我正在使用Keras和Python进行分类和物体检测,已经成功将猫/狗的分类准确率达到80%以上,暂时对此结果满意。我的问题是如何从输入图像中检测猫或狗?我感到完全困惑。我想使用自己的高度而不是从互联网上预训练的高度。
这是目前我的代码:
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Convolution2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense
import numpy as np
import matplotlib.pyplot as plt
import matplotlib
from keras.preprocessing.image import ImageDataGenerator, array_to_img, img_to_array, load_img
#########################################################################################################
#VALUES
# dimensions of our images.
img_width, img_height = 150, 150
train_data_dir = 'data/train'
validation_data_dir = 'data/validation'
nb_train_samples = 2000 #1000 cats/dogs
nb_validation_samples = 800 #400cats/dogs
nb_epoch = 50
#########################################################################################################
#MODEL
model = Sequential()
model.add(Convolution2D(32, 3, 3, input_shape=(3, img_width, img_height)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Convolution2D(32, 3, 3))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Convolution2D(64, 3, 3))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
# this is the augmentation configuration we will use for training
train_datagen = ImageDataGenerator(
rescale=1./255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
##########################################################################################################
#TEST AUGMENTATION
img = load_img('data/train/cats/cat.0.jpg') # this is a PIL image
x = img_to_array(img) # this is a Numpy array with shape (3, 150, 150)
x = x.reshape((1,) + x.shape) # this is a Numpy array with shape (1, 3, 150, 150)
# the .flow() command below generates batches of randomly transformed images
# and saves the results to the `preview/` directory
i = 0
for batch in train_datagen.flow(x, batch_size=1,
save_to_dir='data/TEST AUGMENTATION', save_prefix='cat', save_format='jpeg'):
i += 1
if i > 20:
break # otherwise the generator would loop indefinitely
##########################################################################################################
# this is the augmentation configuration we will use for testing:
# only rescaling
test_datagen = ImageDataGenerator(rescale=1./255)
#PREPARE TRAINING DATA
train_generator = train_datagen.flow_from_directory(
train_data_dir, #data/train
target_size=(img_width, img_height), #RESIZE to 150/150
batch_size=32,
class_mode='binary') #since we are using binarycrosentropy need binary labels
#PREPARE VALIDATION DATA
validation_generator = test_datagen.flow_from_directory(
validation_data_dir, #data/validation
target_size=(img_width, img_height), #RESIZE 150/150
batch_size=32,
class_mode='binary')
#START model.fit
history =model.fit_generator(
train_generator, #train data
samples_per_epoch=nb_train_samples,
nb_epoch=nb_epoch,
validation_data=validation_generator, #validation data
nb_val_samples=nb_validation_samples)
model.save_weights('savedweights.h5')
# list all data in history
print(history.history.keys())
#ACC VS VAL_ACC
plt.plot(history.history['acc'])
plt.plot(history.history['val_acc'])
plt.title('model accuracy ACC VS VAL_ACC')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()
# summarize history for loss
#LOSS VS VAL_LOSS
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('model loss LOSS vs VAL_LOSS')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()
model.load_weights('first_try.h5')
现在我已将猫和狗分类,接下来我需要怎么做才能输入一张图片,并对其进行处理以找到其中的猫或狗,并用边界框标出来呢?我完全是新手,甚至不确定我是否以正确的方式解决了这个问题。 谢谢。
更新 抱歉晚些才发布结果,前几天无法工作。 我正在导入一张图像并将其重塑为1,3,150,150的形状,因为150,150的形状会出现错误:
Exception: Error when checking : expected convolution2d_input_1 to have 4 dimensions, but got array with shape (150L, 150L)
导入图像:
#load test image
img=load_img('data/prediction/cat.155.jpg')
#reshape to 1,3,150,150
img = np.arange(1* 150 * 150).reshape((1,3,150, 150))
#check shape
print(img.shape)
然后我已经将def predict_function(x)更改为:
def predict_function(x):
# example of prediction function for simplicity, you
# should probably use `return model.predict(x)`
# random.seed(x[0][0])
# return random.random()
return model.predict(img)
现在当我运行:
best_box = get_best_bounding_box(img, predict_function)
print('best bounding box %r' % (best_box, ))
我得到的输出为最佳边界框:无
所以我只运行了:
model.predict(img)
并获得以下内容:
model.predict(img)
Out[54]: array([[ 0.]], dtype=float32)
所以它根本不检查是猫还是狗... 有什么想法吗?
注意:当def predict()function(x)使用时:
random.seed(x[0][0])
return random.random()
我确实得到输出结果,它勾选复选框并选择最佳结果。