Results for “fsproj”

Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.

Provides expert guidance on PyTorch Fully Sharded Data Parallel (FSDP) training, covering parameter sharding, mixed precision, CPU offloading, and FSDP2.

Trains, evaluates, exports, and runs inference for FastFoundationStereo (FFS) stereo depth estimation models, a distilled variant of FoundationStereo with lower latency.

Evaluates speaker verification models by computing true positive rate at fixed false positive rate thresholds, probing embedding space separation of same-speaker versus different-speaker pairs.