Results for “deep-learning”

Trains, evaluates, exports, and runs inference for person re-identification models using TAO, learning discriminative embeddings for cross-camera matching.

Post-train LLMs with reinforcement learning using the slime framework, which integrates Megatron-LM for training and SGLang for rollout generation.

Predict continuous values from temporal sequences using aeon's time series regressors, covering convolutional, deep learning, distance-based, feature-based, hybrid, interval-based, and shapelet-based approaches.

Lists TAO Skill Bank capabilities, models, and AutoML support by running packaged scripts.

Organizes PyTorch code with a Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks, and minimal boilerplate. Scales from laptop to supercomputer with the same code.

Trains, evaluates, exports, quantizes, and runs inference for SegFormer semantic segmentation models using NVIDIA TAO.

Provides expert guidance for distributed training with DeepSpeed, covering ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, and sparse attention.

Import object detection models from HuggingFace or NVIDIA NGC into a DeepStream pipeline with automated ONNX download, TensorRT engine build, custom parser, multi-stream benchmark, and PDF report generation.

Train, evaluate, export, quantize, and run inference for a Deformable DETR 2D object detection model using TAO, with deformable attention for efficient multi-scale feature processing.

Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard, MLflow), and distributed training (DDP, FSDP, DeepSpeed) for scalable neural network training.

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace, covering architectures, routing, load balancing, and expert parallelism.

Detect poisoned training data and backdoored models across the ML pipeline using statistical analysis, activation clustering, and spectral signatures.

Trains language models with Direct Preference Optimization using preference pairs, covering DPOTrainer setup, dataset preparation, and beta tuning for stable preference learning without explicit reward models.

Guides implementation of new model architectures in NeMo AutoModel through five phases: discovery, implementation, registration, validation, and testing.

Process whole slide images for digital pathology: detect tissue, extract tiles, and prepare datasets for deep learning pipelines.

Train large-scale MoE models with FP8/INT4 low-precision RL, speculative decoding, and train-inference alignment using the miles framework.

Provides deep generative models for single-cell omics analysis, including probabilistic batch correction, transfer learning, differential expression, and multi-modal integration.

Configure and validate CPU offloading for Megatron Bridge training, including activation offloading and optimizer state offloading with HybridDeviceOptimizer.

Optimizes MoE expert-parallel communication overlap in Megatron Bridge, covering dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling.

Loads and processes whole-slide pathology images, builds spatial graphs, trains deep learning models, and analyzes multiplexed immunofluorescence data across 160+ slide formats.

Train, evaluate, export, and run inference on TAO action-recognition models for classifying temporal actions in video clips using RGB, optical flow, or joint input.

Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.

Guides LLM post-training with RL using slime, a Megatron+SGLang framework for training GLM, Qwen, DeepSeek, and Llama models with GRPO, async, and multi-turn workflows.