def predict(learn: Learner, name: str):
# submission.csv
preds, _ = learn.get_preds(ds_type=DatasetType.Test)
test['has_cactus'] = preds.numpy()[:, 0]
test.to_csv('submission_{}.csv'.format(name), index=False)
print('Finish creating submission_{}.csv'.format(name))
# loss.csv
id_ = range(len(learn.recorder.losses))
loss_df = pd.DataFrame({
'id': id_,
'loss': np.array(learn.recorder.losses)
})
loss_df.to_csv('loss_{}.csv'.format(name), index=False)
print('Finish creating loss_{}.csv'.format(name))
# Calculate some metrics on the training set
preds, targets = learn.get_preds(ds_type=DatasetType.Train)
preds_label = np.argmax(preds.numpy(), axis=1)
id_ = range(len(preds))
train_pred_df = pd.DataFrame({
'id': id_,
'preds': preds.numpy()[:, 0],
'preds_label': preds_label,
'targets': targets.numpy()
})
train_pred_df.to_csv('./train_pred_{}.csv'.format(name))
print('Finish creating train_pred_{}.csv'.format(name))
correct_count = np.equal(preds_label, targets.numpy()).sum()
len_preds = len(preds)
incorrect_count = len_preds - correct_count
fpr, tpr = metrics.roc_curve(preds[:, 0], targets)
fpr, tpr = fpr.numpy(), tpr.numpy()
FP = np.floor(fpr * len_preds)
FN = incorrect_count - FP
TP = np.floor(tpr * len_preds)
TN = correct_count - TP
id_ = range(len(fpr))
train_index_df = pd.DataFrame({
'id': id_,
'fpr': fpr,
'tpr': tpr,
'TP': TP,
'TN': TN,
'FP': FP,
'FN': FN
})
train_index_df.to_csv('./train_index_{}.csv'.format(name))
print('Finish creating train_index_{}.csv'.format(name))
# Destroy learn and save the model
learn.export('./model_{}.pth'.format(name), destroy=True)
def save_learner(learn: Learner,
with_focal_loss=False,
with_oversampling=False,
sample_size=None,
with_weighted_loss=False):
postfix = _get_postfix(with_focal_loss, with_oversampling, sample_size,
with_weighted_loss)
save_file_name = f'{config.PIPELINE_SAVE_FILE}{_version}{postfix}.pkl'
save_path = config.TRAINED_MODEL_DIR / save_file_name
learn.export(save_path)
# fix bug in fastai, missing layer_groups
joblib.dump(learn.layer_groups, f'{save_path}_layer_groups')
