Category: Deep Learning

In this article, we train DINOv2 Small Patch-14 model for image classification on a cotton disease and compare the results between fine-tuning and transfer learning. ...

In this article, we explore the DINOv2 Self-Supervised Computer Vision model for image classification, video classification, semantic segmentation, and depth estimation. ...

In this article, we will be pretraining a semantic segmentation model on the COCO dataset and run inference to analyze the results. ...

In this article, we use different Torchvision backbones for creating DeepLab segmentation models and train it on the Pascal VOC semantic segmentation dataset. ...

In this article, we are adding a custom model to Ollama. We take a fine-tuned Hugging Face model, StarCoder2-3B, convert it to GGUF format, add it to local Ollama, and push the model to Ollama hub. ...