a30_pretrained_nets_pipeline_with_additional_data.py 文件源码

def run_cross_validation_create_models(cnn, nfolds, submission_version):
    from sklearn.cross_validation import KFold
    files = glob.glob(INPUT_PATH + "*/*.jpg")
    additional_files = glob.glob(INPUT_PATH_ADD + "*/*.jpg")
    kf = KFold(len(files), n_folds=nfolds, shuffle=True, random_state=get_random_state(cnn))
    num_fold = 0
    sum_score = 0
    print('Len of additional files: {}'.format(len(additional_files)))
    for train_index, test_index in kf:
        num_fold += 1
        print('Start KFold number {} from {}'.format(num_fold, nfolds))
        print('Split train: ', len(train_index))
        print('Split valid: ', len(test_index))

        score = train_single_model(cnn, num_fold, train_index, test_index, files, additional_files, submission_version)
        sum_score += score

    print('Avg loss: {}'.format(sum_score/nfolds))