Skip to content

Niamipek #180

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
niamipek wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Niamipek #180

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
fdcd49d
Create cal_mean_variance-checkpoint.ipynb
niamipek Oct 16, 2025
117eb5c
Create motion_representation-checkpoint.ipynb
niamipek Oct 16, 2025
f3d9ab7
text
niamipek Oct 16, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
313 changes: 313 additions & 0 deletions .ipynb_checkpoints/cal_mean_variance-checkpoint.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,313 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import sys\n",
"import os\n",
"from os.path import join as pjoin\n",
"\n",
"\n",
"# root_rot_velocity (B, seq_len, 1)\n",
"# root_linear_velocity (B, seq_len, 2)\n",
"# root_y (B, seq_len, 1)\n",
"# ric_data (B, seq_len, (joint_num - 1)*3)\n",
"# rot_data (B, seq_len, (joint_num - 1)*6)\n",
"# local_velocity (B, seq_len, joint_num*3)\n",
"# foot contact (B, seq_len, 4)\n",
"def mean_variance(data_dir, save_dir, joints_num):\n",
" file_list = os.listdir(data_dir)\n",
" data_list = []\n",
"\n",
" for file in file_list:\n",
" data = np.load(pjoin(data_dir, file))\n",
" if np.isnan(data).any():\n",
" print(file)\n",
" continue\n",
" data_list.append(data)\n",
"\n",
" data = np.concatenate(data_list, axis=0)\n",
" print(data.shape)\n",
" Mean = data.mean(axis=0)\n",
" Std = data.std(axis=0)\n",
" Std[0:1] = Std[0:1].mean() / 1.0\n",
" Std[1:3] = Std[1:3].mean() / 1.0\n",
" Std[3:4] = Std[3:4].mean() / 1.0\n",
" Std[4: 4+(joints_num - 1) * 3] = Std[4: 4+(joints_num - 1) * 3].mean() / 1.0\n",
" Std[4+(joints_num - 1) * 3: 4+(joints_num - 1) * 9] = Std[4+(joints_num - 1) * 3: 4+(joints_num - 1) * 9].mean() / 1.0\n",
" Std[4+(joints_num - 1) * 9: 4+(joints_num - 1) * 9 + joints_num*3] = Std[4+(joints_num - 1) * 9: 4+(joints_num - 1) * 9 + joints_num*3].mean() / 1.0\n",
" Std[4 + (joints_num - 1) * 9 + joints_num * 3: ] = Std[4 + (joints_num - 1) * 9 + joints_num * 3: ].mean() / 1.0\n",
"\n",
" assert 8 + (joints_num - 1) * 9 + joints_num * 3 == Std.shape[-1]\n",
"\n",
" np.save(pjoin(save_dir, 'Mean.npy'), Mean)\n",
" np.save(pjoin(save_dir, 'Std.npy'), Std)\n",
"\n",
" return Mean, Std"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"# The given data is used to double check if you are on the right track.\n",
"reference1 = np.load('./HumanML3D/Mean.npy')\n",
"reference2 = np.load('./HumanML3D/Std.npy')"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"📘 Mean.npy shape: (263,)\n",
"Top 10 giá trị đầu tiên trong Mean.npy:\n",
"[-1.03839448e-05 -3.12114498e-05 1.09036025e-02 9.35517669e-01\n",
" 5.61682135e-02 8.50852609e-01 -9.22142435e-03 -5.96521795e-02\n",
" 8.47016096e-01 -1.00206519e-02]\n",
"\n",
"📗 Std.npy shape: (263,)\n",
"Top 10 giá trị đầu tiên trong Std.npy:\n",
"[0.01489514 0.02076071 0.02076071 0.1500181 0.11935793 0.11935793\n",
" 0.11935793 0.11935793 0.11935793 0.11935793]\n"
]
}
],
"source": [
"import numpy as np\n",
"\n",
"def check_reference_data(mean_path, std_path, top_n=10):\n",
" reference1 = np.load(mean_path)\n",
" reference2 = np.load(std_path)\n",
"\n",
" print(\"📘 Mean.npy shape:\", reference1.shape)\n",
" print(\"Top 10 giá trị đầu tiên trong Mean.npy:\")\n",
" print(reference1[:top_n])\n",
"\n",
" print(\"\\n📗 Std.npy shape:\", reference2.shape)\n",
" print(\"Top 10 giá trị đầu tiên trong Std.npy:\")\n",
" print(reference2[:top_n])\n",
"\n",
"# Gọi hàm\n",
"check_reference_data('./HumanML3D/Mean.npy', './HumanML3D/Std.npy')\n"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(2191926, 263)\n",
"[-1.03839448e-05 -3.12114498e-05 1.09036025e-02 9.35517669e-01\n",
" 5.61682135e-02 8.50852609e-01 -9.22142435e-03 -5.96521795e-02\n",
" 8.47016096e-01 -1.00206519e-02 -3.45199624e-05 1.05221903e+00\n",
" -3.63960341e-02 1.17378183e-01 4.99920160e-01 4.72080037e-02\n",
" -1.20139033e-01 4.97536749e-01 4.56939898e-02 -2.47492630e-04\n",
" 1.19074190e+00 3.75931873e-03 9.88527164e-02 1.04053952e-01\n",
" -5.07620610e-02 -1.01210706e-01 1.07580900e-01 -5.07357344e-02\n",
" -2.95429694e-04 1.22119427e+00 2.47317124e-02 1.42412677e-01\n",
" 5.12279198e-02 5.90304546e-02 -1.46887317e-01 5.26042059e-02\n",
" 6.35762736e-02 -5.61898691e-04 1.44361055e+00 3.36999148e-02\n",
" 7.06304982e-02 1.33715022e+00 2.34650169e-02 -7.45727867e-02\n",
" 1.34506810e+00 2.31429040e-02 -7.05347571e-04 1.48842430e+00\n",
" 9.94738936e-02 1.90338433e-01 1.32878268e+00 2.41578687e-02\n",
" -1.86426789e-01 1.33457303e+00 2.34030969e-02 2.51533508e-01\n",
" 1.12345576e+00 2.20350106e-03 -2.48369038e-01 1.12301922e+00\n",
" 7.07851199e-04 2.74772704e-01 9.78893816e-01 1.17656335e-01\n",
" -2.71994710e-01 9.77389872e-01 1.17384762e-01 4.10277665e-01\n",
" -7.94034004e-01 -7.21916556e-02 5.58863223e-01 4.98951137e-01\n",
" -4.55520265e-02 4.12868917e-01 7.89685488e-01 6.82888925e-02\n",
" -5.59208512e-01 4.98897702e-01 -4.13234159e-02 7.69626975e-01\n",
" 1.41538054e-04 -2.63520889e-03 4.20157858e-06 9.33114648e-01\n",
" -2.05915764e-01 3.13521177e-01 8.50986123e-01 3.85009646e-02\n",
" -8.18409145e-01 3.21360320e-01 -1.72695920e-01 3.14085782e-01\n",
" -8.51511955e-01 -3.72499898e-02 8.18751216e-01 3.21653932e-01\n",
" -1.72134742e-01 9.66012418e-01 -5.82688954e-04 -1.35261726e-04\n",
" 5.89909614e-04 7.76775122e-01 4.19852734e-01 9.49863255e-01\n",
" -1.52659237e-01 -2.21206844e-02 1.43100590e-01 7.94648051e-01\n",
" 2.53118336e-01 9.51009512e-01 1.51994780e-01 2.20180079e-02\n",
" -1.42357707e-01 7.95577526e-01 2.53528208e-01 9.89599586e-01\n",
" -2.39383895e-04 -7.81588897e-05 2.45350762e-04 9.47646618e-01\n",
" 6.59239367e-02 7.77234912e-01 -3.32972151e-03 -2.64888614e-01\n",
" 1.76207032e-02 8.84397388e-01 1.83548942e-01 7.78611422e-01\n",
" 4.04106826e-03 2.62810171e-01 -1.78565569e-02 8.85229349e-01\n",
" 1.83455810e-01 9.84383583e-01 5.65050577e-04 -1.55308488e-04\n",
" -5.58983709e-04 9.04012084e-01 -2.62933850e-01 3.78813475e-01\n",
" 7.94350326e-01 -1.49574894e-02 -5.60764730e-01 4.82002586e-01\n",
" 1.76811349e-02 3.77226174e-01 -7.96095490e-01 1.12690711e-02\n",
" 5.61106920e-01 4.82153773e-01 1.36994794e-02 9.09557045e-01\n",
" -2.62261543e-04 -9.18289530e-04 -4.33052599e-04 5.64815521e-01\n",
" -6.99468374e-01 5.95113397e-01 2.98070073e-01 1.08402930e-02\n",
" -5.01311183e-01 6.52549267e-01 -1.92495417e-02 5.95143974e-01\n",
" -2.97382116e-01 -8.26226920e-03 5.01323342e-01 6.52519286e-01\n",
" -2.02467460e-02 4.23221409e-01 -6.49836481e-01 1.31164361e-02\n",
" 6.12879694e-01 3.44750762e-01 5.97855039e-02 4.23525065e-01\n",
" 6.49513245e-01 -1.20427869e-02 -6.12739265e-01 3.44783843e-01\n",
" 6.16712123e-02 7.98856676e-01 -8.43466073e-02 -5.09356931e-02\n",
" 1.00723775e-02 5.71187735e-01 -4.36023831e-01 7.98229873e-01\n",
" 8.53761658e-02 5.08573875e-02 -1.15064047e-02 5.71032286e-01\n",
" -4.35627371e-01 -3.12603188e-05 6.64494564e-06 1.09527716e-02\n",
" -3.54243566e-05 5.97536882e-06 1.09692374e-02 -2.71006393e-05\n",
" 5.95488109e-06 1.09701995e-02 -3.10894975e-05 7.26151575e-06\n",
" 1.09319407e-02 -6.32220826e-06 1.85041554e-05 1.11111086e-02\n",
" -5.77885439e-05 1.83763750e-05 1.11101661e-02 -3.10606483e-05\n",
" 3.25940960e-06 1.09234322e-02 5.33055936e-05 4.72917927e-05\n",
" 1.11895790e-02 -1.17800591e-04 4.67138780e-05 1.11860558e-02\n",
" -3.10462965e-05 4.24390282e-06 1.09144114e-02 6.23307715e-05\n",
" 3.63463259e-05 1.12053119e-02 -1.27391817e-04 3.52883471e-05\n",
" 1.12017868e-02 -3.10238975e-05 1.15050477e-06 1.08913928e-02\n",
" -4.80403105e-05 1.93144092e-06 1.09029803e-02 -1.32744426e-05\n",
" 1.86131354e-06 1.09028071e-02 -3.06511938e-05 6.95700555e-06\n",
" 1.08025894e-02 -9.04958288e-05 2.12706473e-05 1.09060807e-02\n",
" 2.64286773e-05 1.99768547e-05 1.09056458e-02 -6.92553585e-05\n",
" 8.56247279e-05 1.09784901e-02 4.27348004e-06 8.58790881e-05\n",
" 1.09793702e-02 -2.64543178e-05 1.79968032e-04 1.09710442e-02\n",
" -3.99090677e-05 1.81499548e-04 1.09722409e-02 8.46179545e-01\n",
" 8.61126721e-01 8.46463799e-01 8.61388564e-01]\n",
"[0.01489514 0.02076071 0.02076071 0.1500181 0.11935793 0.11935793\n",
" 0.11935793 0.11935793 0.11935793 0.11935793 0.11935793 0.11935793\n",
" 0.11935793 0.11935793 0.11935793 0.11935793 0.11935793 0.11935793\n",
" 0.11935793 0.11935793 0.11935793 0.11935793 0.11935793 0.11935793\n",
" 0.11935793 0.11935793 0.11935793 0.11935793 0.11935793 0.11935793\n",
" 0.11935793 0.11935793 0.11935793 0.11935793 0.11935793 0.11935793\n",
" 0.11935793 0.11935793 0.11935793 0.11935793 0.11935793 0.11935793\n",
" 0.11935793 0.11935793 0.11935793 0.11935793 0.11935793 0.11935793\n",
" 0.11935793 0.11935793 0.11935793 0.11935793 0.11935793 0.11935793\n",
" 0.11935793 0.11935793 0.11935793 0.11935793 0.11935793 0.11935793\n",
" 0.11935793 0.11935793 0.11935793 0.11935793 0.11935793 0.11935793\n",
" 0.11935793 0.284643 0.284643 0.284643 0.284643 0.284643\n",
" 0.284643 0.284643 0.284643 0.284643 0.284643 0.284643\n",
" 0.284643 0.284643 0.284643 0.284643 0.284643 0.284643\n",
" 0.284643 0.284643 0.284643 0.284643 0.284643 0.284643\n",
" 0.284643 0.284643 0.284643 0.284643 0.284643 0.284643\n",
" 0.284643 0.284643 0.284643 0.284643 0.284643 0.284643\n",
" 0.284643 0.284643 0.284643 0.284643 0.284643 0.284643\n",
" 0.284643 0.284643 0.284643 0.284643 0.284643 0.284643\n",
" 0.284643 0.284643 0.284643 0.284643 0.284643 0.284643\n",
" 0.284643 0.284643 0.284643 0.284643 0.284643 0.284643\n",
" 0.284643 0.284643 0.284643 0.284643 0.284643 0.284643\n",
" 0.284643 0.284643 0.284643 0.284643 0.284643 0.284643\n",
" 0.284643 0.284643 0.284643 0.284643 0.284643 0.284643\n",
" 0.284643 0.284643 0.284643 0.284643 0.284643 0.284643\n",
" 0.284643 0.284643 0.284643 0.284643 0.284643 0.284643\n",
" 0.284643 0.284643 0.284643 0.284643 0.284643 0.284643\n",
" 0.284643 0.284643 0.284643 0.284643 0.284643 0.284643\n",
" 0.284643 0.284643 0.284643 0.284643 0.284643 0.284643\n",
" 0.284643 0.284643 0.284643 0.284643 0.284643 0.284643\n",
" 0.284643 0.284643 0.284643 0.284643 0.284643 0.284643\n",
" 0.284643 0.284643 0.284643 0.284643 0.284643 0.284643\n",
" 0.284643 0.02279257 0.02279257 0.02279257 0.02279257 0.02279257\n",
" 0.02279257 0.02279257 0.02279257 0.02279257 0.02279257 0.02279257\n",
" 0.02279257 0.02279257 0.02279257 0.02279257 0.02279257 0.02279257\n",
" 0.02279257 0.02279257 0.02279257 0.02279257 0.02279257 0.02279257\n",
" 0.02279257 0.02279257 0.02279257 0.02279257 0.02279257 0.02279257\n",
" 0.02279257 0.02279257 0.02279257 0.02279257 0.02279257 0.02279257\n",
" 0.02279257 0.02279257 0.02279257 0.02279257 0.02279257 0.02279257\n",
" 0.02279257 0.02279257 0.02279257 0.02279257 0.02279257 0.02279257\n",
" 0.02279257 0.02279257 0.02279257 0.02279257 0.02279257 0.02279257\n",
" 0.02279257 0.02279257 0.02279257 0.02279257 0.02279257 0.02279257\n",
" 0.02279257 0.02279257 0.02279257 0.02279257 0.02279257 0.02279257\n",
" 0.02279257 0.35368326 0.35368326 0.35368326 0.35368326]\n"
]
}
],
"source": [
"if __name__ == '__main__':\n",
" data_dir = './HumanML3D/new_joint_vecs/'\n",
" save_dir = './HumanML3D/'\n",
" mean, std = mean_variance(data_dir, save_dir, 22)\n",
" print(mean)\n",
" print(std)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Check if your data is correct. If it's aligned with the given reference, then it is right"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.0"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"abs(mean-reference1).sum()"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.0"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"abs(std-reference2).sum()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.10"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
Loading