Computes and stores the average and current value

base data loader class that contains functions shared by almost all data loader classes.

evaluator to evaluate predictions Args: name (str): the name of the evaluator function

r"""Single Layer GIN from `Strategies for Pre-training Graph Neural Networks <https://arxiv.org/abs/1905.12265>`__ Parameters ----------

MLP with linear output

Wrapper of DeepPurpose model

Global Average pooling Widely used in ResNet, Inception, DenseNet, etc.

r"""Single GCN layer from `Semi-Supervised Classification with Graph Convolutional Networks <https://arxiv.org/abs/1609.02907>`__ Parameters

Element-wise SiLU non-linearity.

Data loader class to load datasets in ADME task. More info: https://tdcommons.ai/single_pred_tasks/adme/ Args: name (str): the dataset na

r""" References: Ren et al., Balanced Meta-Softmax for Long-Tailed Visual Recognition, NeurIPS 2020. Equation: Loss(x, c) = -log(\frac{n_

Data loader class to load datasets in Bioactivity task, e.g. HIV replication inhibition Args: name (str): the dataset name. path

r""" References: Class-Dependent Temperatures (CDT) Loss, Ye et al., Identifying and Compensating for Feature Deviation in Imbalanced Deep Lea

Data loader class to load datasets in Catalyst Prediction task More info: https://tdcommons.ai/multi_pred_tasks/catalyst/ Task Descriptio

r""" Reference: Cui et al., Class-Balanced Loss Based on Effective Number of Samples. CVPR 2019. Equation: Loss(x, c) = \frac{1-\beta

r""" Reference: Li et al., Focal Loss for Dense Object Detection. ICCV 2017. Cui et al., Class-Balanced Loss Based on Effective Number of

The basic config class for models, modules, and dadaloaders The designer: The one who design the Config for a corresponding class The use

The interface for the configurable object

r""" Equation: Loss(z, c) = - (\frac{N_min}{N_c})^\gamma * CrossEntropy(z, c), where gamma is a hyper-parameter to control the weights

r"""Cross entropy loss with label-aware smoothing regularizer. Reference: Zhong et al. Improving Calibration for Long-Tailed Recognition.

r"""Cross entropy loss with label smoothing regularizer. Reference: Szegedy et al. Rethinking the Inception Architecture for Computer Vision.

Data loader class to load datasets in Drug-Drug Interaction Prediction task More info: https://tdcommons.ai/multi_pred_tasks/ddi/ Task Descr

Data loader class to load datasets in Drug-Target Interaction Prediction task. More info: https://tdcommons.ai/multi_pred_tasks/dti/ Regress

A base data loader class that each multi-instance prediction task dataloader class can inherit from. Attributes: TODO

A base data loader class that each bi-instance prediction task dataloader class can inherit from. Attributes: TODO

A base data loader class. Args: name (str): The dataset name. path (str): The path to save the data file label_name (str): For multi-label dat

Knowledge Distillation References: Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. arXiv p

r"""GCN from `Semi-Supervised Classification with Graph Convolutional Networks <https://arxiv.org/abs/1609.02907>`__ Parameters ----------

r"""Graph Isomorphism Network from `Strategies for Pre-training Graph Neural Networks <https://arxiv.org/abs/1905.12265>`__ This module is for

r""" References: Seulki et al., Influence-Balanced Loss for Imbalanced Visual Classification, ICCV 2021.

LDAMLoss is modified from the official PyTorch implementation in LDAM (https://github.com/kaidic/LDAM-DRW). References: Cao et al., Lear

Data loader class to load datasets in Protein-Protein Interaction Prediction task. More info: https://tdcommons.ai/multi_pred_tasks/ppi/ Tas

Data loader class to load datasets in QM (Quantum Mechanics Modeling) task. More info: https://tdcommons.ai/single_pred_tasks/qm/ Args: n

Data loader class to load datasets in Reaction Type Prediction task Task Description: Given reactant and product set X, predict the reation ty

Data loader class to load datasets in ReactType (Reaction Type Prediction) task. Args: name (str): the dataset name. path (str,

r""" Reference: Tan et al., Equalization Loss for Long-Tailed Object Recognition. CVPR 2020. SEQL means softmax equalization loss Eq

The simple version of Config.

Summary Attributes: entity1_name (str): Description entity2_name (str): Description two_types (bool): Description

Data loader class to test the single instance prediction data loader. Args: name (str): the dataset name. path (str, optional):

Data loader class to load datasets in Tox (Toxicity Prediction) task. More info: https://tdcommons.ai/single_pred_tasks/tox/ Args: name (

Data loader class to load datasets in Transposition Prediction task. More info: https://tdcommons.ai/single_pred_tasks/epitope/ Args: nam

Data loader class to load datasets in Yields (Reaction Yields Prediction) task. More info: https://tdcommons.ai/single_pred_tasks/yields/ Args:

Data loader class to load datasets in Yields (Reaction Yields Prediction) task. More info: https://tdcommons.ai/single_pred_tasks/yields/ Args: