# l.set_weights(res_img.layers[i + 1].get_weights())
return model
# create callbacks list
from keras.callbacks import ModelCheckpoint, LearningRateScheduler, EarlyStopping, ReduceLROnPlateau, TensorBoard
from keras_callbacks import F1Metric
from keras_metrics import f1, f1_02
from keras_losses import f1_loss
epochs = [2, 120]
batch_size = 16
# split data into train, valid
mskf = MultilabelStratifiedKFold(n_splits=5, shuffle=True, random_state=18)
y = np.zeros((len(train_dataset_info), 28))
for i in range(len(train_dataset_info)):
y[i][train_dataset_info[i]['labels']] = 1
mskf.get_n_splits(train_dataset_info, y)
kf = mskf.split(train_dataset_info, y)
fold_id = 0
train_indexes, valid_indexes = next(kf)
train_generator = data_generator.create_train(
train_dataset_info[train_indexes],
batch_size, (SIZE, SIZE, 3),
augument=True,
heavy_augment_rares=False,
oversample_factor=0)
# l.set_weights(res_img.layers[i + 1].get_weights())
return model
# create callbacks list
from keras.callbacks import ModelCheckpoint, LearningRateScheduler, EarlyStopping, ReduceLROnPlateau, TensorBoard
from keras_callbacks import F1Metric
from keras_metrics import f1, f1_02
from keras_losses import f1_loss
epochs = [2, 100]
batch_size = 32
# split data into train, valid
mskf = MultilabelStratifiedKFold(n_splits=5, shuffle=True, random_state=18)
#y = np.zeros((len(train_dataset_info), 28))
#for i in range(len(train_dataset_info)):
# y[i][train_dataset_info[i]['labels']] = 1
#mskf.get_n_splits(train_dataset_info, y)
#kf = mskf.split(train_dataset_info, y)
train_indexes, valid_indexes = get_fold_ids(fold_id, train_dataset_info)
#train_indexes, valid_indexes = next(kf)
train_generator = data_generator.create_train(
train_dataset_info[train_indexes],
batch_size, (SIZE, SIZE, 3),
augument=True,
oversample_factor=3)
