CODEWITHSUNDEEP
pytorch
joe
joe

Reputation: 99

pytorch doesn't give expected output

Firstly, a bunch of data is classified by the CNN model. Then, I'm trying to make prediction on correctly classified data from first step, which is expected to give an accuracy of 100%. However, I found the result is unstable, sometimes 99+%, but not 100%. Is there anybody know what is the problem with my code? Thank you very much in advance, it has troubled me several days ~ ~

torch.version

'0.3.1.post2'

import numpy as np
import torch 
import torch.nn as nn
from torch.autograd import Variable

n = 2000
data = np.random.randn(n, 1, 10, 10)
label = np.random.randint(2, size=(n, ))

def test_pred(model, data_test, label_test):

    data_batch = data_test
    labels_batch = label_test

    images = torch.autograd.Variable(torch.FloatTensor(data_batch))
    labels = torch.autograd.Variable(torch.FloatTensor(labels_batch))

    outputs = model(images)

    _, predicted = torch.max(outputs.data, 1)

    correct = (np.array(predicted) == labels_batch).sum()

    label_pred = np.array(predicted)

    acc = correct/len(label_test)
    print(" acc:", acc)

    return acc, label_pred

class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(1, 16, kernel_size=5, padding=2),
            nn.BatchNorm2d(16),
            nn.ReLU(),
            nn.MaxPool2d(2))
        self.layer2 = nn.Sequential(
            nn.Conv2d(16, 32, kernel_size=5, padding=2),
            nn.BatchNorm2d(32),
            nn.ReLU(),
            nn.MaxPool2d(2))
        self.fc = nn.Linear(128, 2)

    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = out.view(out.size(0), -1)
        out = self.fc(out)
        return out

cnn = CNN()

[_, label_pred] = test_pred(cnn, data, label)

print("Acc:", np.mean(label_pred==label))
# Given the correctly classified data in previous step, expect to get 100% accuracy
# Why it sometimes doesn't give a 100% accuracy ?
print("Using selected data size {}:".format(data[label_pred==label].shape))
_, _ = test_pred(cnn, data[label_pred==label], label[label_pred==label])

output:

acc: 0.482

Acc: 0.482

Using selected data size (964, 1, 10, 10):

acc: 0.9979253112033195

Upvotes: 0

Views: 221

Answers (1)

Manuel Lagunas
Manuel Lagunas

Reputation: 2751

Seems like you did not set the network to evaluation mode which might be causing some problems, specially with the BatchNorm layers. Do 

cnn = CNN()
cnn.eval()

and it should work.

Upvotes: 1

Related Questions