Spaces:
Sleeping
Sleeping
File size: 3,978 Bytes
d1474ea |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"a:\\python\\312\\Lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n",
"a:\\python\\312\\Lib\\site-packages\\transformers\\utils\\hub.py:128: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.\n",
" warnings.warn(\n"
]
}
],
"source": [
"import os\n",
"os.chdir('..')\n",
"\n",
"import torch\n",
"from scr.sbert import sbert\n",
"from scr.dataset import TextDataset"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\timof\\AppData\\Local\\Temp\\ipykernel_12548\\753396127.py:1: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
" dataset = torch.load('data/dataset.pt')\n"
]
}
],
"source": [
"dataset = torch.load('data/dataset.pt')"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Размер датасета: 14412\n",
"Тексты: tensor([[-0.7709, 0.2756, -1.8136, ..., -0.1891, 0.6464, -0.0877],\n",
" [ 0.0737, 0.2665, -0.2466, ..., 0.1983, 0.9042, 0.7120],\n",
" [-0.4836, 0.2575, -0.3310, ..., -0.0648, 0.6074, -0.2436],\n",
" ...,\n",
" [ 0.5273, 0.2523, -0.4174, ..., -0.1361, 0.0777, 0.1805],\n",
" [-0.6573, 0.1075, -1.1338, ..., 0.0145, 0.0062, 0.1264],\n",
" [ 0.4965, 0.1897, -1.8090, ..., -0.0378, 0.2283, 0.6433]])\n",
"Метки: tensor([1., 0., 0., 1., 0., 0., 0., 1., 0., 1., 1., 1., 1., 0., 0., 0.],\n",
" dtype=torch.float64)\n"
]
}
],
"source": [
"from torch.utils.data import DataLoader\n",
"\n",
"# Проверяем размер\n",
"print(f\"Размер датасета: {len(dataset)}\")\n",
"\n",
"# Создаем DataLoader\n",
"dataloader = DataLoader(dataset, batch_size=16, shuffle=True)\n",
"\n",
"# Обрабатываем данные в батчах\n",
"for texts, labels in dataloader:\n",
" print(\"Тексты:\", texts)\n",
" print(\"Метки:\", labels)\n",
" break"
]
}
],
"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": "3.12.4"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|