notebook for dataset creating

alexeybokhovkin · Mar 4, 2019 · 0a3f3ca · 0a3f3ca
1 parent ec4fabb
commit 0a3f3ca
Show file tree

Hide file tree

Showing 5 changed files with 236 additions and 0 deletions.
diff --git a/.gitignore b/.gitignore
@@ -1,6 +1,8 @@
 data/raw_data/
 src/notebooks/.ipynb_checkpoints/
 src/backend/__pycache__/
+src/backend/datasets/__pycache__/
+src/backend/sampler/__pycache__/
 
 *.npy
 *.npz
diff --git a/src/backend/__init__.py b/src/backend/__init__.py
diff --git a/src/backend/sampler/__init__.py b/src/backend/sampler/__init__.py
@@ -0,0 +1 @@
+from .sampler import MeshSampler
diff --git a/src/backend/sampler.py → src/backend/sampler/sampler.py b/src/backend/sampler.py → src/backend/sampler/sampler.py
diff --git a/src/notebooks/create_dataset.ipynb b/src/notebooks/create_dataset.ipynb
@@ -0,0 +1,233 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sys \n",
+    "sys.path.append('..')\n",
+    "import warnings\n",
+    "warnings.filterwarnings('ignore')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from backend.sampler import MeshSampler\n",
+    "import trimesh\n",
+    "import numpy as np\n",
+    "import os\n",
+    "from tqdm import tqdm_notebook as tqdm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "DATA_DIR = '../../../../data/ShapeNetCorev2/ShapeNetCore.v2/'\n",
+    "SAVE_DIR = '../../data/processed_data/'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "9607c49b076d4181b9a4810eb29abba0",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(IntProgress(value=0, max=56), HTML(value='')))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "0483c2c4a3d64ffcb0f37520e2fec48e",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(IntProgress(value=0, max=2373), HTML(value='')))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "7024385d627849639910e0ae76821625",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(IntProgress(value=0, max=71300), HTML(value='')))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "ff22e66b581b49088807fc435405653f",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(IntProgress(value=0, max=250000), HTML(value='')))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "15a821d689bb4fb49628569c7a595f0a",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(IntProgress(value=0, max=33250), HTML(value='')))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "41c10ea4f80444b6adb94c065e54ddec",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(IntProgress(value=0, max=250000), HTML(value='')))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "7566250046804f7e84fd918e94959901",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(IntProgress(value=0, max=5072), HTML(value='')))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "bd99a243f14e48188eb0fecfa52fe4c5",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(IntProgress(value=0, max=250000), HTML(value='')))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "84e258df96dd44d4b7414651f7445bb5",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(IntProgress(value=0, max=56326), HTML(value='')))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a4abfe096c5247eeaeabd30a94dd1773",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(IntProgress(value=0, max=250000), HTML(value='')))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "for synsetId in tqdm(os.listdir(DATA_DIR)):\n",
+    "    SYNSET_DIR = os.path.join(DATA_DIR, synsetId)\n",
+    "    for i, modelId in enumerate(tqdm(os.listdir(SYNSET_DIR))):\n",
+    "        if i == 5:\n",
+    "            break\n",
+    "        MODEL_DIR = os.path.join(SYNSET_DIR, modelId, 'models')\n",
+    "        MESH = os.path.join(MODEL_DIR, 'model_normalized.obj')\n",
+    "        \n",
+    "        sampler = MeshSampler(trimesh.load(MESH))\n",
+    "        sampler.compute_visible_faces()\n",
+    "        sampler.sample_points(n_points=250000)\n",
+    "        correct_mesh_points, correct_sdf = sampler.compute_sdf(sigma=0.0025)\n",
+    "        \n",
+    "        SAVE_PATH = os.path.join(SAVE_DIR, synsetId, modelId)\n",
+    "        os.makedirs(SAVE_PATH, exist_ok=True)\n",
+    "        np.save(os.path.join(SAVE_PATH, 'points.npy'), correct_mesh_points)\n",
+    "        np.save(os.path.join(SAVE_PATH, 'sdfs.npy'), correct_sdf)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.6.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}