How aria-funded-trend/ihms works
This repository is a research implementation of the Co⁴ architecture, with reinforcement-learning experiments and a separate vision-classification implementation. The documented workflow configures and trains agents or vision models, evaluates experiments, and uses pretrained checkpoints; vision inference also loads weights and produces class predictions. Sampled RL task code shows environment construction and wrappers, while vision source shows the model-to-attention stack. Some training and evaluation wiring is documented only at repository level, so those links are identified as documented rather than inferred from unsampled code.
Main entry points: inference.py Image inference · util.py RL utilities · eval_agent.py RL evaluation · train_agent.py RL training
Components 22
RL experiments
- RL training
Reinforcement Learning/AttentionNeuron/train_agent.py - RL evaluation
Reinforcement Learning/AttentionNeuron/eval_agent.py - RL utilities
Reinforcement Learning/AttentionNeuron/util.py - Task factory
Reinforcement Learning/AttentionNeuron/util.py - Solution factory
Reinforcement Learning/AttentionNeuron/util.py - RL environments
Reinforcement Learning/AttentionNeuron/tasks/rl_tasks.py - CartPole dynamics
Reinforcement Learning/AttentionNeuron/tasks/cartpole_env.py - Atari wrappers
Reinforcement Learning/AttentionNeuron/tasks/atari_wrappers.py - RL policies
Reinforcement Learning/AttentionNeuron/solutions/torch_solutions.py - RL modulation layers
Reinforcement Learning/AttentionNeuron/solutions/torch_modules.py - Solution contract
Reinforcement Learning/AttentionNeuron/solutions/base_solution.py
Vision models
- Image inference
Vision/object_recognition/inference.py - Vision evaluation
Vision/object_recognition/evaluation.py - Vision transformer
Vision/object_recognition/vit.py - Transformer blocks
Vision/object_recognition/transformer.py - Modulated attention
Vision/object_recognition/attention.py
Experiment assets
- Experiment configs
Reinforcement Learning/AttentionNeuron/configs - Pretrained checkpoints
Reinforcement Learning/AttentionNeuron/pretrained
Other components
- Researcher
- Image input
- Class predictions
- Label service
Connections 23
- Researcher → RL training: starts training
README.md - Researcher → RL evaluation: starts evaluation
README.md - Researcher → Image inference: requests inference
- RL training → Experiment configs: uses configurations
README.md - RL evaluation → Experiment configs: uses configurations
README.md - RL training → RL utilities: uses utilities
Reinforcement Learning/AttentionNeuron/train_agent.py - RL evaluation → RL utilities: uses utilities
Reinforcement Learning/AttentionNeuron/eval_agent.py - RL utilities → Solution contract: checks solution type
Reinforcement Learning/AttentionNeuron/util.py - RL utilities → Task factory: constructs tasks
Reinforcement Learning/AttentionNeuron/util.py - RL utilities → Solution factory: constructs solutions
Reinforcement Learning/AttentionNeuron/util.py - RL environments → CartPole dynamics: constructs environment
Reinforcement Learning/AttentionNeuron/tasks/rl_tasks.py - RL environments → Atari wrappers: wraps Atari environment
Reinforcement Learning/AttentionNeuron/tasks/rl_tasks.py - RL policies → RL modulation layers: instantiates layers
Reinforcement Learning/AttentionNeuron/solutions/torch_solutions.py - RL policies → Solution contract: implements contract
Reinforcement Learning/AttentionNeuron/solutions/torch_solutions.py - RL evaluation → Pretrained checkpoints: loads pretrained models
README.md - Image input → Image inference: provides image
Vision/object_recognition/inference.py - Image inference → Vision transformer: builds model
Vision/object_recognition/inference.py - Vision evaluation → Vision transformer: evaluates model
Vision/object_recognition/evaluation.py - Vision transformer → Transformer blocks: uses blocks
Vision/object_recognition/vit.py - Transformer blocks → Modulated attention: selects attention
Vision/object_recognition/transformer.py - Image inference → Pretrained checkpoints: loads weights
- Image inference → Label service: fetches labels
Vision/object_recognition/inference.py - Image inference → Class predictions: returns top classes
Vision/object_recognition/inference.py