Ahmet Erdem's starred repositories
pytorch-image-models
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
best-of-ml-python
๐ A ranked list of awesome machine learning Python libraries. Updated weekly.
pytorch-grad-cam
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
segmentation_models
Segmentation models with pretrained backbones. Keras and TensorFlow Keras.
h2o-llmstudio
H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/
make-sense
Free to use online tool for labelling photos. https://makesense.ai
docker-python
Kaggle Python docker image
lm-format-enforcer
Enforce the output format (JSON Schema, Regex etc) of a language model
lofo-importance
Leave One Feature Out Importance
dfdc_deepfake_challenge
A prize winning solution for DFDC challenge
bert-embedding
๐ก Token level embeddings from BERT model on mxnet and gluonnlp
kaggle_salt_bes_phalanx
Winning solution for the Kaggle TGS Salt Identification Challenge.
GroupChatApp
Developed a Group chat application using Flutter and Firebase, where users can register and create groups or join already existing groups and start conversing with each other.
kinship_prediction
Deep Neural Networks for Kinship prediction using face photos
kaggle-google-quest
Google QUEST Q&A Labeling Kaggle Competition 6th Place Solution
flutter-gen-l10n-example
Flutter app localization example with gen_l10n
rapids-kaggle-utils
High level utility functions for using Rapids on Kaggle Competitions
Diversity-Sampling
GPU-accelerated algorithm for subsampling datasets while preserving diversity
matching-pairs
A classic matching game played with a set of cards that improves memory and concentration.
kaggle-quest
TPU-Ready TF 2.1 Solution to Google QUEST Q&A Labeling using Siamese RoBERTa Encoder Model