| import joblib |
| import random |
| import numpy as np |
| from tqdm import tqdm |
|
|
| data_root = 'data/final_data' |
| all_data = [] |
| all_g1_motion = [] |
| all_smplx_motion = [] |
| with open(f'{data_root}/all.txt', 'r') as f: |
| data_paths = f.readlines() |
| for data_path in tqdm(data_paths): |
| data = joblib.load(data_path.strip()) |
| all_data.append(data) |
| all_g1_motion.append(data['g1_motion']) |
| all_smplx_motion.append(data['smplx_motion']) |
|
|
| g1_data = np.concatenate(all_g1_motion, axis=0) |
| Mean = g1_data.mean(axis=0) |
| Std = g1_data.std(axis=0) |
| joints_num = 30 |
| Std[:2] = Std[:2].mean() / 1.0 |
| Std[2:8] = Std[2:8].mean() / 1.0 |
| Std[8:8+3*joints_num] = Std[8:8+3*joints_num].mean() / 1.0 |
| Std[8+3*joints_num:8+6*joints_num] = Std[8+3*joints_num:8+6*joints_num].mean() / 1.0 |
| Std[8+6*joints_num:] = Std[8+6*joints_num:].mean() / 1.0 |
| np.save(f'{data_root}/g1_mean.npy', Mean) |
| np.save(f'{data_root}/g1_std.npy', Std) |
|
|
| smplx_data = np.concatenate(all_smplx_motion, axis=0) |
| Mean = smplx_data.mean(axis=0) |
| Std = smplx_data.std(axis=0) |
| joints_num = 22 |
| Std[:2] = Std[:2].mean() / 1.0 |
| Std[2:8] = Std[2:8].mean() / 1.0 |
| Std[8:8+3*joints_num] = Std[8:8+3*joints_num].mean() / 1.0 |
| Std[8+3*joints_num:8+6*joints_num] = Std[8+3*joints_num:8+6*joints_num].mean() / 1.0 |
| Std[8+6*joints_num:] = Std[8+6*joints_num:].mean() / 1.0 |
| np.save(f'{data_root}/smplx_mean.npy', Mean) |
| np.save(f'{data_root}/smplx_std.npy', Std) |
|
|
| random.shuffle(all_data) |
| random.shuffle(all_data) |
| random.shuffle(all_data) |
| random.shuffle(all_data) |
| random.shuffle(all_data) |
| joblib.dump(all_data[:12500], f'{data_root}/train.pkl') |
| joblib.dump(all_data[12500:], f'{data_root}/test.pkl') |
