. Ann With Mnist 1

[1]:

12

# we will download 60K train images and 10k test images 
# First we will need to flatten out 28*28 images to 784

[3]:

1234

!python3.11 -m pip install torchvision

stdout

Collecting torchvision Downloading torchvision-0.26.0-cp311-cp311-macosx_11_0_arm64.whl.metadata (5.5 kB) Requirement already satisfied: numpy in /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages (from torchvision) (2.4.3) Collecting torch==2.11.0 (from torchvision) Downloading torch-2.11.0-cp311-cp311-macosx_11_0_arm64.whl.metadata (29 kB) Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages (from torchvision) (10.4.0) Requirement already satisfied: filelock in /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages (from torch==2.11.0->torchvision) (3.24.3) Requirement already satisfied: typing-extensions>=4.10.0 in /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages (from torch==2.11.0->torchvision) (4.15.0) Requirement already satisfied: setuptools<82 in /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages (from torch==2.11.0->torchvision) (65.5.0) Requirement already satisfied: sympy>=1.13.3 in /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages (from torch==2.11.0->torchvision) (1.14.0) Requirement already satisfied: networkx>=2.5.1 in /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages (from torch==2.11.0->torchvision) (3.6.1) Requirement already satisfied: jinja2 in /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages (from torch==2.11.0->torchvision) (3.1.4) Requirement already satisfied: fsspec>=0.8.5 in /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages (from torch==2.11.0->torchvision) (2026.2.0) Requirement already satisfied: mpmath<1.4,>=1.1.0 in /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages (from sympy>=1.13.3->torch==2.11.0->torchvision) (1.3.0) Requirement already satisfied: MarkupSafe>=2.0 in /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages (from jinja2->torch==2.11.0->torchvision) (3.0.2) Downloading torchvision-0.26.0-cp311-cp311-macosx_11_0_arm64.whl (1.9 MB) [2K [90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m1.9/1.9 MB[0m [31m383.4 kB/s[0m eta [36m0:00:00[0ma [36m0:00:01[0m [?25hDownloading torch-2.11.0-cp311-cp311-macosx_11_0_arm64.whl (80.5 MB) [2K [90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[0m [32m80.5/80.5 MB[0m [31m1.6 MB/s[0m eta [36m0:00:00[0m00:01[0m00:02[0m0m [?25hInstalling collected packages: torch, torchvision Attempting uninstall: torch Found existing installation: torch 2.10.0 Uninstalling torch-2.10.0: Successfully uninstalled torch-2.10.0 Successfully installed torch-2.11.0 torchvision-0.26.0 [1m[[0m[34;49mnotice[0m[1;39;49m][0m[39;49m A new release of pip is available: [0m[31;49m24.3.1[0m[39;49m -> [0m[32;49m26.0.1[0m [1m[[0m[34;49mnotice[0m[1;39;49m][0m[39;49m To update, run: [0m[32;49mpip3 install --upgrade pip[0m

[2]:

1

# lets start with importing pytorch

[2]:

123

import torch
import torch.nn as nn # import neural network 
import torch.nn.functional as F

[3]:

123456

from torchvision import datasets,transforms
import numpy as np 
import pandas as pd
from sklearn.metrics import confusion_matrix 
import matplotlib.pyplot as plt
from torch.utils.data import DataLoader

[6]:

12

# MNIST Image file convert to Tensors

[15]:

1

transform=transforms.ToTensor()

[16]:

1

train_data=datasets.MNIST(root='../Data',train=True,download=True,transform=transform)

[17]:

1

test_data=datasets.MNIST(root='../Data',train=False,download=True,transform=transform)

[18]:

12

type(train_data) # this is torch vision

Out[18]:

torchvision.datasets.mnist.MNIST

[19]:

1

train_data[0]  # first tensor

Out[19]:

(tensor([[[0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0118, 0.0706, 0.0706, 0.0706, 0.4941, 0.5333, 0.6863, 0.1020, 0.6510, 1.0000, 0.9686, 0.4980, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.1176, 0.1412, 0.3686, 0.6039, 0.6667, 0.9922, 0.9922, 0.9922, 0.9922, 0.9922, 0.8824, 0.6745, 0.9922, 0.9490, 0.7647, 0.2510, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.1922, 0.9333, 0.9922, 0.9922, 0.9922, 0.9922, 0.9922, 0.9922, 0.9922, 0.9922, 0.9843, 0.3647, 0.3216, 0.3216, 0.2196, 0.1529, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0706, 0.8588, 0.9922, 0.9922, 0.9922, 0.9922, 0.9922, 0.7765, 0.7137, 0.9686, 0.9451, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.3137, 0.6118, 0.4196, 0.9922, 0.9922, 0.8039, 0.0431, 0.0000, 0.1686, 0.6039, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0549, 0.0039, 0.6039, 0.9922, 0.3529, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.5451, 0.9922, 0.7451, 0.0078, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0431, 0.7451, 0.9922, 0.2745, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.1373, 0.9451, 0.8824, 0.6275, 0.4235, 0.0039, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.3176, 0.9412, 0.9922, 0.9922, 0.4667, 0.0980, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.1765, 0.7294, 0.9922, 0.9922, 0.5882, 0.1059, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0627, 0.3647, 0.9882, 0.9922, 0.7333, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.9765, 0.9922, 0.9765, 0.2510, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.1804, 0.5098, 0.7176, 0.9922, 0.9922, 0.8118, 0.0078, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.1529, 0.5804, 0.8980, 0.9922, 0.9922, 0.9922, 0.9804, 0.7137, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0941, 0.4471, 0.8667, 0.9922, 0.9922, 0.9922, 0.9922, 0.7882, 0.3059, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0902, 0.2588, 0.8353, 0.9922, 0.9922, 0.9922, 0.9922, 0.7765, 0.3176, 0.0078, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0706, 0.6706, 0.8588, 0.9922, 0.9922, 0.9922, 0.9922, 0.7647, 0.3137, 0.0353, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.2157, 0.6745, 0.8863, 0.9922, 0.9922, 0.9922, 0.9922, 0.9569, 0.5216, 0.0431, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.5333, 0.9922, 0.9922, 0.9922, 0.8314, 0.5294, 0.5176, 0.0627, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000]]]), 5)

[20]:

1

type(train_data[0])  # this is a tuple

Out[20]:

tuple

[21]:

12

# if we see the length of the this tuple it will be 2 
len(train_data[0])  # the first value of tuple indicates actuall arraya and second one is the digit

Out[21]:

2

[22]:

1

train_data[0][1]  # this array represent the number 5

Out[22]:

5

[23]:

1

image,label=train_data[0]

[24]:

1

image.shape  # since this is greyscaled image hence firts is 1 .

Out[24]:

torch.Size([1, 28, 28])

[25]:

123

plt.imshow(image.reshape((28,28)))  # handwritten 5 
# since matplot it has default color mapping hence we see this dark purpole and yellow color
# but this is actually a grey scale image

Out[25]:

<matplotlib.image.AxesImage at 0x13602f750>

[26]:

1

plt.imshow(image.reshape((28,28)),cmap='gist_yarg')  # handwritten 5 in greyscale

Out[26]:

<matplotlib.image.AxesImage at 0x1357f49d0>

[27]:

123456

# right now out input has 60 K , we will load the training data in images 
torch.manual_seed(101)
train_loader=DataLoader(train_data,batch_size=100,shuffle=True)  # we will only be loading 100 image at a time as batch
# shuffle is require bacause sometime data is organized or sorted 
# all the 0 images , all the 0 images 
# this will create problem in network hence we do sorting

[28]:

1

test_loader=DataLoader(test_data,batch_size=500,shuffle=False) #shuffle is not required here and we can also increase batch size

[29]:

123

# lets see the images in grid first with labels 
from torchvision.utils import make_grid
np.set_printoptions(formatter=dict(int=lambda x:f'{x:4}'))

[30]:

123

# first batch 
for image,label in train_loader:
    break

[31]:

1

image.shape  # 100 images 1 colore channel and 28*28 images

Out[31]:

torch.Size([100, 1, 28, 28])

[32]:

12345

# print first 12 labels 
print('Labels: ',label[:12].numpy())
im=make_grid(image[:12],nrow=12) # default n_row is 8
plt.figure(figsize=(10,4))
plt.imshow(np.transpose(im.numpy(),(1,2,0)))

stdout

Labels: [ 7 2 3 5 8 5 3 6 9 9 1 3]

Out[32]:

<matplotlib.image.AxesImage at 0x136124f90>

[47]:

12345678910111213141516

class MultiLayerPerceptron(nn.Module):
    def __init__(self,in_size=784,out_size=10,layers=[120,84]):  # 28*28 when expanded size will be 784, since there are 10 numbers in 
        super().__init__()
        # since there are 10 numbers in output hence out_size is 8 ,
        # we will only create 2 hidden layers for now hence 120,84 is there 
        self.fc1=nn.Linear(in_size,layers[0])  # fully connected layer using linear function
        self.fc2=nn.Linear(layers[0],layers[1])
        self.fc3=nn.Linear(layers[1],out_size)

    def forward(self,X):
        X=F.relu(self.fc1(X))
        X=F.relu(self.fc2(X))
        X=self.fc3(X)

        return F.log_softmax(X,dim=1) # multi class classification

[49]:

123

torch.manual_seed(101)
model=MultiLayerPerceptron()
model

Out[49]:

MultiLayerPerceptron( (fc1): Linear(in_features=784, out_features=120, bias=True) (fc2): Linear(in_features=120, out_features=84, bias=True) (fc3): Linear(in_features=84, out_features=10, bias=True) )

[50]:

12

for param in model.parameters():
    print(param.numel()) # all the parameters

stdout

94080 120 10080 84 840 10

[51]:

12

# if we use CNN we wll have lot less param

[52]:

12

creterion=nn.CrossEntropyLoss()
optimizer=torch.optim.Adam(model.parameters(),lr=0.001)

[53]:

12

# flattening the images 
image.view(100,-1).shape

Out[53]:

torch.Size([100, 784])

[54]:

123456789101112131415161718192021222324252627282930313233343536373839404142

import time 
start_time=time.time()

# Training 
epochs=10
train_losses=[]
test_losses=[]
train_correct=[]
test_correct=[]

for i in range(epochs):
    trn_correct=0
    tst_correct=0

    for b,(x_train,y_train) in enumerate(train_loader):
        b+=1
        y_pred=model(x_train.view(100,-1))
        loss=creterion(y_pred,y_train)
        predicted=torch.max(y_pred.data,1)[1]  # [0.1,0.0,....0.8]
        batch_corr=(predicted==y_train).sum()
        trn_correct+=batch_corr
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        if b%200==0:
            accuracy=trn_correct.item()*100/(100*b)
            print(f"Epoch {i} batch {b} loss: {loss.item()} accuracy :{accuracy}")
    train_losses.append(loss)
    train_correct.append(trn_correct)
    with torch.no_grad():
        for b,(X_test,y_test) in enumerate(test_loader):
            y_val=model(X_test.view(500,-1))
            predicted=torch.max(y_val.data,1)[1]
            tst_correct+=(predicted==y_test).sum()
    loss=creterion(y_val,y_test)
    test_losses.append(loss)
    test_correct.append(tst_correct)



total_time=time.time()-start_time
print(f"Duration :{total_time/60}")

stdout

Epoch 0 batch 200 loss: 0.2356237769126892 accuracy :83.245 Epoch 0 batch 400 loss: 0.3533071279525757 accuracy :87.5325 Epoch 0 batch 600 loss: 0.13765765726566315 accuracy :89.58166666666666 Epoch 1 batch 200 loss: 0.2450992614030838 accuracy :94.88 Epoch 1 batch 400 loss: 0.139908567070961 accuracy :95.1075 Epoch 1 batch 600 loss: 0.07150521874427795 accuracy :95.37666666666667 Epoch 2 batch 200 loss: 0.08816862106323242 accuracy :96.565 Epoch 2 batch 400 loss: 0.06208188831806183 accuracy :96.66 Epoch 2 batch 600 loss: 0.07086564600467682 accuracy :96.72166666666666 Epoch 3 batch 200 loss: 0.11753450334072113 accuracy :97.63 Epoch 3 batch 400 loss: 0.055651258677244186 accuracy :97.4825 Epoch 3 batch 600 loss: 0.0344504714012146 accuracy :97.52333333333333 Epoch 4 batch 200 loss: 0.10662715137004852 accuracy :98.165 Epoch 4 batch 400 loss: 0.04711269214749336 accuracy :97.995 Epoch 4 batch 600 loss: 0.054924558848142624 accuracy :98.01666666666667 Epoch 5 batch 200 loss: 0.009507461450994015 accuracy :98.44 Epoch 5 batch 400 loss: 0.03661220148205757 accuracy :98.505 Epoch 5 batch 600 loss: 0.057259634137153625 accuracy :98.395 Epoch 6 batch 200 loss: 0.031195903196930885 accuracy :98.845 Epoch 6 batch 400 loss: 0.06201673671603203 accuracy :98.69 Epoch 6 batch 600 loss: 0.08318546414375305 accuracy :98.67 Epoch 7 batch 200 loss: 0.06914353370666504 accuracy :99.16 Epoch 7 batch 400 loss: 0.07898400723934174 accuracy :98.9475 Epoch 7 batch 600 loss: 0.04138811677694321 accuracy :98.88833333333334 Epoch 8 batch 200 loss: 0.005578312091529369 accuracy :99.26 Epoch 8 batch 400 loss: 0.006579724606126547 accuracy :99.1425 Epoch 8 batch 600 loss: 0.09109019488096237 accuracy :99.105 Epoch 9 batch 200 loss: 0.008466478437185287 accuracy :99.405 Epoch 9 batch 400 loss: 0.011405331082642078 accuracy :99.305 Epoch 9 batch 600 loss: 0.023204762488603592 accuracy :99.295 Duration :0.36086444854736327

[46]:

1

x_train.view(100,-1).shape

Out[46]:

torch.Size([100, 784])

[63]:

123

plt.plot([x.item() for x in train_losses],label="Training Loss")
plt.plot([x.item() for x in test_losses],label="Test Loss")
plt.legend()

Out[63]:

<matplotlib.legend.Legend at 0x146bbcb90>

[69]:

123

train_acc=[x/600 for x in train_correct]
test_acc=[x/100 for x in test_correct]

[70]:

123

plt.plot(train_acc,label="Training Accuracy")
plt.plot(test_acc,label="Test Accuracy")
plt.legend()

Out[70]:

<matplotlib.legend.Legend at 0x146c13250>

[71]:

1

test_load_all=DataLoader(test_data,batch_size=100000,shuffle=False)

[72]:

123456

with torch.no_grad():
    correct=0
    for X_test,y_test in test_load_all:
        y_val=model(X_test.view(len(X_test),-1))
        predicted=torch.max(y_val,1)[1]
        correct+=(predicted==y_test).sum()

[73]:

1

100*correct.item()/len(test_data)

Out[73]:

97.82

[74]:

1

confusion_matrix(predicted.view(-1),y_test.view(-1))

Out[74]:

array([[ 970, 0, 5, 0, 1, 2, 5, 2, 3, 1], [ 0, 1125, 3, 0, 0, 0, 3, 7, 0, 3], [ 1, 3, 1002, 1, 1, 0, 2, 8, 4, 0], [ 3, 2, 4, 989, 0, 10, 1, 2, 3, 2], [ 0, 0, 3, 0, 968, 3, 1, 2, 2, 9], [ 0, 0, 0, 6, 0, 865, 5, 1, 3, 4], [ 1, 1, 3, 0, 5, 2, 940, 0, 1, 0], [ 1, 0, 3, 4, 0, 1, 0, 985, 2, 0], [ 3, 4, 9, 3, 1, 7, 1, 2, 951, 3], [ 1, 0, 0, 7, 6, 2, 0, 19, 5, 987]])

[ ]:

1