diff --git a/README.md b/README.md index d5f4184630d6321b71d916400d61eae3faf439d4..6a4fb38a8923fbd2b8559f39a0b18ee9d468e4e2 100644 --- a/README.md +++ b/README.md @@ -22,7 +22,7 @@ The two models are tested on the image database CIFAR-10 which consists of 60 00 - `read_cifar(path)`: takes the path of the directory containing the six batches and returns a matrix `data` and a vector `labels`. - `split_dataset(data, labels, split_factor)`: randomly splits the dataset into a training set and a test set with a specified split factor. - +m ### K-Nearest Neighbors 3. The Python file named `knn.py` is composed of: @@ -55,9 +55,18 @@ The two models are tested on the image database CIFAR-10 which consists of 60 00 5. In the `results` folder there are three plot images: - `knn.png`: refers to the knn algorithm, it represents the plot of the accuracy evolution along increasing value of 'k' (from 1 to 20) + <div style="text-align:center;"> + <img src="results/knn.png" alt="knn" width="300" height="200"> + </div> + - `mlp.png`: refers to the MLP neural network, it represents the plot of the training accuracies evolution along 100 epochs - `loss.png`: refers to the MLP neural network, it represents the plot of the loss evolution along 100 epochs (further proof that the network works) +<div style="text-align:center;"> + <img src="results/mlp.png" alt="mlp" width="300" height="200"> + <img src="results/loss.png" alt="loss" width="300" height="200"> +</div> + ## Usage 1. Clone the repository.