【发布时间】：2019-12-30 05:55:48
【问题描述】：
我正在尝试使用 IAM 数据集构建手写文字识别 在训练时，我面临过度拟合问题。您能不能 帮我弄清楚我在下面的代码中犯了什么错误。
我已经尝试了所有可以找到的解决方案来解决问题，但仍然存在同样的过拟合问题。
import os
import fnmatch
import cv2
import numpy as np
import string
import time
import random
from keras import regularizers, optimizers
from keras.regularizers import l2
from keras.preprocessing.sequence import pad_sequences
from keras.layers import Dense, LSTM, Reshape, BatchNormalization, Input, Conv2D, MaxPool2D, Lambda, Bidirectional, Dropout
from keras.models import Model
from keras.activations import relu, sigmoid, softmax
import keras.backend as K
from keras.utils import to_categorical
from keras.callbacks import ModelCheckpoint,ReduceLROnPlateau
import matplotlib.pyplot as plt
imgSize = (128,32)
def preprocess(img, imgSize, dataAugmentation=False):
"put img into target img of size imgSize, transpose for TF and normalize gray-values"
# there are damaged files in IAM dataset - just use black image instead
if img is None:
img = np.zeros([imgSize[1], imgSize[0]])
# increase dataset size by applying random stretches to the images
if dataAugmentation:
stretch = (random.random() - 0.5) # -0.5 .. +0.5
wStretched = max(int(img.shape[1] * (1 + stretch)), 1) # random width, but at least 1
img = cv2.resize(img, (wStretched, img.shape[0])) # stretch horizontally by factor 0.5 .. 1.5
img = cv2.adaptiveThreshold(img,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C,cv2.THRESH_BINARY,11,2)
# print('Data Augmented')
# create target image and copy sample image into it
(wt, ht) = imgSize
(h, w) = img.shape
fx = w / wt
fy = h / ht
f = max(fx, fy)
newSize = (max(min(wt, int(w / f)), 1), max(min(ht, int(h / f)), 1)) # scale according to f (result at least 1 and at most wt or ht)
img = cv2.resize(img, newSize)
target = np.ones([ht, wt]) * 255
target[0:newSize[1], 0:newSize[0]] = img
# transpose for TF
img = cv2.transpose(target)
# normalize
(m, s) = cv2.meanStdDev(img)
m = m[0][0]
s = s[0][0]
img = img - m
img = img / s if s>0 else img
img = np.expand_dims(img , axis = 2)
return img
def truncateLabel(text, maxTextLen): # A,32
cost = 0
for i in range(len(text)):
if i != 0 and text[i] == text[i-1]:
cost += 2
else:
cost += 1
if cost > maxTextLen:
return text[:i] # returns words with repeated chars
return text
path = 'iam_dataset_words/'
maxTextLen = 32
samples = []
bad_samples = []
fileName = ''
dataAugmentation = False
chars = set()
f=open(path+ 'words.txt', "r")
cou = 0
bad_samples = []
bad_samples_reference = ['a01-117-05-02.png',
'r06-022-03-05.png']
for line in f:
cou+=1
# ignore comment line
if not line or line[0]=='#':
continue
lineSplit = line.strip().split(' ')
assert len(lineSplit) >= 9
fileNameSplit = lineSplit[0].split('-') #a01-000u-00-00 splits
#../data/words/a01/a01-000u/a01-000u-00-00.png
fileName = path + 'words/' \
+ fileNameSplit[0] + '/' \
+ fileNameSplit[0] + '-' \
+ fileNameSplit[1] \
+ '/' + lineSplit[0] + '.png'
# GT text are columns starting at 9
gtText = truncateLabel(' '.join(lineSplit[8:]), maxTextLen) #A,32
#chars = chars.union(gtText) #unique chars only
chars = chars.union(set(list(gtText)))
# check if image is not empty
if not os.path.getsize(fileName):
bad_samples.append(lineSplit[0] + '.png')
continue
# put sample into list
#'A','../data/words/a01/a01-000u/a01-000u-00-00.png'
samples.append([gtText, fileName])
print(cou)
print(len(samples))
print(samples[:2])
if set(bad_samples) != set(bad_samples_reference):
print("Warning, damaged images found:", bad_samples)
print("Damaged images expected:", bad_samples_reference)
trainSamples = []
validationSamples = []
testSamples = []
valid_testSamples = []
# split into training and validation set: 90% - 10%
# dataAugmentation = True
random.shuffle(samples)
splitIdx = int(0.75 * len(samples))
train_samples = samples[:splitIdx]
valid_testSamples = samples[splitIdx:]
print('vv:', len(valid_testSamples))
validationSamples = valid_testSamples[:15000]
testSamples = valid_testSamples[15000:]
print('valid: ',len(validationSamples))
print('test: ',len(testSamples))
print('train_before: ',len(train_samples))
# # start with train set
trainSamples = train_samples[:25000] #tran data 25000
print('train_ after: ',len(trainSamples))
# # list of all unique chars in dataset
charList = sorted(list(chars))
char_list = str().join(charList)
# print('test samples: ',testSamples)
print('char list : ',char_list)
# # save characters of model for inference mode
# open(FilePaths.fnCharList, 'w').write(str().join(charList))
# # save words contained in dataset into file
# open(FilePaths.fnCorpus, 'w').write(str(' ').join(loader.trainWords + validationWords))
def encode_to_labels(txt):
# encoding each output word into digits
chars = []
for index, char in enumerate(txt):
try:
chars.append(char_list.index(char))
except:
print(char)
return chars
print(trainSamples[:2])
# lists for training dataset
train_img = []
train_txt = []
train_input_length = []
train_label_length = []
train_orig_txt = []
max_label_len = 0
b = 0
for words, imgPath in trainSamples:
img = preprocess(cv2.imread(imgPath, cv2.IMREAD_GRAYSCALE), imgSize, dataAugmentation = True)
# compute maximum length of the text
if len(words) > max_label_len:
max_label_len = len(words)
train_orig_txt.append(words)
train_label_length.append(len(words))
train_input_length.append(31)
train_img.append(img)
train_txt.append(encode_to_labels(words))
b+=1
# print(train_img[1])
print(len(train_txt))
train_txt[:5]
a = 0
#lists for validation dataset
valid_img = []
valid_txt = []
valid_input_length = []
valid_label_length = []
valid_orig_txt = []
for words, imgPath in validationSamples:
img = preprocess(cv2.imread(imgPath, cv2.IMREAD_GRAYSCALE), imgSize, dataAugmentation = False)
valid_orig_txt.append(words)
valid_label_length.append(len(words))
valid_input_length.append(31)
valid_img.append(img)
valid_txt.append(encode_to_labels(words))
a+=1
print(len(valid_txt))
valid_txt[:5]
# lists for training dataset
test_img = []
test_txt = []
test_input_length = []
test_label_length = []
test_orig_txt = []
c = 0
for words, imgPath in testSamples:
img = preprocess(cv2.imread(imgPath, cv2.IMREAD_GRAYSCALE), imgSize, dataAugmentation = False)
test_orig_txt.append(words)
test_label_length.append(len(words))
test_input_length.append(31)
test_img.append(img)
test_txt.append(encode_to_labels(words))
c+=1
# print(c)
print(test_img[0].shape)
print('Train: {}\nValid: {}\nTest: {}'.format(b,a,c))
print(max_label_len)
# pad each output label to maximum text length
train_padded_txt = pad_sequences(train_txt, maxlen=max_label_len, padding='post', value = len(char_list))
valid_padded_txt = pad_sequences(valid_txt, maxlen=max_label_len, padding='post', value = len(char_list))
test_padded_txt = pad_sequences(test_txt, maxlen=max_label_len, padding='post', value = len(char_list))
print(len(train_padded_txt))
print(len(test_padded_txt))
print(valid_padded_txt[1])
# input with shape of height=32 and width=128
inputs = Input(shape=(128,32,1))
print(inputs.shape)
# convolution layer with kernel size (3,3)
conv_1 = Conv2D(32, (3,3), activation = 'relu', padding='same')(inputs)
batch_norm_1 = BatchNormalization()(conv_1)
# poolig layer with kernel size (2,2)
pool_1 = Conv2D(32, kernel_size=(1, 1), strides=2, padding='valid')(batch_norm_1)
conv_2 = Conv2D(64, (3,3), activation = 'relu', padding='same')(pool_1)
batch_norm_2 = BatchNormalization()(conv_2)
pool_2 = Conv2D(64, kernel_size=(1, 1), strides=2, padding='valid')(batch_norm_2)
conv_3 = Conv2D(128, (3,3), activation = 'relu', padding='same')(pool_2)
batch_norm_3 = BatchNormalization()(conv_3)
conv_4 = Conv2D(128, (3,3), activation = 'relu', padding='same')(batch_norm_3)
batch_norm_4 = BatchNormalization()(conv_4)
# poolig layer with kernel size (1,2)
pool_4 = MaxPool2D(pool_size=(1,2))(batch_norm_4)
conv_5 = Conv2D(256, (3,3), activation = 'relu', padding='same')(pool_4)
# Batch normalization layer
batch_norm_5 = BatchNormalization()(conv_5)
conv_6 = Conv2D(256, (3,3), activation = 'relu', padding='same')(batch_norm_5)
batch_norm_6 = BatchNormalization()(conv_6)
pool_6 = MaxPool2D(pool_size=(1,2))(batch_norm_6)
conv_7 = Conv2D(256, (2,2), activation = 'relu')(pool_6)
batch_norm_7 = BatchNormalization()(conv_7)
# print(conv_7.shape)
# map-to-sequence-- dropping 1 dimension
squeezed = Lambda(lambda x: K.squeeze(x, 2))(batch_norm_7)
# print('squeezed',squeezed.shape)
# bidirectional LSTM layers with units=128
blstm_1 = Bidirectional(LSTM(128, return_sequences=True, dropout = 0.3))(squeezed)
blstm_2 = Bidirectional(LSTM(128, return_sequences=True, dropout = 0.3))(blstm_1)
outputs = Dense(len(char_list)+1, activation = 'softmax')(blstm_2)
# model to be used at test time
word_model = Model(inputs, outputs)
adam = optimizers.Adamax(lr=0.01, decay = 1e-5)
model.compile(loss= {'ctc': lambda y_true, y_pred: y_pred}, optimizer = adam, metrics = ['accuracy'])
filepath="best_model.hdf5"
checkpoint1 = ReduceLROnPlateau(monitor='val_loss', verbose=1,
mode='auto',factor=0.2,patience=4, min_lr=0.0001)
checkpoint2 = ModelCheckpoint(filepath=filepath, monitor='val_loss', verbose=1, save_best_only=True, mode='auto')
callbacks_list = [checkpoint1, checkpoint2]
train_img = np.array(train_img)
train_input_length = np.array(train_input_length)
train_label_length = np.array(train_label_length)
valid_img = np.array(valid_img)
valid_input_length = np.array(valid_input_length)
valid_label_length = np.array(valid_label_length)
test_img = np.array(test_img)
test_input_length = np.array(test_input_length)
test_label_length = np.array(test_label_length)
test_img.shape
batch_size = 50
epochs = 30
train_history = model.fit(x=[train_img, train_padded_txt, train_input_length, train_label_length],
y=np.zeros(len(train_img)), batch_size=batch_size, epochs = epochs,
validation_data = ([valid_img, valid_padded_txt, valid_input_length,
valid_label_length], [np.zeros(len(valid_img))]),
verbose = 1, callbacks = callbacks_list)
训练 25000 个样本，验证 15000 个样本
Epoch 1/30
25000/25000 [==============================] - 159s 6ms/step - loss: 13.6510 - acc: 0.0199 - val_loss: 11.4910 - val_acc: 0.0651
Epoch 00001: val_loss improved from inf to 11.49100, saving model to best_model.hdf5
Epoch 2/30
25000/25000 [==============================] - 146s 6ms/step - loss: 10.9559 - acc: 0.0603 - val_loss: 9.7359 - val_acc: 0.0904
Epoch 00002: val_loss improved from 11.49100 to 9.73587, saving model to best_model.hdf5
Epoch 3/30
25000/25000 [==============================] - 146s 6ms/step - loss: 9.0720 - acc: 0.0943 - val_loss: 7.3571 - val_acc: 0.1565
Epoch 00003: val_loss improved from 9.73587 to 7.35715, saving model to best_model.hdf5
Epoch 4/30
25000/25000 [==============================] - 145s 6ms/step - loss: 6.9501 - acc: 0.1520 - val_loss: 5.5228 - val_acc: 0.2303
Epoch 00004: val_loss improved from 7.35715 to 5.52277, saving model to best_model.hdf5
Epoch 5/30
25000/25000 [==============================] - 144s 6ms/step - loss: 5.4893 - acc: 0.2129 - val_loss: 4.3179 - val_acc: 0.2895
Epoch 00005: val_loss improved from 5.52277 to 4.31793, saving model to best_model.hdf5
Epoch 6/30
25000/25000 [==============================] - 143s 6ms/step - loss: 4.7053 - acc: 0.2612 - val_loss: 3.7490 - val_acc: 0.3449
Epoch 00006: val_loss improved from 4.31793 to 3.74896, saving model to best_model.hdf5
Epoch 7/30
25000/25000 [==============================] - 143s 6ms/step - loss: 4.1183 - acc: 0.3096 - val_loss: 3.5902 - val_acc: 0.3805
Epoch 00007: val_loss improved from 3.74896 to 3.59015, saving model to best_model.hdf5
Epoch 8/30
25000/25000 [==============================] - 143s 6ms/step - loss: 3.6662 - acc: 0.3462 - val_loss: 3.7923 - val_acc: 0.3350
Epoch 00008: val_loss did not improve from 3.59015
Epoch 9/30
25000/25000 [==============================] - 143s 6ms/step - loss: 3.3398 - acc: 0.3809 - val_loss: 3.1352 - val_acc: 0.4344
Epoch 00009: val_loss improved from 3.59015 to 3.13516, saving model to best_model.hdf5
Epoch 10/30
25000/25000 [==============================] - 143s 6ms/step - loss: 3.0199 - acc: 0.4129 - val_loss: 2.9798 - val_acc: 0.4541
Epoch 00010: val_loss improved from 3.13516 to 2.97978, saving model to best_model.hdf5
Epoch 11/30
25000/25000 [==============================] - 143s 6ms/step - loss: 2.7361 - acc: 0.4447 - val_loss: 3.3836 - val_acc: 0.3780
Epoch 00011: val_loss did not improve from 2.97978
Epoch 12/30
25000/25000 [==============================] - 143s 6ms/step - loss: 2.5127 - acc: 0.4695 - val_loss: 2.9266 - val_acc: 0.5041
Epoch 00012: val_loss improved from 2.97978 to 2.92656, saving model to best_model.hdf5
Epoch 13/30
25000/25000 [==============================] - 142s 6ms/step - loss: 2.3045 - acc: 0.4974 - val_loss: 2.7329 - val_acc: 0.5174
Epoch 00013: val_loss improved from 2.92656 to 2.73294, saving model to best_model.hdf5
Epoch 14/30
25000/25000 [==============================] - 141s 6ms/step - loss: 2.1245 - acc: 0.5237 - val_loss: 2.8624 - val_acc: 0.5339
Epoch 00014: val_loss did not improve from 2.73294
Epoch 15/30
25000/25000 [==============================] - 142s 6ms/step - loss: 1.9091 - acc: 0.5524 - val_loss: 2.6933 - val_acc: 0.5506
Epoch 00015: val_loss improved from 2.73294 to 2.69333, saving model to best_model.hdf5
Epoch 16/30
25000/25000 [==============================] - 141s 6ms/step - loss: 1.7565 - acc: 0.5705 - val_loss: 2.7697 - val_acc: 0.5461
Epoch 00016: val_loss did not improve from 2.69333
Epoch 17/30
25000/25000 [==============================] - 145s 6ms/step - loss: 1.6273 - acc: 0.5892 - val_loss: 2.8992 - val_acc: 0.5361
Epoch 00017: val_loss did not improve from 2.69333
Epoch 18/30
25000/25000 [==============================] - 145s 6ms/step - loss: 1.5007 - acc: 0.6182 - val_loss: 2.9558 - val_acc: 0.5345
Epoch 00018: val_loss did not improve from 2.69333
Epoch 19/30
25000/25000 [==============================] - 143s 6ms/step - loss: 1.3775 - acc: 0.6311 - val_loss: 2.8437 - val_acc: 0.5744
Epoch 00019: ReduceLROnPlateau reducing learning rate to 0.0019999999552965165.
Epoch 00019: val_loss did not improve from 2.69333
Epoch 20/30
25000/25000 [==============================] - 144s 6ms/step - loss: 0.9636 - acc: 0.7115 - val_loss: 2.6072 - val_acc: 0.6083
Epoch 00020: val_loss improved from 2.69333 to 2.60724, saving model to best_model.hdf5
Epoch 21/30
25000/25000 [==============================] - 146s 6ms/step - loss: 0.7940 - acc: 0.7583 - val_loss: 2.6613 - val_acc: 0.6167
Epoch 00021: val_loss did not improve from 2.60724
Epoch 22/30
25000/25000 [==============================] - 146s 6ms/step - loss: 0.6995 - acc: 0.7797 - val_loss: 2.7180 - val_acc: 0.6220
Epoch 00022: val_loss did not improve from 2.60724
Epoch 23/30
25000/25000 [==============================] - 144s 6ms/step - loss: 0.6197 - acc: 0.8046 - val_loss: 2.7504 - val_acc: 0.6226
Epoch 00023: val_loss did not improve from 2.60724
Epoch 24/30
25000/25000 [==============================] - 143s 6ms/step - loss: 0.5668 - acc: 0.8167 - val_loss: 2.8238 - val_acc: 0.6255
Epoch 00024: ReduceLROnPlateau reducing learning rate to 0.0003999999724328518.
Epoch 00024: val_loss did not improve from 2.60724
Epoch 25/30
25000/25000 [==============================] - 144s 6ms/step - loss: 0.5136 - acc: 0.8316 - val_loss: 2.8167 - val_acc: 0.6283
Epoch 00025: val_loss did not improve from 2.60724
Epoch 26/30
25000/25000 [==============================] - 143s 6ms/step - loss: 0.5012 - acc: 0.8370 - val_loss: 2.8244 - val_acc: 0.6299
Epoch 00026: val_loss did not improve from 2.60724
Epoch 27/30
25000/25000 [==============================] - 143s 6ms/step - loss: 0.4886 - acc: 0.8425 - val_loss: 2.8366 - val_acc: 0.6282
Epoch 00027: val_loss did not improve from 2.60724
Epoch 28/30
25000/25000 [==============================] - 143s 6ms/step - loss: 0.4820 - acc: 0.8432 - val_loss: 2.8447 - val_acc: 0.6271
Epoch 00028: ReduceLROnPlateau reducing learning rate to 0.0001.
Epoch 00028: val_loss did not improve from 2.60724
Epoch 29/30
25000/25000 [==============================] - 141s 6ms/step - loss: 0.4643 - acc: 0.8452 - val_loss: 2.8538 - val_acc: 0.6278
Epoch 00029: val_loss did not improve from 2.60724
Epoch 30/30
25000/25000 [==============================] - 141s 6ms/step - loss: 0.4576 - acc: 0.8496 - val_loss: 2.8555 - val_acc: 0.6277
Epoch 00030: val_loss did not improve from 2.60724
模型评估
test_history = model.evaluate([test_img, test_padded_txt,
test_input_length, test_label_length],
y=np.zeros(len(test_img)), verbose = 1)
test_history
输出
13830/13830 [==============================] - 42s 3ms/step
[2.855567638786134, 0.6288503253882292]
【问题讨论】：