javier-marti-isasi Goto Github PK

03mair-algoritmos-de-optimizacion

binary-semantic-segmentation-using-u-net

Binary semantic segmentation using U-Net (in Keras)

color-based-tracking-with-opencv

In this real-case scenario, an advanced Computer Vision project successfully tracks the tip of a glowing steel bar using color-based tracking techniques with OpenCV.

finetuning-stable-diffusion

Finetuning Stable Diffusion 2.0 and Stable Diffusion 1.5

finetuning_yolov5m_on_custom_dataset

Object detection YOLOv5m training on custom dataset with PyTorch using Transfer Learning and Fine Tuning. Inference on videos.

gans-with-limited-data

BigGAN training with limited data using Transfer Learning, Data Augmentation and Conistency Regularization.

market_alarms

multiclass-semantic-segmentation-using-u-net

Multiclass semantic segmentation using U-Net with Keras.

object-detection-with-mobilenet-ssd

Object detection with MobileNet SSD, pretrained on the MS COCO dataset and fine-tuned on PASCAL VOC, implemented with OpenCV.

ocr-free-document-understanding-with-donut-transformer

This project tackles a real-world challenge of automating client document processing, with a focus on enhancing document classification, error detection, data extraction, and validation.

text-to-image-generation-with-stable-diffusion

Stable Diffusion is a text-to-image latent diffusion model created by the researchers and engineers from CompVis, Stability AI and LAION. It is trained on 512x512 images from a subset of the LAION-5B database.

yolov5m-training-using-finetuning-and-data-augmentation-on-a-custom-labeled-dataset

Object detection YOLOv5m finetuning on custom dataset with PyTorch. The custom dataset was labeled in CVAT and preprocessed in Roboflow. Data augmentation is implemented in the last experiments. Inference on images.