vladimir-chernykh / coreml-performance
Utility to test the performance of CoreML models.
☆68Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for coreml-performance
- Export utility for unconstrained channel pruned models☆67Updated last year
- ☆70Updated 10 months ago
- Research publication code for "Forward Compatible Training for Large-Scale Embedding Retrieval Systems", CVPR 2022, and "FastFill: Effici…☆54Updated last year
- This repo provides scripts for converting tensorflow and pytorch models to coreml for variety of tasks. Converted models like efficientDe…☆39Updated 4 years ago
- 4K-Face: A Dataset with Huge Scale-variance Faces☆32Updated 5 years ago
- CoreML Model Zoo: collection of unified and converted pre-trained models☆23Updated 4 years ago
- Page for the CVPR 2023 Tutorial - Efficient Neural Networks: From Algorithm Design to Practical Mobile Deployments☆13Updated last year
- Semantic segmentation on iPhone using ESPNetv2☆74Updated 5 years ago
- A code generator from ONNX to PyTorch code☆133Updated 2 years ago
- This repository contains the official implementation of the research paper, "An Improved One millisecond Mobile Backbone".☆729Updated 2 years ago
- Overhead-free ONNX graph inference engine with Metal under the hood☆50Updated 2 years ago
- DeltaCNN End-to-End CNN Inference of Sparse Frame Differences in Videos☆60Updated last year
- ☆191Updated 3 months ago
- TVMScript kernel for deformable attention☆24Updated 2 years ago
- Count number of parameters / MACs / FLOPS for ONNX models.☆89Updated 3 weeks ago
- ☆30Updated 5 months ago
- Scripts for exporting YOLOv5 models to CoreML and benchmarking it.☆68Updated 3 years ago
- Scailable ONNX python tools☆96Updated 3 weeks ago
- Source code for my blog post series "On-device training with Core ML"☆99Updated 4 years ago
- Adam with minor modifications which give significant improvement☆19Updated 3 years ago
- Using ideas from product quantization for state-of-the-art neural network compression.☆145Updated 3 years ago
- A criticism of a recent paper on buggy image downsampling methods in popular image processing and deep learning libraries.☆72Updated 2 years ago
- Style Transfer a face into cartoon without GAN. A UNet++ network with MobileNet v3 backbone optimized for mobile frameworks☆25Updated 2 years ago
- [ICML 2022] "DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks", by Yonggan …☆69Updated 2 years ago
- MnasNet snapshot☆34Updated 5 years ago
- A very simple tool that compresses the overall size of the ONNX model by aggregating duplicate constant values as much as possible.☆52Updated 2 years ago
- Re-implementation of pSp that use mobilenet-v3 and stylegan2-256p☆19Updated 3 years ago
- TF2 implementation of knowledge distillation using the "function matching" hypothesis from https://arxiv.org/abs/2106.05237.☆87Updated 3 years ago
- MegEngine到其他框架的转换器☆67Updated last year
- ☆57Updated 2 years ago