Update README.md

README.md

@@ -1,3 +1,16 @@
+---
+license: mit
+datasets:
+- GATE-engine/omniglot
+language:
+- ko
+pipeline_tag: image-classification
+tags:
+- pytorch
+- few-shot-learning
+- one-shot-learning
+- meta-learning
+---
 `torch` `torchvision` `tqdm`
 
 This implementation is inspired by **"Prototypical Networks for Few-Shot Learning" (Snell et al., 2017)**.
@@ -65,4 +78,4 @@ Prototypical Networks are a powerful approach for **few-shot learning**, where t
 * **Embedding Representation with CNN**: Each input image is passed through a convolutional encoder to obtain a feature embedding.
 * **Prototype Computation**: The prototype for each class is computed as the mean of the embeddings of support samples belonging to that class.
 * **Distance-Based Classification**: Query samples are classified based on the distance (using `torch.cdist`) to the nearest prototype.
-* **Optimization**: The network is trained to minimize the distance between query samples and their correct prototypes while maximizing the distance to incorrect ones.
+* **Optimization**: The network is trained to minimize the distance between query samples and their correct prototypes while maximizing the distance to incorrect ones.