Question

我是keras的新手。我已经从其中一个示例中采用了我的模型，并且它的效果出奇地好。突然，我的模型开始总是只预测很多班中的一个班。我认为，我对该模型所做的唯一更改是添加了更多样本。现在我迷路了，不知道如何找出原因。有人可以告诉我从哪里开始以及要检查什么吗？

以防万一，这里是代码。该应用程序从vew分类的图像中学习，以对其余未分类的图像进行分类。图像看起来像这样，训练集中每个班800个，测试集中每个班300个。验证和测试是相同的集合。

import numpy as np
from keras.models import model_from_json
from keras.preprocessing import image
import os
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense
from keras import backend as K
from shutil import copyfile

# dimensions of the images.
img_width, img_height = 64, 64
input_dirs = [
    #list of dirs to sort with model,
]
out_directory = 'dir_of_auto_sorted_images'
train_base = 'dir_with_training_images'
train_dir = 'train'
val_dir = 'test'
test_dir = 'test'

nb_train_samples = 800*5 #800 training images per class, flipped V/H and zoomed in generator
nb_validation_samples = 1000 #just a number
nb_test_samples = 300*5
epochs = 100
batch_size = 32


#Read class names from training dir. In test in val they should be the same
tmp = os.path.join(train_base, train_dir)
classes = os.listdir(tmp)
classes.sort() #Classes in prediction seem to be sorted by dir_name

for c in classes: #Create output for predicted, where to copy unsorted from model
    try:
        os.makedirs(os.path.join(out_directory,c))
    except:
        pass

#############################


# Is right got gray-scale images? Shouldn't be 1 instead of 3
if K.image_data_format() == 'channels_first':
    input_shape = (1, img_width, img_height)
else:
    input_shape = (img_width, img_height, 1)

# Define model as proposed in keras tutorials
model = Sequential()
model.add(Conv2D(64, (3, 3), input_shape=input_shape))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(128, (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(len(classes), activation='softmax'))
model.add(Activation('sigmoid'))

CreateModel = 1
if CreateModel:
model.compile(loss='categorical_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])

test_datagen = ImageDataGenerator(
    zoom_range=0.2,
    horizontal_flip=True,
    vertical_flip=True)

train_datagen = ImageDataGenerator(
    zoom_range=0.2,
    horizontal_flip=True,
    vertical_flip=True)

train_generator = train_datagen.flow_from_directory(
    os.path.join(train_base, train_dir),
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='categorical',
    color_mode='grayscale',
    #save_to_dir=out_directory+"\\gendebug"
)

validation_generator = train_datagen.flow_from_directory(
    os.path.join(train_base, val_dir),
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='categorical',
    color_mode='grayscale'
)

test_generator = test_datagen.flow_from_directory(
    os.path.join(train_base, test_dir)
    , target_size=(img_width, img_height)
    , batch_size=batch_size
    , class_mode='categorical',
    color_mode='grayscale'
    # ,save_to_dir=out_dir
)

model.fit_generator(
    train_generator,
    steps_per_epoch=nb_train_samples // batch_size,
    epochs=epochs,
    validation_data=validation_generator,
    validation_steps=nb_validation_samples // batch_size)

# Save model architecture
model_json = model.to_json()
json_file = open(train_base+"/keras_model.json", "w")
json_file.write(model_json)
json_file.close()

# Save model weights
model.save_weights(train_base+"/keras_model.h5")
print("Finished saving")

score = model.evaluate_generator(test_generator, nb_test_samples // batch_size)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

score = model.predict_generator(train_generator, nb_test_samples // batch_size)

print('Test loss:', score[0])
print('Test accuracy:', score[1])
print('Score', score)
#############################


json_file = open(train_base+"/keras_model.json", "r")
loaded_model_json = json_file.read()
json_file.close()
loaded_model = model_from_json(loaded_model_json)
loaded_model.load_weights(train_base+"/keras_model.h5")

loaded_model.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['accuracy'])


def get_class(prediction):
    m=max(prediction)
    if m < 0.6:
        return -1

    for i in range(0, len(prediction)):
        if prediction[i] == m:
            return i
    return -1


    right = 0
    wrong = 0





for input_directory in input_dirs:
    print(input_directory)
    cnt=0
    for filename in os.listdir(input_directory):
        os.sys.stdout.write('.')
        os.sys.stdout.flush()
        fn = os.path.join(input_directory, filename)
        img = image.load_img(fn, target_size=(64, 64), color_mode='grayscale')

        x = image.img_to_array(img)
        x = x.astype('float32')
        x /= 255
        x = np.expand_dims(x, axis=0)

        prediction = loaded_model.predict(x)[0]
        c = get_class(prediction)
        if c >= 0 and c < len(prediction):
            predicted = classes[c]
            print(fn, prediction)

            copyfile(fn, os.path.join(out_directory,predicted, filename))
            cnt += 1
            if cnt > 100:
                break

凯拉斯预测只有3个班级有一个班级

0 个答案: