今回は、このサイトのコードを参考にしながらkaggleのdogs vs. cats reduxをやる。先ず最初にkaggleのサイトから今回のチュートリアルに必要な画像データを入手してくる。
スポンサーリンク
データの準備¶
ダウンロードしたアーカイブファイルを解凍する。
!unzip all.zip
dataサブディレクトリを作成する。
!mkdir data
解凍したアーカイブファイルをdataフォルダに移動する。
!mv train.zip data
!mv test.zip data
dataディレクトリに移動する。
cd data
train.zipとtest.zipを解凍する。
!unzip train.zip
!unzip test.zip
スポンサーリンク
必要なモジュールとデータのインポート¶
import cv2 # working with, mainly resizing, images
import numpy as np # dealing with arrays
import os # dealing with directories
from random import shuffle # mixing up or currently ordered data that might lead our network astray in training.
from tqdm import tqdm # a nice pretty percentage bar for tasks.
TRAIN_DIR = 'train'
TEST_DIR = 'test'
IMG_SIZE = 50
LR = 1e-3
MODEL_NAME = 'dogsvscats-{}-{}.model'.format(LR, '2conv-basic') # just so we remember which saved model is which, sizes must match
def label_img(img):
word_label = img.split('.')[-3]
# conversion to one-hot array [cat,dog]
# [much cat, no dog]
if word_label == 'cat': return [1,0]
# [no cat, very doggo]
elif word_label == 'dog': return [0,1]
def create_train_data():
training_data = []
for img in tqdm(os.listdir(TRAIN_DIR)):
label = label_img(img)
path = os.path.join(TRAIN_DIR,img)
img = cv2.imread(path,cv2.IMREAD_GRAYSCALE)
img = cv2.resize(img, (IMG_SIZE,IMG_SIZE))
training_data.append([np.array(img),np.array(label)])
shuffle(training_data)
np.save('train_data.npy', training_data)
return training_data
def process_test_data():
testing_data = []
for img in tqdm(os.listdir(TEST_DIR)):
path = os.path.join(TEST_DIR,img)
img_num = img.split('.')[0]
img = cv2.imread(path,cv2.IMREAD_GRAYSCALE)
img = cv2.resize(img, (IMG_SIZE,IMG_SIZE))
testing_data.append([np.array(img), img_num])
shuffle(testing_data)
np.save('test_data.npy', testing_data)
return testing_data
train_data = create_train_data()
# If you have already created the dataset:
#train_data = np.load('train_data.npy')
スポンサーリンク
tflearnのインストール¶
import tflearn
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.estimator import regression
convnet = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 1], name='input')
convnet = conv_2d(convnet, 32, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)
convnet = conv_2d(convnet, 64, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)
convnet = fully_connected(convnet, 1024, activation='relu')
convnet = dropout(convnet, 0.8)
convnet = fully_connected(convnet, 2, activation='softmax')
convnet = regression(convnet, optimizer='adam', learning_rate=LR, loss='categorical_crossentropy', name='targets')
model = tflearn.DNN(convnet, tensorboard_dir='log')
if os.path.exists('{}.meta'.format(MODEL_NAME)):
model.load(MODEL_NAME)
print('model loaded!')
!pip3 install tflearn
import tflearn
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.estimator import regression
convnet = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 1], name='input')
convnet = conv_2d(convnet, 32, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)
convnet = conv_2d(convnet, 64, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)
convnet = fully_connected(convnet, 1024, activation='relu')
convnet = dropout(convnet, 0.8)
convnet = fully_connected(convnet, 2, activation='softmax')
convnet = regression(convnet, optimizer='adam', learning_rate=LR, loss='categorical_crossentropy', name='targets')
model = tflearn.DNN(convnet, tensorboard_dir='log')
if os.path.exists('{}.meta'.format(MODEL_NAME)):
model.load(MODEL_NAME)
print('model loaded!')
スポンサーリンク
モデルのトレーニング¶
train_data = np.load('download/data/train_data.npy')
train = train_data[:-500]
test = train_data[-500:]
X = np.array([i[0] for i in train]).reshape(-1,IMG_SIZE,IMG_SIZE,1)
Y = [i[1] for i in train]
test_x = np.array([i[0] for i in test]).reshape(-1,IMG_SIZE,IMG_SIZE,1)
test_y = [i[1] for i in test]
model.fit({'input': X}, {'targets': Y}, n_epoch=3, validation_set=({'input': test_x}, {'targets': test_y}),
snapshot_step=500, show_metric=True, run_id=MODEL_NAME)
import tensorflow as tf
tf.reset_default_graph()
#size matters - bigger network
convnet = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 1], name='input')
convnet = conv_2d(convnet, 32, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)
convnet = conv_2d(convnet, 64, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)
convnet = conv_2d(convnet, 128, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)
convnet = conv_2d(convnet, 64, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)
convnet = conv_2d(convnet, 32, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)
convnet = fully_connected(convnet, 1024, activation='relu')
convnet = dropout(convnet, 0.8)
convnet = fully_connected(convnet, 2, activation='softmax')
convnet = regression(convnet, optimizer='adam', learning_rate=LR, loss='categorical_crossentropy', name='targets')
model = tflearn.DNN(convnet, tensorboard_dir='log')
if os.path.exists('{}.meta'.format(MODEL_NAME)):
model.load(MODEL_NAME)
print('model loaded!')
train = train_data[:-500]
test = train_data[-500:]
X = np.array([i[0] for i in train]).reshape(-1,IMG_SIZE,IMG_SIZE,1)
Y = [i[1] for i in train]
test_x = np.array([i[0] for i in test]).reshape(-1,IMG_SIZE,IMG_SIZE,1)
test_y = [i[1] for i in test]
model.fit({'input': X}, {'targets': Y}, n_epoch=10, validation_set=({'input': test_x}, {'targets': test_y}),
snapshot_step=500, show_metric=True, run_id=MODEL_NAME)
model.save(MODEL_NAME)
import matplotlib.pyplot as plt
plt.rcParams['figure.figsize'] = 20, 15
plt.rcParams["font.size"] = "16"
# if you need to create the data:
test_data = process_test_data()
# if you already have some saved:
#test_data = np.load('test_data.npy')
fig=plt.figure()
for num,data in enumerate(test_data[:12]):
# cat: [1,0]
# dog: [0,1]
img_num = data[1]
img_data = data[0]
y = fig.add_subplot(3,4,num+1)
orig = img_data
data = img_data.reshape(IMG_SIZE,IMG_SIZE,1)
#model_out = model.predict([data])[0]
model_out = model.predict([data])[0]
if np.argmax(model_out) == 1: str_label='Dog'
else: str_label='Cat'
y.imshow(orig,cmap='gray')
plt.title(str_label)
y.axes.get_xaxis().set_visible(False)
y.axes.get_yaxis().set_visible(False)
plt.show()
検証精度が0.7940なので、間違いが結構ある。
スポンサーリンク
csvファイルの作成¶
with open('submission_file.csv','w') as f:
f.write('id,label\n')
with open('submission_file.csv','a') as f:
for data in tqdm(test_data):
img_num = data[1]
img_data = data[0]
orig = img_data
data = img_data.reshape(IMG_SIZE,IMG_SIZE,1)
model_out = model.predict([data])[0]
f.write('{},{}\n'.format(img_num,model_out[1]))
!head -n 11 submission_file.csv
import pandas as pd
pd.read_csv("submission_file.csv", nrows=11)
スポンサーリンク
スポンサーリンク