Pinned Repositories
imgrec_train_tensorflow_colab
Google Colab (Jupyter) notebook to retrain a model with transfer learning, and make image recognition in Tensorflow.
kaggle_airbusship_maskrcnn_colab
Google Colab (Jupyter) notebook for Kaggle Airbus Ship detection competition, based on Matterport Mask R-CNN
onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
PaddleSeg
Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image Matting, 3D Segmentation, etc.
notebooks
Examples and tutorials on using SOTA computer vision models and techniques. Learn everything from old-school ResNet, through YOLO and object-detection transformers like DETR, to the latest models like Grounding DINO and SAM.
deeplab_retrain_ade20k_colab
Colaboratory (Jupyter) notebook to retrain model for semantic segmentation in Deeplab, Tensorflow. Initial model is MobileNet or Xception with ADE20K dataset. Derived from Tensorflow official demo.
maskrcnn_train_tensorflow_colab
Google Colab (Jupyter) notebook to train Instance Segmentation Tensorflow model with custom dataset, based on Matterport Mask R-CNN
objdet_fizyr_colab
Colab (Jupyter) notebook to train Object Detection model with custom dataset, based on Fizyr implementation of RetinaNet in Keras.
objdet_train_tensorflow_colab
Google Colab (Jupyter) notebook to retrain Object Detection Tensorflow model with custom dataset.
deeplab_retrain_voc2012_colab
Colaboratory (Jupyter) notebook to retrain model for semantic segmentation in Deeplab, Tensorflow. Initial model is MobileNet or Xception with Pascal Voc 2012 dataset. Derived from Tensorflow official demo.
RomRoc's Repositories
RomRoc/objdet_train_tensorflow_colab
Google Colab (Jupyter) notebook to retrain Object Detection Tensorflow model with custom dataset.
RomRoc/maskrcnn_train_tensorflow_colab
Google Colab (Jupyter) notebook to train Instance Segmentation Tensorflow model with custom dataset, based on Matterport Mask R-CNN
RomRoc/objdet_fizyr_colab
Colab (Jupyter) notebook to train Object Detection model with custom dataset, based on Fizyr implementation of RetinaNet in Keras.
RomRoc/deeplab_retrain_ade20k_colab
Colaboratory (Jupyter) notebook to retrain model for semantic segmentation in Deeplab, Tensorflow. Initial model is MobileNet or Xception with ADE20K dataset. Derived from Tensorflow official demo.