Diyago

"""
LightGBM vs TabM binary-classification benchmark with optimized training
Requirements: pip install lightgbm tabm torch pandas scikit-learn tqdm
!git clone https://github.com/Diyago/Tabular-data-generation.git
!mv Tabular-data-generation/Research/data/* data/

"""
"""
LightGBM vs TabM vs RealMLP binary-classification benchmark with optimized training
Requirements: pip install lightgbm tabm torch pandas scikit-learn tqdm "pytabkit[models]"

Diyago

class SimpleGNN(torch.nn.Module):
    """Original from http://pages.di.unipi.it/citraro/files/slides/Landolfi_tutorial.pdf"""
    def __init__(self, dataset, hidden=64, layers=6):
        super(SimpleGNN, self).__init__()
        self.dataset = dataset
        self.convs = torch.nn.ModuleList()
        self.convs.append(GCNConv(in_channels=dataset.num_node_features,
                                  out_channels=hidden))

        for _ in range(1, layers):

Diyago

augmented = aug_with_crop(image_size = 1024)(image=img, mask=mask)
image_aug = augmented['image']
mask_aug = augmented['mask']

Diyago

def aug_with_crop(image_size = 256, crop_prob = 1):
    return Compose([
        RandomCrop(width = image_size, height = image_size, p=crop_prob),
        HorizontalFlip(p=0.5),
        VerticalFlip(p=0.5),
        RandomRotate90(p=0.5),
        Transpose(p=0.5),
        ShiftScaleRotate(shift_limit=0.01, scale_limit=0.04, rotate_limit=0, p=0.25),
        RandomBrightnessContrast(p=0.5),
        RandomGamma(p=0.25),

Diyago

model = Unet(backbone_name = 'efficientnetb0', encoder_weights='imagenet', encoder_freeze = False)
model.compile(optimizer = Adam(), loss=bce_jaccard_loss, metrics=[iou_score])

history = model.fit_generator(train_generator, shuffle =True,
                  epochs=50, workers=4, use_multiprocessing=True,
                  validation_data = test_generator, 
                  verbose = 1, callbacks=callbacks)

Diyago

from keras.callbacks import ModelCheckpoint, ReduceLROnPlateau, EarlyStopping, TensorBoard

# reduces learning rate on plateau
lr_reducer = ReduceLROnPlateau(factor=0.1,
                               cooldown= 10,
                               patience=10,verbose =1,
                               min_lr=0.1e-5)
# model autosave callbacks
mode_autosave = ModelCheckpoint("./weights/road_crop.efficientnetb0imgsize.h5", 
                                monitor='val_iou_score', 

Diyago

test_generator = DataGeneratorFolder(root_dir = './data/road_segmentation_ideal/training', 
                           image_folder = 'input/', 
                           mask_folder = 'output/', 
                           nb_y_features = 1)

train_generator = DataGeneratorFolder(root_dir = './data/road_segmentation_ideal/training', 
                                      image_folder = 'input/', 
                                      mask_folder = 'output/', 
                                      batch_size=4,
                                      image_size=512,

Diyago

def __getitem__(self, index):
      data_index_min = int(index*self.batch_size)
      data_index_max = int(min((index+1)*self.batch_size, len(self.image_filenames)))

      indexes = self.image_filenames[data_index_min:data_index_max]
      this_batch_size = len(indexes) # The last batch can be smaller than the others

      X = np.empty((this_batch_size, self.image_size, self.image_size, 3), dtype=np.float32)
      y = np.empty((this_batch_size, self.image_size, self.image_size, self.nb_y_features), dtype=np.uint8)

Diyago

def __init__(self, root_dir=r'../data/val_test', image_folder='img/', mask_folder='masks/', 
             batch_size=1, image_size=768, nb_y_features=1, 
             augmentation=None,
             suffle=True):
    self.image_filenames = listdir_fullpath(os.path.join(root_dir, image_folder))
    self.mask_names = listdir_fullpath(os.path.join(root_dir, mask_folder))
    self.batch_size = batch_size
    self.augmentation = augmentation
    self.image_size = image_size
    self.nb_y_features = nb_y_features

Diyago

conda install -c conda-forge keras
pip install git+https://github.com/qubvel/efficientnet
pip install git+https://github.com/qubvel/classification_models.git
pip install git+https://github.com/qubvel/segmentation_models
pip install git+https://github.com/albu/albumentations
pip install tta-wrapper