Pinned Loading

1. distilbert-onnx-quantization-benchmark distilbert-onnx-quantization-benchmark Public

   End-to-end ONNX quantization benchmark for DistilBERT — FP32 vs dynamic vs static INT8, comparing accuracy, latency, and model size tradeoffs

   Python

2. Optimized-Inference-Server Optimized-Inference-Server Public

   FastAPI-served MobileNetV3 inference server with ONNX quantization (dynamic vs. static), in-memory caching, and dynamic request batching — 11.4x throughput under concurrent load

   Python

3. Realtime-Lane-Detection Realtime-Lane-Detection Public

   Python

4. Diffusion-Classifier-Based-Multimodal-Emotion-Recognition Diffusion-Classifier-Based-Multimodal-Emotion-Recognition Public

   This is a M.Tech Research Thesis Repository containing the files for the development of the related models.

   Python