File size: 3,329 Bytes
a5407e7 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 |
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from PIL import Image\n",
"import torch\n",
"from tqdm.auto import tqdm\n",
"\n",
"from point_e.diffusion.configs import DIFFUSION_CONFIGS, diffusion_from_config\n",
"from point_e.diffusion.sampler import PointCloudSampler\n",
"from point_e.models.download import load_checkpoint\n",
"from point_e.models.configs import MODEL_CONFIGS, model_from_config\n",
"from point_e.util.plotting import plot_point_cloud"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\n",
"\n",
"print('creating base model...')\n",
"base_name = 'base40M' # use base300M or base1B for better results\n",
"base_model = model_from_config(MODEL_CONFIGS[base_name], device)\n",
"base_model.eval()\n",
"base_diffusion = diffusion_from_config(DIFFUSION_CONFIGS[base_name])\n",
"\n",
"print('creating upsample model...')\n",
"upsampler_model = model_from_config(MODEL_CONFIGS['upsample'], device)\n",
"upsampler_model.eval()\n",
"upsampler_diffusion = diffusion_from_config(DIFFUSION_CONFIGS['upsample'])\n",
"\n",
"print('downloading base checkpoint...')\n",
"base_model.load_state_dict(load_checkpoint(base_name, device))\n",
"\n",
"print('downloading upsampler checkpoint...')\n",
"upsampler_model.load_state_dict(load_checkpoint('upsample', device))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"sampler = PointCloudSampler(\n",
" device=device,\n",
" models=[base_model, upsampler_model],\n",
" diffusions=[base_diffusion, upsampler_diffusion],\n",
" num_points=[1024, 4096 - 1024],\n",
" aux_channels=['R', 'G', 'B'],\n",
" guidance_scale=[3.0, 3.0],\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Load an image to condition on.\n",
"img = Image.open('example_data/cube_stack.jpg')\n",
"\n",
"# Produce a sample from the model.\n",
"samples = None\n",
"for x in tqdm(sampler.sample_batch_progressive(batch_size=1, model_kwargs=dict(images=[img]))):\n",
" samples = x"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"pc = sampler.output_to_point_clouds(samples)[0]\n",
"fig = plot_point_cloud(pc, grid_size=3, fixed_bounds=((-0.75, -0.75, -0.75),(0.75, 0.75, 0.75)))"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3.9.9 64-bit ('3.9.9')",
"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": "3.9.9"
},
"orig_nbformat": 4,
"vscode": {
"interpreter": {
"hash": "b270b0f43bc427bcab7703c037711644cc480aac7c1cc8d2940cfaf0b447ee2e"
}
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|