python - 如何处理 CNN 训练 Keras 的数千张图像

Question

我有大约 10000k 图像无法放入内存。所以现在我只能读取 1000 张图像并对其进行训练...

我的代码在这里:

img_dir = "TrainingSet" # Enter Directory of all images 
image_path = os.path.join(img_dir+"/images",'*.bmp')
files = glob.glob(image_path)
images = []
masks = []
contours = []
indexes = []
files_names = []

for f1 in np.sort(files):
  img = cv2.imread(f1)
  result = re.search('original_cropped_(.*).bmp', str(f1))
  idx = result.group(1)
  mask_path = img_dir+"/masks/mask_cropped_"+str(idx)+".bmp"
  mask = cv2.imread(mask_path,0)
  contour_path = img_dir+"/contours/contour_cropped_"+str(idx)+".bmp"
  contour = cv2.imread(contour_path,0)

  indexes.append(idx)
  images.append(img)
  masks.append(mask)
  contours.append(contour)

train_df = pd.DataFrame({"id":indexes,"masks": masks, "images": images,"contours": contours })
train_df.sort_values(by="id",ascending=True,inplace=True)
print(train_df.shape)

img_size_target = (256,256)

ids_train, ids_valid, x_train, x_valid, y_train, y_valid, c_train, c_valid = train_test_split(
    train_df.index.values,
    np.array(train_df.images.apply(lambda x: cv2.resize(x,img_size_target).reshape(img_size_target[0],img_size_target[1],3))), 
    np.array(train_df.masks.apply(lambda x: cv2.resize(x,img_size_target).reshape(img_size_target[0],img_size_target[1],1))), 
    np.array(train_df.contours.apply(lambda x: cv2.resize(x,img_size_target).reshape(img_size_target[0],img_size_target[1],1))), 
    test_size=0.2, random_state=1337)

#Here we define the model architecture... 
#.....
#End of model definition

# Training 
optimizer = Adam(lr=1e-3,decay=1e-10)    
model.compile(loss="binary_crossentropy", optimizer=optimizer, metrics=["accuracy"])

early_stopping = EarlyStopping(patience=10, verbose=1)
model_checkpoint = ModelCheckpoint("./keras.model", save_best_only=True, verbose=1)
reduce_lr = ReduceLROnPlateau(factor=0.5, patience=5, min_lr=0.00001, verbose=1)

epochs = 200
batch_size = 32

history = model.fit(x_train, y_train,
                validation_data=[x_valid, y_valid], 
                epochs=epochs,
                batch_size=batch_size,
                callbacks=[early_stopping, model_checkpoint, reduce_lr])

我想知道的是如何修改我的代码以便批量处理一小部分图像而不将所有其他 10000 个图像加载到内存中？这意味着该算法将在每个时期从目录中读取 X 个图像并对其进行训练，然后再进行下一个 X 直到最后一个。

这里的 X 是可以放入内存的合理数量的图像。

Answer 1

使用fit_generator代替fit

def generate_batch_data(num):
    #load X images here
    return images

model.fit_generator(generate_batch_data(X),
        samples_per_epoch=10000, nb_epoch=10)

您可以使用train_on_batch代替fit

GitHub 上关于此主题的讨论:https://github.com/keras-team/keras/issues/2708