【发布时间】：2021-01-11 19:21:24
【问题描述】：
我有 100 多个本身包含多个图像的 tif 文件。我想创建一个二元分类器。首先，我将所有 tif 分解为 png 图像（例如，2 个 tif 文件分别包含 20 和 30 个图像，然后在另一个目录中转换为 50 个 png 图像（600 x 600））。然后，我在上面应用了 CNN，但结果并不达标。 tif 的图像本质上是连续的，并且包含可能与分类目的相关的重要信息。 现在，我正在尝试为此目的应用 CNN+LSTM。我有一个包含文件名和标签的 csv 文件，我正在使用 ImageGenerator 的 flow_from_Dataframe 来加载数据。这是代码：-
img_width, img_height = 600, 600
no_frame = 5
original_train = "PATH TO IMAGES"
nb_training_samples = 6587
nb_validation_samples = 1646
epochs = 1
batch_size = 32
lr = 0.001
if k.image_data_format() == "channels_first":
input_shape = (3,img_width,img_height)
else:
input_shape = (img_width, img_height,3)
METRICS = [
metrics.TruePositives(name='tp'),
metrics.FalsePositives(name='fp'),
metrics.TrueNegatives(name='tn'),
metrics.FalseNegatives(name='fn'),
metrics.BinaryAccuracy(name='accuracy'),
metrics.Precision(name='precision'),
metrics.Recall(name='recall'),
metrics.AUC(name='auc'),
]
model = Sequential()
model.add(ConvLSTM2D(filters = 32, kernel_size=(3,3),
activation='relu',
return_sequences=True,
padding='same',
input_shape=(None,img_width, img_height,3)))
model.add(BatchNormalization())
model.add(ConvLSTM2D(64,(3,3), activation='relu',padding='same'))
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(2))
model.add(Activation('sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='rmsprop', metrics=METRICS)
model.summary()
Model: "sequential_5"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv_lst_m2d_10 (ConvLSTM2D) (None, None, 600, 600, 32 40448
_________________________________________________________________
batch_normalization_9 (Batch (None, None, 600, 600, 32 128
_________________________________________________________________
conv_lst_m2d_11 (ConvLSTM2D) (None, 600, 600, 64) 221440
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 300, 300, 64) 0
_________________________________________________________________
flatten_3 (Flatten) (None, 5760000) 0
_________________________________________________________________
dense_4 (Dense) (None, 64) 368640064
_________________________________________________________________
activation_2 (Activation) (None, 64) 0
_________________________________________________________________
dropout_2 (Dropout) (None, 64) 0
_________________________________________________________________
dense_5 (Dense) (None, 2) 130
_________________________________________________________________
activation_3 (Activation) (None, 2) 0
=================================================================
Total params: 368,902,210
Trainable params: 368,902,146
Non-trainable params: 64
_________________________________________________________________
datagen = ImageDataGenerator(rescale=1/255., validation_split=0.2)
train_generator = datagen.flow_from_dataframe(dataframe=data, directory=original_train,
x_col='Id',
y_col='label',
target_size=(img_width,img_height),
class_mode='categorical',
batch_size=batch_size,
subset='training',
seed=7)
print(train_generator.class_indices)
validation_generator = datagen.flow_from_dataframe(dataframe=data, directory=original_train,
x_col='Id',
y_col='label',
target_size=(img_width,img_height),
class_mode='categorical',
batch_size=batch_size,
subset='validation',
seed=7)
print(validation_generator.class_indices)
train_steps = train_generator.n//train_generator.batch_size
validation_steps = validation_generator.n//validation_generator.batch_size
history = model.fit_generator(train_generator,steps_per_epoch=train_steps, epochs=epochs,
validation_data=validation_generator,validation_steps=validation_steps)
在此之后我收到此错误：-
ValueError: Error when checking input: expected conv_lst_m2d_10_input to have 5 dimensions, but got array with shape (32, 600, 600, 3)
我对此有几个疑问：-
- 如何解决此错误？
- 如何将一个 tif 作为批次传递？由于单个 tif 中的图像数量不同。
任何帮助都是可观的。
谢谢:)
编辑 1：
我创建了一个自定义生成器，如下所示：
class DataGenerator(Sequence):
def __init__(self, list_IDs, labels, image_path, to_fit=True, batch_size=32, dim=(5,600,600),
n_channel=1, n_classes=2, shuffle=True):
self.list_IDs = list_IDs
self.labels = labels
self.image_path = image_path
self.to_fit = to_fit
self.batch_size = batch_size
self.dim = dim
self.n_channel = n_channel
self.n_classes = n_classes
self.shuffle = shuffle
self.on_epoc_end()
def __len__(self):
return int(np.floor(len(self.list_IDs)/self.batch_size))
def __getitem__(self,index):
indexes = self.indexes[index * self.batch_size:(index+1)*self.batch_size]
list_IDs_temp = [self.list_IDs[k] for k in indexes]
X,y = self._generate_data(list_IDs_temp)
return X,y
def on_epoc_end(self):
self.indexes = np.arange(len(self.list_IDs))
if self.shuffle == True:
np.random.shuffle(self.indexes)
def _generate_data(self, list_IDs_temp):
X = np.empty((self.batch_size, *self.dim, self.n_channel))
y = np.empty((self.batch_size), dtype = np.uint8)
for i, ID in enumerate(list_IDs_temp):
X[i,] = self._load_grayscale_image(self.image_path + ID)
y[i] = self.labels[i]
return X, y
def _load_grayscale_image(self,image_path):
img = cv2.imread(image_path+'.png')
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
img = img / 255
img = img[:,:,np.newaxis]
return img
并加载数据
def loadData(filepath, val_sample=0.2):
data = pd.read_csv(filepath)
image_IDs = data['Id'].values
labels = data['label'].values
X_train, X_test, Y_train, Y_test = train_test_split(image_IDs, labels, test_size=val_sample, shuffle=False)
train_data = DataGenerator(X_train, Y_train,image_path = original_train, batch_size = batch_size, shuffle=False)
val_data = DataGenerator(X_test,Y_test,image_path = original_train, batch_size = batch_size, shuffle=False)
return train_data,val_data
但是在获得适合模型的形状后，它的捐赠：-
ValueError: Error when checking input: expected reshape_2_input to have 4 dimensions, but got array with shape (32, 5, 600, 600, 1)
【问题讨论】：
标签： python tensorflow image-processing keras lstm