practice deep learning example

.gitignore

@@ -104,3 +104,4 @@ venv.bak/
 .mypy_cache/
 .idea
 .vscode
+data

examples/pytorch/attention_seq2seq.ipynb

@@ -0,0 +1,44 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import math \n",
+ "import torch\n",
+ "from torch import nn\n",
+ "from d2l import torch as d2l"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "num_hiddens, num_headers = 100, 5"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "nlp_env",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "name": "python",
+ "version": "3.9.16"
+ },
+ "orig_nbformat": 4,
+ "vscode": {
+ "interpreter": {
+ "hash": "9be210f112d3bd93a6327b459217e15105c4405a02aec2765b09f959417e942a"
+ }
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

examples/pytorch/pytorch_file.ipynb

@@ -0,0 +1,222 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import os\n",
+ "os.makedirs(os.path.join('..', 'data'), exist_ok=True)\n",
+ "data_file = os.path.join(\"..\", \"data\", \"house_tiny.csv\")\n",
+ "\n",
+ "with open(data_file, 'w') as f:\n",
+ " f.write(\"NumRooms, Alley, Price\\n\")\n",
+ " f.write(\"NA, Pave, 127500\\n\")\n",
+ " f.write(\"2,NA,106000\\n\")\n",
+ " f.write(\"4,NA,178100\\n\")\n",
+ " f.write(\"NA,NA,140000\\n\")\n",
+ " "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ " NumRooms Alley Price\n",
+ "0 NaN Pave 127500\n",
+ "1 2.0 NaN 106000\n",
+ "2 4.0 NaN 178100\n",
+ "3 NaN NaN 140000\n"
+ ]
+ }
+ ],
+ "source": [
+ "import pandas as pd\n",
+ "data = pd.read_csv(os.path.join(\"..\", \"data\", \"house_tiny.csv\"))\n",
+ "print(data)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import torch\n",
+ "x = torch.arange(20).reshape(5, 4)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "tensor([[ 0, 4, 8, 12, 16],\n",
+ " [ 1, 5, 9, 13, 17],\n",
+ " [ 2, 6, 10, 14, 18],\n",
+ " [ 3, 7, 11, 15, 19]])"
+ ]
+ },
+ "execution_count": 5,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "x\n",
+ "x.T"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "tensor([[ 0, 2, 6],\n",
+ " [ 6, 0, 20],\n",
+ " [18, 28, 40]])"
+ ]
+ },
+ "execution_count": 11,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "B = torch.tensor([[1, 2, 3], [2,0,4], [3, 4, 5]])\n",
+ "B\n",
+ "\n",
+ "A = torch.arange(9).reshape(3, 3)\n",
+ "\n",
+ "A\n",
+ "A*B"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "torch.Size([2, 5, 4])"
+ ]
+ },
+ "execution_count": 12,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "a = torch.ones([2, 5, 4])\n",
+ "a.shape"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "torch.Size([5, 4])"
+ ]
+ },
+ "execution_count": 16,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "a.sum().shape\n",
+ "a.sum(axis=1).shape\n",
+ "a.sum(axis=2).shape\n",
+ "a.sum(axis=0).shape"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 18,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "tensor([[0.9088, 0.8009, 0.1684, 0.0296, 0.5991],\n",
+ " [0.5647, 0.1612, 0.0448, 0.4050, 0.8085]])"
+ ]
+ },
+ "execution_count": 18,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "A = torch.rand(2, 5)\n",
+ "A.shape\n",
+ "A"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 20,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0"
+ ]
+ },
+ "execution_count": 20,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "torch.cuda.device_count()"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "base",
+ "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": "3.9.13"
+ },
+ "orig_nbformat": 4,
+ "vscode": {
+ "interpreter": {
+ "hash": "40d3a090f54c6569ab1632332b64b2c03c39dcf918b08424e98f38b5ae0af88f"
+ }
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}