und zwar versuche ich gerade meinen Autoencoder in PyTorch zu rekonstruieren allerdings habe ich etwas Probleme beim laden der Daten bzw. Verständnisprobleme vlt. kann mir ja jmd auf die Sprünge helfen
TF/Keras:
Code: Alles auswählen
from tensorflow.keras.preprocessing.image import load_img, img_to_array
from sklearn.model_selection import train_test_split
train_images_path = '../denoising/train'
train_cleaned_path = '../denoising/train_cleaned'
train_images = sorted(os.listdir(train_images_path))
train_cleaned = sorted(os.listdir(train_cleaned_path))
x_train = []
y_train = []
for image in train_images:
img_path = os.path.join(train_images_path, image)
img = load_img(img_path, color_mode = 'grayscale', target_size = (420, 540))
img = img_to_array(img).astype('float32')/255
x_train.append(img)
for image in train_cleaned:
img_path = os.path.join(train_cleaned_path, image)
img = load_img(img_path, color_mode = 'grayscale', target_size = (420, 540))
img = img_to_array(img).astype('float32')/255
y_train.append(img)
x = np.array(x_train)
y = np.array(y_train)
x_train, x_valid, y_train, y_valid = train_test_split(x, y, test_size = 0.25)Code: Alles auswählen
from tensorflow.keras.preprocessing.image import load_img, img_to_array
from sklearn.model_selection import train_test_split
train_images_path = '../denoising/train'
train_cleaned_path = '../denoising/train_cleaned'
train_images = sorted(os.listdir(train_images_path))
train_cleaned = sorted(os.listdir(train_cleaned_path))
x_train = []
y_train = []
for image in train_images:
img_path = os.path.join(train_images_path, image)
img = load_img(img_path, color_mode = 'grayscale', target_size = (420, 540))
img = img_to_array(img).astype('float32')/255
x_train.append(img)
for image in train_cleaned:
img_path = os.path.join(train_cleaned_path, image)
img = load_img(img_path, color_mode = 'grayscale', target_size = (420, 540))
img = img_to_array(img).astype('float32')/255
y_train.append(img)
x = np.array(x_train)
y = np.array(y_train)
x_train, x_valid, y_train, y_valid = train_test_split(x, y, test_size = 0.25)
transform = transforms.Compose([
transforms.ToPILImage(),
transforms.ToTensor()
])
class ImageData(Dataset):
def __init__(self, images, labels=None, transforms=None):
self.X = images
self.y = labels
self.transforms = transforms
def __len__(self):
return (len(self.X))
def __getitem__(self, i):
data = self.X[i][:]
if self.transforms:
data = self.transforms(data)
if self.y is not None:
labels = self.y[i][:]
labels = self.transforms(labels)
return (data, labels)
else:
return data
train_data = ImageData(x_train, y_train, transform)
test_data = ImageData(x_valid, None, transform)
train_loader = DataLoader(train_data, batch_size=BATCH_SIZE)
test_loader = DataLoader(test_data, batch_size=BATCH_SIZE)Ich hatte in der Docu gesehen das es eine ImageFolder Klasse gibt:
https://pytorch.org/docs/stable/torchvi ... magefolder
2. angenommen ich möchte jedem Bild ein Label zuweisen
Keras:
Code: Alles auswählen
for f in os.listdir(best_doc_dir):
img_file = os.path.join(best_doc_dir, f)
try:
img = load_img(img_file, color_mode = 'grayscale', target_size = (IMG_HEIGHT, IMG_WIDTH))
img = img_to_array(img).astype('float32')/255
x[cnt] = img
y[cnt] = BEST_CLASS_IDX
cnt += 1
except:
print("best document image %s cannot be read!" % f)
# Dropping not readable image idxs
x = x[:cnt]
y = y[:cnt]
np.save(os.path.join(FILE_DIR, "x.npy"), x)
np.save(os.path.join(FILE_DIR, "y.npy"), y)Da diese DataLoader ja anscheinend über die Daten iterieren ohne das ich irgendwie darauf einwirken kann (außer durch CustomDataLoader) gibt es da eine Alternative ?
Vielen Dank für eure Hilfe
