Hi I have processed data in this format. There are 10 Folds each with 6 folders. In these folders there are labels of 0, 5 and 10 with their respective images. Does Tensorflow have any built in functionality to do this for me?
frames
├── Fold1_part1
│ ├── 01
│ │ ├── 0
│ │ │ ├── 00001.jpg
│ │ │ ├── 00006.jpg
│ │ │ ├── 00011.jpg
│ │ │ ├── 00016.jpg
│ │ │ ├── 00021.jpg
Found out how to do it but had to reorder the folder. I created new folders for each category and moved the images into them, then I used the code below:
test_datagen = ImageDataGenerator(
rescale=1. / 255,
rotation_range = 180,
width_shift_range = 0.2,
height_shift_range = 0.2,
brightness_range = (0.8, 1.2),
shear_range = 0.2,
zoom_range = 0.2,
horizontal_flip = True,
vertical_flip = True,
validation_split = 0.1
)
train_datagen = ImageDataGenerator(
rotation_range = 180,
width_shift_range = 0.2,
height_shift_range = 0.2,
brightness_range = (0.8, 1.2),
rescale = 1. / 255,
shear_range = 0.2,
zoom_range = 0.2,
horizontal_flip = True,
vertical_flip = True,
validation_split = 0.1
)
train_generator = train_datagen.flow_from_directory(
train_data_dir,
target_size = (img_width, img_height),
batch_size = batch_size,
class_mode ='binary',
seed = 42
)
validation_generator = test_datagen.flow_from_directory(
validation_data_dir,
target_size = (img_width, img_height),
batch_size = batch_size,
class_mode = 'binary',
seed = 42
)
history = 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)
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.