Object overview

Every public object with its tags. Type in the box to narrow the table: each word must appear somewhere in the row, so model hybrid finds the hybrid models and regressor finds everything that predicts values. Inspired from sktime tag system: https://www.sktime.net/models/

The same search from code:

from pyqit.base import all_objects, object_overview

all_objects("model", filter_tags={"model_type": "hybrid"})
object_overview()   # every row of the table below, as dicts

Each tag’s meaning is in pyqit/base/_tags.py.

Object	Type	Tags
BasicEntanglerAnsatz	ansatz	authors: phoeenniixx, n_qubits_min: 1
CNOTLadderAnsatz	ansatz	authors: phoeenniixx, n_qubits_min: 1
EfficientSU2Ansatz	ansatz	authors: phoeenniixx, python_dependencies: pennylane-qiskit, n_qubits_min: 1
RealAmplitudesAnsatz	ansatz	authors: phoeenniixx, python_dependencies: pennylane-qiskit, n_qubits_min: 1
SELAnsatz	ansatz	authors: phoeenniixx, n_qubits_min: 1
SimplifiedTwoDesignAnsatz	ansatz	authors: phoeenniixx, n_qubits_min: 2
EarlyStopping	callback	authors: phoeenniixx
HistoryCallback	callback	authors: phoeenniixx
ModelCheckpoint	callback	authors: phoeenniixx
DataModule	datamodule	authors: phoeenniixx
AmplitudeEmbedding	embedding	authors: phoeenniixx, differentiable: False, embedding_type: amplitude, prescale: amplitude, n_qubits_min: 1
AngleEmbedding	embedding	authors: phoeenniixx, differentiable: True, embedding_type: angle, prescale: angle_pi, n_qubits_min: 1
HadamardAngleEmbedding	embedding	authors: phoeenniixx, differentiable: True, embedding_type: angle, prescale: angle_half_pi, n_qubits_min: 1
IQPEmbedding	embedding	authors: phoeenniixx, differentiable: False, embedding_type: iqp, prescale: angle_pi, n_qubits_min: 2
ZZFeatureMap	embedding	authors: phoeenniixx, differentiable: True, embedding_type: zz, prescale: angle_pi, n_qubits_min: 2
DenseClassifier	layer	authors: phoeenniixx, model_type: classical, estimator_type: classifier, is_quantum: False, bp_scale_factor: 0.25, differentiable: True, requires_fit: True
DenseLayer	layer	authors: phoeenniixx, model_type: classical, is_quantum: False, differentiable: True, requires_fit: True
QuantumLayer	layer	authors: phoeenniixx, model_type: quantum, is_quantum: True, differentiable: True, requires_fit: True
CrossEntropyLoss	loss	authors: phoeenniixx, name: cross_entropy, backends: ('pennylane', 'torch'), target_dtype: int
HingeLoss	loss	authors: phoeenniixx, name: hinge, backends: ('pennylane', 'torch'), target_dtype: float
MSELoss	loss	authors: phoeenniixx, name: mse, backends: ('pennylane', 'torch'), target_dtype: float
DataReuploadingClassifier	model	authors: phoeenniixx, model_type: quantum, estimator_type: classifier, is_quantum: True, bp_scale_factor: 0.25, differentiable: True, requires_fit: True
DressedQuantumClassifier	model	authors: phoeenniixx, model_type: hybrid, estimator_type: classifier, is_quantum: True, bp_scale_factor: 0.25, differentiable: True, requires_fit: True
VQCClassifier	model	authors: phoeenniixx, model_type: quantum, estimator_type: classifier, is_quantum: True, bp_scale_factor: 0.25, differentiable: True, requires_fit: True
VQCRegressor	model	authors: phoeenniixx, model_type: quantum, estimator_type: regressor, is_quantum: True, differentiable: True, requires_fit: True
QuantumPipeline	pipeline	authors: phoeenniixx
Trainer	trainer	authors: phoeenniixx