{ "cells": [ { "cell_type": "code", "execution_count": 17, "id": "f5ab3881", "metadata": {}, "outputs": [], "source": [ "import pickle,gzip,math,os,time,shutil,torch,matplotlib as mpl,numpy as np,matplotlib.pyplot as plt\n", "import fastcore.all as fc\n", "from collections.abc import Mapping\n", "from pathlib import Path\n", "\n", "from torch import tensor,nn,optim\n", "from torch.utils.data import DataLoader,default_collate\n", "import torch.nn.functional as F\n", "from datasets import load_dataset,load_dataset_builder" ] }, { "cell_type": "code", "execution_count": 3, "id": "84a947f2", "metadata": {}, "outputs": [], "source": [ "import torchvision.transforms.functional as TF\n", "from fastcore.test import test_close\n", "\n", "torch.set_printoptions(precision=2, linewidth=140, sci_mode=False)\n", "torch.manual_seed(1)\n", "mpl.rcParams['image.cmap'] = 'gray'\n", "\n", "import logging\n", "logging.disable(logging.WARNING)" ] }, { "cell_type": "code", "execution_count": 4, "id": "195306d7", "metadata": {}, "outputs": [], "source": [ "# from torch.utils.data.sampler import BatchSampler, RandomSampler, SequentialSampler\n", "# from transformers import default_data_collator\n", "# from collections.abc import Mapping" ] }, { "cell_type": "markdown", "id": "518c5f72", "metadata": {}, "source": [ "## Dict model" ] }, { "cell_type": "code", "execution_count": 35, "id": "6e610b16", "metadata": {}, "outputs": [], "source": [ "x,y = 'image','labels'" ] }, { "cell_type": "code", "execution_count": 8, "id": "4ded6c4e", "metadata": {}, "outputs": [], "source": [ "def data_loader(ds, batch_size, as_tuple=True):\n", " kw = {'collate_fn':collate_dict(ds)} if as_tuple else {}\n", " return DataLoader(ds, batch_size=batch_size, **kw)" ] }, { "cell_type": "code", "execution_count": 213, "id": "a5b2c21b", "metadata": {}, "outputs": [], "source": [ "dls = DataLoaders.from_dd(tds, bs, as_tuple=False)" ] }, { "cell_type": "code", "execution_count": 214, "id": "f9edb11a", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'image': tensor([[0., 0., 0., ..., 0., 0., 0.],\n", " [0., 0., 0., ..., 0., 0., 0.],\n", " [0., 0., 0., ..., 0., 0., 0.],\n", " ...,\n", " [0., 0., 0., ..., 0., 0., 0.],\n", " [0., 0., 0., ..., 0., 0., 0.],\n", " [0., 0., 0., ..., 0., 0., 0.]]),\n", " 'label': tensor([9, 0, 0, 3, 0, 2, 7, 2, 5, 5, 0, 9, 5, 5, 7, 9, 1, 0, 6, 4, 3, 1, 4, 8, 4, 3, 0, 2, 4, 4, 5, 3, 6, 6, 0, 8, 5, 2, 1, 6, 6, 7, 9, 5,\n", " 9, 2, 7, 3, 0, 3, 3, 3, 7, 2, 2, 6, 6, 8, 3, 3, 5, 0, 5, 5, 0, 2, 0, 0, 4, 1, 3, 1, 6, 3, 1, 4, 4, 6, 1, 9, 1, 3, 5, 7, 9, 7, 1, 7,\n", " 9, 9, 9, 3, 2, 9, 3, 6, 4, 1, 1, 8, 8, 0, 1, 1, 6, 8, 1, 9, 7, 8, 8, 9, 6, 6, 3, 1, 5, 4, 6, 7, 5, 5, 9, 2, 2, 2, 7, 6])}" ] }, "execution_count": 214, "metadata": {}, "output_type": "execute_result" } ], "source": [ "b = next(iter(dls.train))\n", "b" ] }, { "cell_type": "code", "execution_count": 219, "id": "41de7ff5", "metadata": {}, "outputs": [], "source": [ "class FashionMLP(nn.Module):\n", " def __init__(self):\n", " super().__init__()\n", " self.l1 = nn.Linear(m,nh)\n", " self.relu = nn.ReLU()\n", " self.l2 = nn.Linear(nh,10)\n", "\n", " def forward(self, b):\n", " xb = b[x]\n", " yb = b[y]\n", " pred = self.l2(self.relu(self.l1(xb)))\n", " return {'preds':pred, 'loss':F.cross_entropy(pred, yb)}" ] }, { "cell_type": "code", "execution_count": 220, "id": "e9682e1d", "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "0 True 1.5404933774903384 0.6351112739872068\n" ] }, { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "0 False 2.156612927400613 0.7089596518987342\n" ] } ], "source": [ "model = FashionMLP()\n", "learn = Learner(model, dls, identity, lr=0.001, cbs=cbs)\n", "learn.fit(1)" ] }, { "cell_type": "code", "execution_count": null, "id": "7c9c8f8f", "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": "3.9.10" }, "toc": { "base_numbering": 1, "nav_menu": {}, "number_sections": false, "sideBar": true, "skip_h1_title": false, "title_cell": "Table of Contents", "title_sidebar": "Contents", "toc_cell": false, "toc_position": {}, "toc_section_display": true, "toc_window_display": false } }, "nbformat": 4, "nbformat_minor": 5 }