Add files via upload

Jupyter Notebook displaying Outputs of the Code

Author: infinitecoder1729

Sample Output v0.ipynb

@@ -0,0 +1,166 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "6584924f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "No. of Training examples:  60000\n",
+      "No. of Test examples:  10000\n"
+     ]
+    }
+   ],
+   "source": [
+    "import torch as tch\n",
+    "import torchvision.datasets as dt\n",
+    "import torchvision.transforms as trans\n",
+    "import torch.nn as nn\n",
+    "import matplotlib.pyplot as plt\n",
+    "from time import time\n",
+    "from torch.utils.tensorboard import SummaryWriter\n",
+    "\n",
+    "writer = SummaryWriter()\n",
+    "\n",
+    "train = dt.MNIST(root=\"./datasets\", train=True, transform=trans.ToTensor(), download=True)\n",
+    "test = dt.MNIST(root=\"./datasets\", train=False, transform=trans.ToTensor(), download=True)\n",
+    "print(\"No. of Training examples: \",len(train))\n",
+    "print(\"No. of Test examples: \",len(test))\n",
+    "\n",
+    "train_batch = tch.utils.data.DataLoader(train, batch_size=30, shuffle=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "148134c6",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch Number : 0 = Loss : 0.5081581976301968\n",
+      "Epoch Number : 1 = Loss : 0.2607014692854136\n",
+      "Epoch Number : 2 = Loss : 0.20602162138931454\n",
+      "Epoch Number : 3 = Loss : 0.16912483075121418\n",
+      "Epoch Number : 4 = Loss : 0.14195448012137785\n",
+      "Epoch Number : 5 = Loss : 0.12255496634542942\n",
+      "Epoch Number : 6 = Loss : 0.10741885769902729\n",
+      "Epoch Number : 7 = Loss : 0.09534787850477733\n",
+      "Epoch Number : 8 = Loss : 0.08542947270977311\n",
+      "Epoch Number : 9 = Loss : 0.07763797796762083\n",
+      "Epoch Number : 10 = Loss : 0.07077616441179999\n",
+      "Epoch Number : 11 = Loss : 0.06475602737592999\n",
+      "Epoch Number : 12 = Loss : 0.05975847951992182\n",
+      "Epoch Number : 13 = Loss : 0.05511430356022902\n",
+      "Epoch Number : 14 = Loss : 0.05111963468440808\n",
+      "Epoch Number : 15 = Loss : 0.04776831939723342\n",
+      "Epoch Number : 16 = Loss : 0.04453270577394869\n",
+      "Epoch Number : 17 = Loss : 0.0416670137080946\n",
+      "\n",
+      "Training Time (in minutes) :  2.8615051031112673\n"
+     ]
+    }
+   ],
+   "source": [
+    "input = 784\n",
+    "hidden = 490\n",
+    "output = 10\n",
+    "\n",
+    "model = nn.Sequential(nn.Linear(input, hidden),\n",
+    "                      nn.LeakyReLU(),\n",
+    "                      nn.Linear(hidden, output),\n",
+    "                      nn.LogSoftmax(dim=1))\n",
+    "\n",
+    "lossfn = nn.NLLLoss()\n",
+    "images, labels = next(iter(train_batch))\n",
+    "images = images.view(images.shape[0], -1)\n",
+    "\n",
+    "logps = model(images)\n",
+    "loss = lossfn(logps, labels)\n",
+    "loss.backward()\n",
+    "\n",
+    "optimize = tch.optim.SGD(model.parameters(), lr=0.003, momentum=0.9)\n",
+    "time_start = time()\n",
+    "epochs = 18\n",
+    "for num in range(epochs):\n",
+    "    run=0\n",
+    "    for images, labels in train_batch:\n",
+    "        images = images.view(images.shape[0], -1)\n",
+    "        optimize.zero_grad()\n",
+    "        output = model(images)\n",
+    "        loss = lossfn(output, labels)\n",
+    "        writer.add_scalar(\"Loss\", loss, num)\n",
+    "        loss.backward()\n",
+    "        optimize.step()\n",
+    "        run += loss.item()\n",
+    "    else:\n",
+    "        print(\"Epoch Number : {} = Loss : {}\".format(num, run/len(train_batch)))\n",
+    "Elapsed=(time()-time_start)/60\n",
+    "print(\"\\nTraining Time (in minutes) : \",Elapsed)\n",
+    "writer.flush()\n",
+    "writer.close()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "99b1476b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Number Of Images Tested :  10000\n",
+      "Model Accuracy :  0.9787\n"
+     ]
+    }
+   ],
+   "source": [
+    "correct=0\n",
+    "all = 0\n",
+    "for images,labels in test:\n",
+    "  img = images.view(1, 784)\n",
+    "  with tch.no_grad():\n",
+    "    logps = model(img)   \n",
+    "  ps = tch.exp(logps)\n",
+    "  probab = list(ps.numpy()[0])\n",
+    "  prediction = probab.index(max(probab))\n",
+    "  truth = labels\n",
+    "  if(truth == prediction):\n",
+    "    correct += 1\n",
+    "  all += 1\n",
+    "\n",
+    "print(\"Number Of Images Tested : \", all)\n",
+    "print(\"Model Accuracy : \", (correct/all))"
+   ]
+  }
+ ],
+ "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": "3.9.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}