Submissions are scored on the log loss:
$$
\textrm{LogLoss} = - \frac{1}{n} \sum_{i=1}^n \left[ y_i \log(\hat{y}_i) + (1 - y_i) \log(1 - \hat{y}_i)\right],
$$
where
n is the number of images in the test set
\\( \hat{y}_i \\) is the predicted probability of the image being a dog
\\( y_i \\) is 1 if the image is a dog, 0 if cat
\\( log() \\) is the natural (base e) logarithm
A smaller log loss is better.
Submission File
For each image in the test set, you must submit a probability that image is a dog. The file should have a header and be in the following format:
id,label
1,0.5
2,0.5
3,0.5
...