build_dataloader.ipynb

{
 "metadata": {
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.5"
  },
  "orig_nbformat": 2,
  "kernelspec": {
   "name": "ml",
   "display_name": "ML",
   "language": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2,
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "encodings = {'input_ids': input_ids, 'attention_mask': mask, 'labels': labels}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "class Dataset(torch.utils.data.Dataset):\n",
    "    def __init__(self, encodings):\n",
    "        # store encodings internally\n",
    "        self.encodings = encodings\n",
    "\n",
    "    def __len__(self):\n",
    "        # return the number of samples\n",
    "        return self.encodings['input_ids'].shape[0]\n",
    "\n",
    "    def __getitem__(self, i):\n",
    "        # return dictionary of input_ids, attention_mask, and labels for index i\n",
    "        return {key: tensor[i] for key, tensor in self.encodings.items()}"
   ]
  },
  {
   "source": [
    "Next we initialize our `Dataset`."
   ],
   "cell_type": "markdown",
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset = Dataset(encodings)"
   ]
  },
  {
   "source": [
    "And initialize the dataloader, which will load the data into the model during training."
   ],
   "cell_type": "markdown",
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "loader = torch.utils.data.DataLoader(dataset, batch_size=16, shuffle=True)"
   ]
  }
 ]
}