robometer/rewardeval_ui
4
1o
2 �TiW3 � @ sH d dl mZmZ d dlZd dlmZmZ d dlm Z G dd� de �Z4dS )� )�Dict�AnyN)�PreferenceSample�5Trajectory)�RFMBaseSamplerc @ s: e Zd ZdZdeeef defdd�Zdd� Z dd � Z6d7S ) � BaseQualityPreferenceSamplera Base class for quality preference samplers.8 9 Subclasses should implement `_generate_all_sample_indices` to define how10 trajectories are paired. This base class provides the common `_generate_sample_from_indices`11 method that loads and processes the trajectories.12 �sample_idx_info�returnc C s� |d }|d }| j | }| j | }|d |d |d |d |d d�}|�d �d13ur2|�d �|d < | j||d �}|d |d |d |d |d d�}|�d �d14urY|�d �|d < | j||d �} t| d d
�}15t|| |16d�} | S )z-Generate a single sample from stored indices.�chosen_traj_idx�rejected_traj_idx�
quality_label� data_source�task�id�frames)r r
r r �17video_path�partial_successN)�traj�metadata�data_gen_strategy�quality_preference)�chosen_trajectory�rejected_trajectoryr )�dataset�get�_get_traj_from_data�getattrr ) �selfr �18chosen_idx� rejected_idx� chosen_traj�
rejected_traj�chosen_metadatar �rejected_metadatar r �sample� r% �;/scr/aliang80/reward_fm/rfm/data/samplers/eval/base_pref.py� _generate_sample_from_indices sF 1920���� �z:BaseQualityPreferenceSampler._generate_sample_from_indicesc C s21 t | j�S �N)�len�sample_indices)r r% r% r& �__len__E s 22z$BaseQualityPreferenceSampler.__len__c C s | � | j| �S r( )r' r* )r �idxr% r% r& � __getitem__H s z(BaseQualityPreferenceSampler.__getitem__N) �__name__�23__module__� __qualname__�__doc__r �strr r r' r+ r- r% r% r% r& r s24 4 r ) �typingr r �numpy�np�rfm.data.dataset_typesr r �rfm.data.samplers.baser r r% r% r% r& �<module> s25