Я новичок в области глубокого обучения и тензорного потока, и я пытаюсь создать классификатор изображений с помощью тензорного потока, который будет классифицировать 5 классов изображений.
Мой обучающий набор данных содержит 25000 изображений, а тестовый набор данных - 5000 изображений.
ниже мой код:
import os
from random import shuffle
import cv2
import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf
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
from tqdm import tqdm
import keras
from keras.models import save_model
"""from keras.models import Sequential
from keras.layers import Dense"""
TRAIN_DIR = 'train'
TEST_DIR = 'test'
IMG_SIZE = 16
LR = 1e-3
MODEL_NAME = 'cifar 10 -convnet'
def create_label(image_name):
""" Create an one-hot encoded vector from image name """
word_label = image_name.split('.')[0:2]
if word_label == 'cat':
return np.array([1,0,0,0,0])
elif word_label == 'Dog':
return np.array([0,1,0,0,0])
elif word_label == 'Automobile':
return np.array([0,0,1,0,0])
elif word_label == 'Airplane':
return np.array([0,0,0,1,0])
elif word_label == 'Ship':
return np.array([0,0,0,0,1])
def create_train_data():
training_data = []
for img in tqdm(os.listdir(TRAIN_DIR)):
path = os.path.join(TRAIN_DIR, img)
img_data = cv2.imread(path, cv2.IMREAD_GRAYSCALE)
img_data = cv2.resize(img_data, (IMG_SIZE, IMG_SIZE))
training_data.append([np.array(img_data), create_label(img)])
shuffle(training_data)
np.save('train_data.npy', training_data)
return training_data
def create_test_data():
testing_data = []
for img in tqdm(os.listdir(TEST_DIR)):
path = os.path.join(TEST_DIR, img)
img_num = img.split('.')[0:2]
img_data = cv2.imread(path, cv2.IMREAD_GRAYSCALE)
img_data = cv2.resize(img_data, (IMG_SIZE, IMG_SIZE))
testing_data.append([np.array(img_data), img_num])
shuffle(testing_data)
np.save('test_data.npy', testing_data)
return testing_data
# If dataset is not created:
train_data = create_train_data()
test_data = create_test_data()
# If you have already created the dataset:
# train_data = np.load('train_data.npy')
# test_data = np.load('test_data.npy')
train = train_data[:25000]
test = train_data[:5000]
X_train = np.array([i[0] for i in train]).reshape(-1, IMG_SIZE, IMG_SIZE, 1)
y_train = [i[1] for i in train]
X_test = np.array([i[0] for i in test]).reshape(-1, IMG_SIZE, IMG_SIZE, 1)
y_test = [i[1] for i in test]
# Building The Model
tf.reset_default_graph()
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', tensorboard_verbose=0)
history = model.fit({'input': X_train}, {'targets': y_train}, n_epoch=25,
validation_set=({'input': X_test}, {'targets': y_test}),
snapshot_step=500, show_metric=True, run_id=MODEL_NAME)
#print(history.history.keys())
#plt.figure(1)
# summarize history for accuracy
"""plt.subplot(211)
plt.plot(history.history['acc'])
plt.plot(history.history['val_acc'])
plt.title('model accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'test1'], loc='upper left')
plt.show()"""
fig = plt.figure(figsize=(25, 12))
for num, data in enumerate(test_data[:25]):
img_num = data[1]
img_data = data[0]
y = fig.add_subplot(5, 5, num + 1)
orig = img_data
data = img_data.reshape(IMG_SIZE, IMG_SIZE, 1)
model_out = model.predict([data])[0]
if np.argmax(model_out) == 1:
str_label = 'Dog'
if np.argmax(model_out) == 2:
str_label = 'Automobile'
if np.argmax(model_out) == 3:
str_label = 'Airplane'
if np.argmax(model_out) == 4:
str_label = 'Ship'
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()
Я получаю следующую ошибку:
ValueError: Невозможно передать значение shape (64,) для Tensor 'target / Y: 0', имеющего форму '(?, 2)'
Может ли кто-нибудь помочь мне с этим?
заранее спасибо.