Total params: 1,682,925 Trainable params: 1,682,349 Non-trainable params: 576_________________________________________________________________
由於比賽要求裡最終得分標準是fmeasure而不是acc，故網上找來一段程式碼用以監測訓練中查準率、查全率、fmeasure的變化。原地址找不到了，故而無法貼上，罪過罪過。
code
import keras.backend as K
def precision(y_true, y_pred):
# Calculates the precision
true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
precision = true_positives / (predicted_positives + K.epsilon())
return precision
def recall(y_true, y_pred):
# Calculates the recall
true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))
recall = true_positives / (possible_positives + K.epsilon())
return recall
def fbeta_score(y_true, y_pred, beta=1):
# Calculates the F score, the weighted harmonic mean of precision and recall.
if beta < 0:
raise ValueError('The lowest choosable beta is zero (only precision).')
# If there are no true positives, fix the F score at 0 like sklearn.
if K.sum(K.round(K.clip(y_true, 0, 1))) == 0:
return 0
p = precision(y_true, y_pred)
r = recall(y_true, y_pred)
bb = beta ** 2
fbeta_score = (1 + bb) * (p * r) / (bb * p + r + K.epsilon())
return fbeta_score
def fmeasure(y_true, y_pred):
# Calculates the f-measure, the harmonic mean of precision and recall.
return fbeta_score(y_true, y_pred, beta=1)這裡稍做圖片增強，用Keras裡的ImageDataGenerator函式，同時還可生成器方法進行訓練。
code
from keras.preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(width_shift_range = 0.1,
height_shift_range = 0.1,
zoom_range = 0.1)
val_datagen = ImageDataGenerator() #驗證集不做圖片增強
batch_size = 8
train_generator = train_datagen.flow(X_train2,y_train2,batch_size=batch_size,shuffle=False)
val_generator = val_datagen.flow(X_val,y_val,batch_size=batch_size,shuffle=False)
開始訓練。這裡在ModelCheckpoint裡設定monitor監控feasure，mode為max，不再以最低loss作為模型最優的判斷標準（個人做法，好壞可自行實驗判斷）。
code
checkpointer = ModelCheckpoint(filepath='weights_best_simple_model.hdf5',
monitor='val_fmeasure',verbose=1, save_best_only=True, mode='max')
reduce = ReduceLROnPlateau(monitor='val_fmeasure',factor=0.5,patience=2,verbose=1,min_delta=1e-4,mode='max')
model.compile(optimizer = 'adam',
loss='binary_crossentropy',
metrics=['accuracy',fmeasure,recall,precision])
epochs = 20
history = model.fit_generator(train_generator,
validation_data = val_generator,
epochs=epochs,
callbacks=[checkpointer,reduce],
verbose=1)訓練了20個epoch，這裡給出第20個epoch時的訓練結果，可以看到，val_loss 0.0233，其實已經挺低了；val_acc0.9945，參考意義不大（暫時不清楚有什麼參考意義~~）；val_fmeasure0.17，嗯。。任重道遠啊。
訓練了20個epoch，這裡給出第20個epoch時的訓練結果，可以看到，val_loss 0.0233，其實已經挺低了；val_acc0.9945，參考意義不大（暫時不清楚有什麼參考意義~~）；val_fmeasure0.17，嗯。。任重道遠啊。
Epoch 20/20500/500 [==============================] - 48s 96ms/step - loss: 0.0233 - acc: 0.9946 - fmeasure: 0.1699 - recall: 0.0970 - precision: 0.7108 - val_loss: 0.0233 - val_acc: 0.9946 - val_fmeasure: 0.1700 - val_recall: 0.0968 - val_precision: 0.7162 Epoch 00020: val_fmeasure did not improve from 0.17148
以上只給出5000張圖片的簡單模型訓練方法，但資料處理，搭建模型以及訓練過程已經很清晰明瞭了，後面的進階之路就憑大家各顯身手了。
然後開始進行預測，匯入測試集（當然是在訓練集全部訓練之後再進行測試集的預測）。
code
nub_test = len(glob('valid/*'))
X_test = np.zeros((nub_test,224,224,3),dtype=np.uint8)
path = []
i = 0
for img_path in tqdm(glob('valid/*')):
img = Image.open(img_path)
if img.mode != 'RGB':
i