Upload 30 files

src/static/betas.txt

@@ -0,0 +1,34 @@
+# FEMALE
+Predicted bestas for Petite_Slim
+[-2.405284   -1.5530001  -0.24272324 -1.443513   -0.90185016  1.2732644
+ -0.36933944 -0.05060475 -2.3866267  -0.5039462 ]
+Predicted bestas for Average_Fit
+[-1.3060766  -1.6338427   0.70017195 -0.17132899 -1.1940454   0.29538375
+  0.14818205  0.6067093  -1.2169323  -0.39638677]
+Predicted bestas for Athletic_Tall
+[ 0.22818007 -1.1036383  -1.5221908   0.73692316 -0.35802472  0.948243
+ -0.03018424  0.55922085 -0.16469094 -1.558347  ]
+Predicted bestas for Curvy_Plus
+[-0.5351595  -0.6430263   1.4178932   0.7848561   0.29656753  0.00878574
+  0.9825444  -0.5219289   0.40674126  0.18135245]
+Predicted bestas for Big_and_Heavy
+[ 1.8121121  0.3021033  1.3633814  1.6494894  2.1491473  0.9186887
+  0.9121304 -1.3406857  2.321915  -1.0636625]
+
+
+# MALE
+Predicted bestas for Male_Skinny_Short
+[-0.7108757  -0.7559417  -0.94977564 -0.5261638  -1.7385905  -0.6821138
+ -3.8808734  -1.083193   -0.30184665  0.64134985]
+Predicted bestas for Male_Standard
+[ 0.5232158  -0.6872696  -1.1425025   0.7785673  -1.8967177  -0.9401324
+  0.06393365 -0.3843205  -0.50072473 -0.5430138 ]
+Predicted bestas for Male_V_Shape
+[ 1.1519345   0.38004422 -1.7919775  -0.37787473 -0.1616468   0.6167449
+  0.59436065 -0.7820431  -1.8210857  -0.37498614]
+Predicted bestas for Male_Stocky_Rect
+[ 0.2341475  -0.22931805  1.9749473  -0.05317437 -1.4906491  -2.5173957
+  0.04375501  0.03236455 -0.23340486  0.4409504 ]
+Predicted bestas for Male_Giant_Heavy
+[ 2.932486    0.4136964   1.1478211   1.5842791   1.3554143  -1.7326043
+  1.195378   -1.1438893   0.8729984  -0.06384684]

src/static/poses.txt

@@ -0,0 +1,106 @@
+[ 2.3752,  0.0658, -1.7781, -0.1833,  0.0058, -0.1768, -0.4969,  0.3412,
+0.1805,  0.2078, -0.0801,  0.0113,  0.7961, -0.0638, -0.0320,  1.1230,
+0.1120,  0.0431, -0.0053, -0.0622, -0.1404, -0.0399,  0.1543, -0.0574,
+0.1719, -0.1349,  0.1215, -0.0742,  0.0198, -0.2016, -0.1918,  0.0664,
+0.1843, -0.1893, -0.0836, -0.2172,  0.3527, -0.0895,  0.0831,  0.1069,
+-0.6679, -0.3409, -0.4127,  0.2049, -0.5758,  0.4160,  0.2027,  0.0371,
+-0.0056, -0.8203, -0.7385, -0.5755,  0.6557,  0.1240,  0.3627, -1.5995,
+0.2493, -0.1409,  1.3971, -0.2052, -0.0726, -0.5489,  0.4632,  0.0383,
+0.4377, -0.3150,  0.0867, -0.0317, -0.0694,  0.0872,  0.0519,  0.1608]
+
+[ 3.0614e+00,  6.2280e-02, -7.6650e-03, -1.4160e-01, -5.1097e-02,
+5.0161e-02, -1.3916e-01, -7.7943e-02, -1.4492e-03,  1.0476e-01,
+1.9706e-02, -5.5241e-02,  4.3114e-01, -2.3592e-03,  1.0349e-01,
+3.8765e-01, -5.6183e-01, -2.5906e-01, -1.0401e-01, -3.5997e-02,
+3.2958e-02,  1.1873e-01,  2.8326e-01,  9.6266e-02, -1.7527e-02,
+-4.6820e-01,  4.8134e-03, -3.4153e-03,  3.1733e-02,  7.2645e-02,
+-1.3809e-01, -2.2420e-02,  3.7563e-01, -1.1704e-01,  3.8316e-02,
+-3.5116e-01,  2.1393e-01, -9.0961e-02,  2.1819e-02, -2.2145e-01,
+-8.2792e-02,  4.7571e-01, -3.4885e-01,  1.5275e-01, -3.7524e-01,
+1.9898e-01, -5.6398e-02,  1.5147e-01, -3.6606e-01, -5.0230e-01,
+3.5257e-01, -5.7167e-01,  3.5682e-01, -1.2872e-01,  5.8685e-02,
+-2.1642e+00,  6.4898e-01, -2.4495e-01,  2.1219e+00, -7.5819e-01,
+-4.4861e-01, -4.6142e-01, -1.9626e-01, -3.5913e-01,  4.2019e-01,
+2.7658e-01,  1.7639e-01, -5.2321e-02, -1.1038e-01,  1.2812e-01,
+6.4935e-02,  2.2037e-01]
+
+[ 2.9954,  0.0478, -0.0210, -0.0661, -0.4360,  0.0570, -0.2681,  0.2788,
+-0.0715,  0.2030,  0.0093, -0.1145,  0.2436, -0.0254, -0.1626,  0.5336,
+-0.0321,  0.2793,  0.0192,  0.0449,  0.0101, -0.0073,  0.1966, -0.0735,
+0.0612, -0.1001,  0.1643,  0.1277,  0.0090,  0.0318, -0.1977,  0.0466,
+0.2682, -0.1723, -0.0298, -0.2414, -0.0103, -0.0858,  0.0773,  0.0530,
+-0.0082,  0.0819,  0.0522,  0.1311,  0.1491,  0.1614, -0.0862,  0.0777,
+0.3365, -0.4108, -1.1308,  0.3167,  0.3025,  0.9944,  0.5398, -1.5167,
+-0.0472,  0.3905,  1.4840, -0.1251, -0.2937, -0.1276,  0.0920, -0.2136,
+0.1464,  0.0138, -0.2083, -0.0330, -0.1633, -0.1662,  0.1062,  0.1335]
+
+[ 3.0080,  0.0306, -0.2129, -0.0872,  0.0768,  0.0630, -0.7311, -0.2889,
+-0.4064,  0.2019,  0.0288, -0.0278,  0.4179, -0.1456, -0.0833,  1.8403,
+-0.1916,  0.4140, -0.0385,  0.0567,  0.0509, -0.2573,  0.3238,  0.0203,
+-0.1047, -0.2087,  0.3207, -0.0567, -0.0078,  0.0251, -0.2247,  0.0581,
+0.3587, -0.2693,  0.0096, -0.3148,  0.3628,  0.0998,  0.0767, -0.3403,
+0.1187,  0.3583, -0.3395, -0.0055, -0.2204,  0.2906,  0.0092,  0.0590,
+-0.2578, -0.2382,  0.3031, -0.2698,  0.3195, -0.2413, -0.0659, -2.2600,
+0.8711, -0.1026,  2.1879, -0.8472, -0.2476, -0.3128,  0.0327, -0.0614,
+0.2795,  0.1144, -0.1259, -0.0362, -0.2552, -0.0544,  0.1021,  0.0793]
+
+[-4.4739e-02, -2.5408e-01,  3.0967e+00, -3.2824e-03,  2.9921e-02,
+1.7044e-02, -6.2180e-02,  2.2239e-02, -2.2721e-02,  1.7281e-01,
+-4.6111e-02,  7.4796e-02,  2.1117e-01, -1.6837e-01,  2.9683e-02,
+5.8315e-01,  7.6520e-02,  5.6352e-02, -1.1508e-01, -2.0811e-02,
+3.2421e-02,  3.9826e-01,  3.4520e-01, -2.0537e-01,  3.8679e-01,
+-3.0132e-01,  1.6660e-01,  3.5923e-02,  3.8529e-04, -5.1066e-02,
+-1.0309e-01, -1.7867e-02,  2.7689e-01, -9.9123e-02,  4.2380e-02,
+-2.7752e-01, -3.2211e-01, -2.2977e-02, -4.1069e-04, -2.9728e-01,
+-2.5900e-01,  3.1511e-01, -2.7042e-01,  2.6003e-01, -3.3097e-01,
+-2.2513e-01, -3.0654e-03,  6.8447e-02, -3.8446e-01, -2.3619e-01,
+-3.3112e-02, -3.7500e-01,  1.8820e-01,  1.4296e-02, -3.6162e-01,
+-1.2229e+00,  4.3001e-01, -3.5856e-01,  1.2067e+00, -4.0485e-01,
+1.6419e-01, -3.9610e-01,  2.3677e-01,  5.5694e-02,  3.8777e-01,
+-2.1233e-01,  2.2479e-01, -2.9042e-02, -8.7811e-02,  2.0511e-01,
+9.6519e-03, -4.0550e-02]
+
+[ 1.7333, -0.0567,  2.4417, -0.0180, -0.0489,  0.0498, -1.3883,  0.3772,
+0.1170,  0.4974, -0.2696,  0.0821, -0.0471, -0.1734, -0.1726,  2.0454,
+-0.1127,  0.3053, -0.0921, -0.0844,  0.1480,  0.1261,  0.0869, -0.0254,
+0.3634,  0.0286,  0.2676, -0.0111, -0.1716,  0.0840, -0.1960,  0.0720,
+0.2174, -0.2858, -0.0343, -0.2553,  0.2707,  0.2487, -0.2674, -0.1070,
+-0.8237,  0.1282, -0.0901,  0.8288,  0.1630,  0.2839, -0.0728,  0.0767,
+-0.4713, -1.1815, -0.7286,  0.1370,  0.6182,  1.1314,  0.0833, -1.2036,
+0.1424,  0.3215,  0.4865, -0.0045,  0.1883, -0.3926, -0.0261, -0.0714,
+0.3457,  0.4706, -0.1923, -0.1117, -0.2896,  0.0486,  0.1790,  0.2757]
+
+[ 1.4261e+00, -3.0460e-01,  2.5091e+00, -1.2012e-01, -2.9618e-01,
+-1.8254e-02, -1.3069e+00,  1.9453e-01, -3.7499e-02,  4.6489e-01,
+-1.7681e-01,  1.1480e-01,  1.7867e-01, -2.4253e-01, -1.0137e-01,
+2.0227e+00, -5.9877e-02,  2.9890e-01, -5.5780e-02, -5.1556e-02,
+1.4710e-01,  4.4349e-01,  3.9919e-02, -1.9014e-02,  1.3687e-01,
+1.0056e-01,  2.7448e-01,  3.9938e-02, -1.2095e-02,  7.8835e-02,
+-2.3510e-01,  6.9572e-02,  2.4517e-01, -2.7999e-01, -8.5868e-02,
+-2.3118e-01,  1.7140e-01,  5.1235e-02,  8.8233e-03, -1.8278e-01,
+-8.4868e-01,  2.1059e-01, -8.8805e-02,  7.5416e-01, -1.2976e-01,
+2.1373e-01,  9.2919e-03,  1.4747e-01, -5.4918e-02, -9.1706e-01,
+-8.6564e-01, -3.0029e-01,  1.0207e+00,  6.5611e-01,  6.2078e-01,
+-7.2618e-01, -1.5981e-01, -2.1578e-01,  1.5084e+00, -7.1146e-01,
+-1.7969e-01, -2.6289e-01, -1.9960e-01,  1.3575e-01,  2.0665e-01,
+3.2092e-02,  4.1407e-02,  3.5012e-02, -4.4135e-02,  4.9747e-02,
+1.9240e-03,  5.2838e-03]
+
+[ 5.1824e-01, -1.4906e-01,  2.9998e+00, -8.9804e-02,  7.9969e-02,
+1.2960e-02, -6.9304e-01, -3.2315e-01, -4.9412e-01,  2.4757e-01,
+2.3405e-03,  8.8145e-02,  2.9368e-01, -6.9512e-02, -1.0302e-01,
+1.9027e+00, -2.2508e-01,  3.0125e-01, -6.5824e-02,  9.6872e-02,
+9.2468e-03,  2.6954e-01,  7.0543e-02, -5.8890e-02,  3.6490e-01,
+-1.0701e-01,  1.7876e-01,  4.4869e-02, -1.8048e-02,  1.3204e-02,
+-1.5959e-01,  5.6190e-03,  2.4617e-01, -2.9041e-01, -6.4084e-02,
+-1.8760e-01, -1.5622e-02, -4.4083e-01,  6.6574e-02, -1.3525e-01,
+1.0143e-01, -2.0383e-01, -2.1113e-01,  1.4702e-01, -4.7091e-01,
+-2.1075e-01, -1.5843e-01,  1.1590e-01, -1.5811e-01, -8.1192e-02,
+-1.1480e+00, -5.1663e-01,  4.5162e-01,  5.0580e-02,  2.2351e-01,
+-1.1500e-01,  2.9583e-01, -4.5928e-01,  1.2410e+00, -6.1835e-01,
+5.3863e-01,  8.0154e-02,  8.2205e-02,  8.9368e-02,  6.1148e-01,
+-3.4663e-01,  1.4324e-01, -1.4439e-01, -1.4406e-01,  1.4954e-01,
+1.9718e-02,  1.2337e-01]
+
+
+

src/static/save_betas.py

@@ -0,0 +1,55 @@
+import numpy as np
+
+# FEMALE 数据
+female_data = {
+    "Petite_Slim": np.array([-2.405284, -1.5530001, -0.24272324, -1.443513, -0.90185016, 1.2732644,
+                             -0.36933944, -0.05060475, -2.3866267, -0.5039462]),
+    "Average_Fit": np.array([-1.3060766, -1.6338427, 0.70017195, -0.17132899, -1.1940454, 0.29538375,
+                             0.14818205, 0.6067093, -1.2169323, -0.39638677]),
+    "Athletic_Tall": np.array([0.22818007, -1.1036383, -1.5221908, 0.73692316, -0.35802472, 0.948243,
+                               -0.03018424, 0.55922085, -0.16469094, -1.558347]),
+    "Curvy_Plus": np.array([-0.5351595, -0.6430263, 1.4178932, 0.7848561, 0.29656753, 0.00878574,
+                            0.9825444, -0.5219289, 0.40674126, 0.18135245]),
+    "Big_and_Heavy": np.array([1.8121121, 0.3021033, 1.3633814, 1.6494894, 2.1491473, 0.9186887,
+                               0.9121304, -1.3406857, 2.321915, -1.0636625])
+}
+
+# MALE 数据
+male_data = {
+    "Male_Skinny_Short": np.array([-0.7108757, -0.7559417, -0.94977564, -0.5261638, -1.7385905, -0.6821138,
+                                   -3.8808734, -1.083193, -0.30184665, 0.64134985]),
+    "Male_Standard": np.array([0.5232158, -0.6872696, -1.1425025, 0.7785673, -1.8967177, -0.9401324,
+                               0.06393365, -0.3843205, -0.50072473, -0.5430138]),
+    "Male_V_Shape": np.array([1.1519345, 0.38004422, -1.7919775, -0.37787473, -0.1616468, 0.6167449,
+                              0.59436065, -0.7820431, -1.8210857, -0.37498614]),
+    "Male_Stocky_Rect": np.array([0.2341475, -0.22931805, 1.9749473, -0.05317437, -1.4906491, -2.5173957,
+                                  0.04375501, 0.03236455, -0.23340486, 0.4409504]),
+    "Male_Giant_Heavy": np.array([2.932486, 0.4136964, 1.1478211, 1.5842791, 1.3554143, -1.7326043,
+                                  1.195378, -1.1438893, 0.8729984, -0.06384684])
+}
+
+# 保存 FEMALE 数据
+for i, (body_type, data) in enumerate(female_data.items()):
+    filename = f"betas/FEMALE_BETA_{i}.npz"
+    np.savez(filename, beta=data)
+    print(f"Saved {filename} - {body_type}")
+
+# 保存 MALE 数据
+for i, (body_type, data) in enumerate(male_data.items()):
+    filename = f"betas/MALE_BETA_{i}.npz"
+    np.savez(filename, beta=data)
+    print(f"Saved {filename} - {body_type}")
+
+print("\n所有文件已保存完成！")
+
+# 验证文件保存是否正确
+print("\n验证保存的文件:")
+for i in range(5):
+    female_file = f"betas/FEMALE_BETA_{i}.npz"
+    male_file = f"betas/MALE_BETA_{i}.npz"
+    
+    female_loaded = np.load(female_file)
+    male_loaded = np.load(male_file)
+    
+    print(f"{female_file}: shape={female_loaded['beta'].shape}, dtype={female_loaded['beta'].dtype}")
+    print(f"{male_file}: shape={male_loaded['beta'].shape}, dtype={male_loaded['beta'].dtype}")

src/static/save_poses.py

@@ -0,0 +1,129 @@
+import numpy as np
+import os
+
+# Pose数据列表
+pose_data = [
+    np.array([2.3752, 0.0658, -1.7781, -0.1833, 0.0058, -0.1768, -0.4969, 0.3412,
+              0.1805, 0.2078, -0.0801, 0.0113, 0.7961, -0.0638, -0.0320, 1.1230,
+              0.1120, 0.0431, -0.0053, -0.0622, -0.1404, -0.0399, 0.1543, -0.0574,
+              0.1719, -0.1349, 0.1215, -0.0742, 0.0198, -0.2016, -0.1918, 0.0664,
+              0.1843, -0.1893, -0.0836, -0.2172, 0.3527, -0.0895, 0.0831, 0.1069,
+              -0.6679, -0.3409, -0.4127, 0.2049, -0.5758, 0.4160, 0.2027, 0.0371,
+              -0.0056, -0.8203, -0.7385, -0.5755, 0.6557, 0.1240, 0.3627, -1.5995,
+              0.2493, -0.1409, 1.3971, -0.2052, -0.0726, -0.5489, 0.4632, 0.0383,
+              0.4377, -0.3150, 0.0867, -0.0317, -0.0694, 0.0872, 0.0519, 0.1608]),
+    
+    np.array([3.0614e+00, 6.2280e-02, -7.6650e-03, -1.4160e-01, -5.1097e-02,
+              5.0161e-02, -1.3916e-01, -7.7943e-02, -1.4492e-03, 1.0476e-01,
+              1.9706e-02, -5.5241e-02, 4.3114e-01, -2.3592e-03, 1.0349e-01,
+              3.8765e-01, -5.6183e-01, -2.5906e-01, -1.0401e-01, -3.5997e-02,
+              3.2958e-02, 1.1873e-01, 2.8326e-01, 9.6266e-02, -1.7527e-02,
+              -4.6820e-01, 4.8134e-03, -3.4153e-03, 3.1733e-02, 7.2645e-02,
+              -1.3809e-01, -2.2420e-02, 3.7563e-01, -1.1704e-01, 3.8316e-02,
+              -3.5116e-01, 2.1393e-01, -9.0961e-02, 2.1819e-02, -2.2145e-01,
+              -8.2792e-02, 4.7571e-01, -3.4885e-01, 1.5275e-01, -3.7524e-01,
+              1.9898e-01, -5.6398e-02, 1.5147e-01, -3.6606e-01, -5.0230e-01,
+              3.5257e-01, -5.7167e-01, 3.5682e-01, -1.2872e-01, 5.8685e-02,
+              -2.1642e+00, 6.4898e-01, -2.4495e-01, 2.1219e+00, -7.5819e-01,
+              -4.4861e-01, -4.6142e-01, -1.9626e-01, -3.5913e-01, 4.2019e-01,
+              2.7658e-01, 1.7639e-01, -5.2321e-02, -1.1038e-01, 1.2812e-01,
+              6.4935e-02, 2.2037e-01]),
+    
+    np.array([2.9954, 0.0478, -0.0210, -0.0661, -0.4360, 0.0570, -0.2681, 0.2788,
+              -0.0715, 0.2030, 0.0093, -0.1145, 0.2436, -0.0254, -0.1626, 0.5336,
+              -0.0321, 0.2793, 0.0192, 0.0449, 0.0101, -0.0073, 0.1966, -0.0735,
+              0.0612, -0.1001, 0.1643, 0.1277, 0.0090, 0.0318, -0.1977, 0.0466,
+              0.2682, -0.1723, -0.0298, -0.2414, -0.0103, -0.0858, 0.0773, 0.0530,
+              -0.0082, 0.0819, 0.0522, 0.1311, 0.1491, 0.1614, -0.0862, 0.0777,
+              0.3365, -0.4108, -1.1308, 0.3167, 0.3025, 0.9944, 0.5398, -1.5167,
+              -0.0472, 0.3905, 1.4840, -0.1251, -0.2937, -0.1276, 0.0920, -0.2136,
+              0.1464, 0.0138, -0.2083, -0.0330, -0.1633, -0.1662, 0.1062, 0.1335]),
+    
+    np.array([3.0080, 0.0306, -0.2129, -0.0872, 0.0768, 0.0630, -0.7311, -0.2889,
+              -0.4064, 0.2019, 0.0288, -0.0278, 0.4179, -0.1456, -0.0833, 1.8403,
+              -0.1916, 0.4140, -0.0385, 0.0567, 0.0509, -0.2573, 0.3238, 0.0203,
+              -0.1047, -0.2087, 0.3207, -0.0567, -0.0078, 0.0251, -0.2247, 0.0581,
+              0.3587, -0.2693, 0.0096, -0.3148, 0.3628, 0.0998, 0.0767, -0.3403,
+              0.1187, 0.3583, -0.3395, -0.0055, -0.2204, 0.2906, 0.0092, 0.0590,
+              -0.2578, -0.2382, 0.3031, -0.2698, 0.3195, -0.2413, -0.0659, -2.2600,
+              0.8711, -0.1026, 2.1879, -0.8472, -0.2476, -0.3128, 0.0327, -0.0614,
+              0.2795, 0.1144, -0.1259, -0.0362, -0.2552, -0.0544, 0.1021, 0.0793]),
+    
+    np.array([-4.4739e-02, -2.5408e-01, 3.0967e+00, -3.2824e-03, 2.9921e-02,
+              1.7044e-02, -6.2180e-02, 2.2239e-02, -2.2721e-02, 1.7281e-01,
+              -4.6111e-02, 7.4796e-02, 2.1117e-01, -1.6837e-01, 2.9683e-02,
+              5.8315e-01, 7.6520e-02, 5.6352e-02, -1.1508e-01, -2.0811e-02,
+              3.2421e-02, 3.9826e-01, 3.4520e-01, -2.0537e-01, 3.8679e-01,
+              -3.0132e-01, 1.6660e-01, 3.5923e-02, 3.8529e-04, -5.1066e-02,
+              -1.0309e-01, -1.7867e-02, 2.7689e-01, -9.9123e-02, 4.2380e-02,
+              -2.7752e-01, -3.2211e-01, -2.2977e-02, -4.1069e-04, -2.9728e-01,
+              -2.5900e-01, 3.1511e-01, -2.7042e-01, 2.6003e-01, -3.3097e-01,
+              -2.2513e-01, -3.0654e-03, 6.8447e-02, -3.8446e-01, -2.3619e-01,
+              -3.3112e-02, -3.7500e-01, 1.8820e-01, 1.4296e-02, -3.6162e-01,
+              -1.2229e+00, 4.3001e-01, -3.5856e-01, 1.2067e+00, -4.0485e-01,
+              1.6419e-01, -3.9610e-01, 2.3677e-01, 5.5694e-02, 3.8777e-01,
+              -2.1233e-01, 2.2479e-01, -2.9042e-02, -8.7811e-02, 2.0511e-01,
+              9.6519e-03, -4.0550e-02]),
+    
+    np.array([1.7333, -0.0567, 2.4417, -0.0180, -0.0489, 0.0498, -1.3883, 0.3772,
+              0.1170, 0.4974, -0.2696, 0.0821, -0.0471, -0.1734, -0.1726, 2.0454,
+              -0.1127, 0.3053, -0.0921, -0.0844, 0.1480, 0.1261, 0.0869, -0.0254,
+              0.3634, 0.0286, 0.2676, -0.0111, -0.1716, 0.0840, -0.1960, 0.0720,
+              0.2174, -0.2858, -0.0343, -0.2553, 0.2707, 0.2487, -0.2674, -0.1070,
+              -0.8237, 0.1282, -0.0901, 0.8288, 0.1630, 0.2839, -0.0728, 0.0767,
+              -0.4713, -1.1815, -0.7286, 0.1370, 0.6182, 1.1314, 0.0833, -1.2036,
+              0.1424, 0.3215, 0.4865, -0.0045, 0.1883, -0.3926, -0.0261, -0.0714,
+              0.3457, 0.4706, -0.1923, -0.1117, -0.2896, 0.0486, 0.1790, 0.2757]),
+    
+    np.array([1.4261e+00, -3.0460e-01, 2.5091e+00, -1.2012e-01, -2.9618e-01,
+              -1.8254e-02, -1.3069e+00, 1.9453e-01, -3.7499e-02, 4.6489e-01,
+              -1.7681e-01, 1.1480e-01, 1.7867e-01, -2.4253e-01, -1.0137e-01,
+              2.0227e+00, -5.9877e-02, 2.9890e-01, -5.5780e-02, -5.1556e-02,
+              1.4710e-01, 4.4349e-01, 3.9919e-02, -1.9014e-02, 1.3687e-01,
+              1.0056e-01, 2.7448e-01, 3.9938e-02, -1.2095e-02, 7.8835e-02,
+              -2.3510e-01, 6.9572e-02, 2.4517e-01, -2.7999e-01, -8.5868e-02,
+              -2.3118e-01, 1.7140e-01, 5.1235e-02, 8.8233e-03, -1.8278e-01,
+              -8.4868e-01, 2.1059e-01, -8.8805e-02, 7.5416e-01, -1.2976e-01,
+              2.1373e-01, 9.2919e-03, 1.4747e-01, -5.4918e-02, -9.1706e-01,
+              -8.6564e-01, -3.0029e-01, 1.0207e+00, 6.5611e-01, 6.2078e-01,
+              -7.2618e-01, -1.5981e-01, -2.1578e-01, 1.5084e+00, -7.1146e-01,
+              -1.7969e-01, -2.6289e-01, -1.9960e-01, 1.3575e-01, 2.0665e-01,
+              3.2092e-02, 4.1407e-02, 3.5012e-02, -4.4135e-02, 4.9747e-02,
+              1.9240e-03, 5.2838e-03]),
+    
+    np.array([5.1824e-01, -1.4906e-01, 2.9998e+00, -8.9804e-02, 7.9969e-02,
+              1.2960e-02, -6.9304e-01, -3.2315e-01, -4.9412e-01, 2.4757e-01,
+              2.3405e-03, 8.8145e-02, 2.9368e-01, -6.9512e-02, -1.0302e-01,
+              1.9027e+00, -2.2508e-01, 3.0125e-01, -6.5824e-02, 9.6872e-02,
+              9.2468e-03, 2.6954e-01, 7.0543e-02, -5.8890e-02, 3.6490e-01,
+              -1.0701e-01, 1.7876e-01, 4.4869e-02, -1.8048e-02, 1.3204e-02,
+              -1.5959e-01, 5.6190e-03, 2.4617e-01, -2.9041e-01, -6.4084e-02,
+              -1.8760e-01, -1.5622e-02, -4.4083e-01, 6.6574e-02, -1.3525e-01,
+              1.0143e-01, -2.0383e-01, -2.1113e-01, 1.4702e-01, -4.7091e-01,
+              -2.1075e-01, -1.5843e-01, 1.1590e-01, -1.5811e-01, -8.1192e-02,
+              -1.1480e+00, -5.1663e-01, 4.5162e-01, 5.0580e-02, 2.2351e-01,
+              -1.1500e-01, 2.9583e-01, -4.5928e-01, 1.2410e+00, -6.1835e-01,
+              5.3863e-01, 8.0154e-02, 8.2205e-02, 8.9368e-02, 6.1148e-01,
+              -3.4663e-01, 1.4324e-01, -1.4439e-01, -1.4406e-01, 1.4954e-01,
+              1.9718e-02, 1.2337e-01])
+]
+
+# 保存pose数据
+for i, pose in enumerate(pose_data):
+    filename = f"poses/POSE_{i}.npz"
+    np.savez(filename, pose=pose)
+    print(f"Saved {filename} - shape: {pose.shape}")
+
+print(f"\n已保存 {len(pose_data)} 个pose文件到poses目录")
+
+# 验证文件保存是否正确
+print("\n验证保存的文件:")
+for i in range(len(pose_data)):
+    filename = f"poses/POSE_{i}.npz"
+    if os.path.exists(filename):
+        loaded = np.load(filename)
+        pose = loaded['pose']
+        print(f"{filename}: shape={pose.shape}, dtype={pose.dtype}, first_value={pose[0]:.4f}")
+    else:
+        print(f"{filename}: 文件不存在")
+