osmr/imgclsmob
A research repository implementing convolutional neural network models for image classification, segmentation, detection, and pose estimation across PyTorch, TensorFlow, Keras, MXNet, and Chainer.
Velocity · 7d
+1.0
★ / day
Trend
→steady
star history
This repository provides (re)implementations of various deep learning models primarily for computer vision tasks, including classification, semantic segmentation, object detection, and human pose estimation. Models are implemented in multiple frameworks (MXNet/Gluon, PyTorch, Chainer, Keras, TensorFlow 1.x/2.x) and distributed as separate PIP packages. The repo includes training scripts, evaluation tools, and model conversion utilities with pretrained weights on datasets like ImageNet, CIFAR, COCO, and Pascal VOC.