Model
Bases: StaticCollection
A class describing a model that was trained on a particular dataset.
Attributes:
Name | Type | Description |
---|---|---|
name |
String
|
The name of the model. |
metadata |
Dictionary
|
A dictionary of metadata that describes the model. |
Examples:
>>> Model.create(name="model1")
>>> Model.create(name="model1", metadata={})
>>> Model.create(name="model1", metadata={"foo": "bar", "pi": 3.14})
Source code in valor/coretypes.py
639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 |
|
Functions
valor.Model.__init__(*, name, metadata=None, connection=None)
Creates a local instance of a model.
Use 'Model.create' classmethod to create a model with persistence.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
name
|
String
|
The name of the model. |
required |
metadata
|
Dictionary
|
A dictionary of metadata that describes the model. |
None
|
connection
|
ClientConnection
|
An initialized client connection. |
None
|
Source code in valor/coretypes.py
valor.Model.add_prediction(dataset, prediction)
Add a prediction to the model.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
dataset
|
Dataset
|
The dataset that is being operated over. |
required |
prediction
|
Prediction
|
The prediction to create. |
required |
Source code in valor/coretypes.py
valor.Model.add_predictions(dataset, predictions, timeout=10.0)
Add multiple predictions to the model.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
dataset
|
Dataset
|
The dataset that is being operated over. |
required |
predictions
|
List[Prediction]
|
The predictions to create. |
required |
timeout
|
float
|
The number of seconds the client should wait until raising a timeout. |
10.0
|
Source code in valor/coretypes.py
valor.Model.create(name, metadata=None, connection=None, **_)
classmethod
Creates a model that persists in the back end.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
name
|
str
|
The name of the model. |
required |
metadata
|
dict
|
A dictionary of metadata that describes the model. |
None
|
connection
|
ClientConnection
|
An initialized client connection. |
None
|
Source code in valor/coretypes.py
valor.Model.delete(timeout=0)
Delete the Model
object from the back end.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
timeout
|
int
|
Sets a timeout in seconds. |
0
|
Source code in valor/coretypes.py
valor.Model.evaluate_classification(datasets, filters=None, label_map=None, pr_curve_max_examples=1, metrics_to_return=None, *_, allow_retries=False, timeout=None)
Start a classification evaluation job.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
datasets
|
Union[Dataset, List[Dataset]]
|
The dataset or list of datasets to evaluate against. |
required |
filters
|
Filter
|
Optional set of constraints to filter evaluation by. |
None
|
label_map
|
Dict[Label, Label]
|
Optional mapping of individual labels to a grouper label. Useful when you need to evaluate performance using labels that differ across datasets and models. |
None
|
metrics_to_return
|
List[MetricType]
|
The list of metrics to compute, store, and return to the user. |
None
|
allow_retries
|
bool
|
Option to retry previously failed evaluations. |
= False
|
timeout
|
float
|
The number of seconds the client should wait until raising a timeout. |
None
|
Returns:
Type | Description |
---|---|
Evaluation
|
A job object that can be used to track the status of the job and get the metrics of it upon completion. |
Source code in valor/coretypes.py
valor.Model.evaluate_detection(datasets, filters=None, convert_annotations_to_type=None, iou_thresholds_to_compute=None, iou_thresholds_to_return=None, label_map=None, recall_score_threshold=0, metrics_to_return=None, pr_curve_iou_threshold=0.5, pr_curve_max_examples=1, *_, allow_retries=False, timeout=None)
Start an object-detection evaluation job.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
datasets
|
Union[Dataset, List[Dataset]]
|
The dataset or list of datasets to evaluate against. |
required |
filters
|
Filter
|
Optional set of constraints to filter evaluation by. |
None
|
convert_annotations_to_type
|
AnnotationType
|
Forces the object detection evaluation to compute over this type. |
None
|
iou_thresholds_to_compute
|
List[float]
|
Thresholds to compute mAP against. |
None
|
iou_thresholds_to_return
|
List[float]
|
Thresholds to return AP for. Must be subset of |
None
|
label_map
|
Dict[Label, Label]
|
Optional mapping of individual labels to a grouper label. Useful when you need to evaluate performance using labels that differ across datasets and models. |
None
|
recall_score_threshold
|
float
|
The confidence score threshold for use when determining whether to count a prediction as a true positive or not while calculating Average Recall. |
0
|
metrics_to_return
|
List[MetricType]
|
The list of metrics to compute, store, and return to the user. |
None
|
pr_curve_iou_threshold
|
float
|
The IOU threshold to use when calculating precision-recall curves. Defaults to 0.5. |
0.5
|
pr_curve_max_examples
|
int
|
The maximum number of datum examples to store when calculating PR curves. |
1
|
allow_retries
|
bool
|
Option to retry previously failed evaluations. |
= False
|
timeout
|
float
|
The number of seconds the client should wait until raising a timeout. |
None
|
Returns:
Type | Description |
---|---|
Evaluation
|
A job object that can be used to track the status of the job and get the metrics of it upon completion. |
Source code in valor/coretypes.py
906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 |
|
valor.Model.evaluate_segmentation(datasets, filters=None, label_map=None, metrics_to_return=None, *_, allow_retries=False, timeout=None)
Start a semantic-segmentation evaluation job.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
datasets
|
Union[Dataset, List[Dataset]]
|
The dataset or list of datasets to evaluate against. |
required |
filters
|
Filter
|
Optional set of constraints to filter evaluation by. |
None
|
label_map
|
Dict[Label, Label]
|
Optional mapping of individual labels to a grouper label. Useful when you need to evaluate performance using labels that differ across datasets and models. |
None
|
metrics_to_return
|
List[MetricType]
|
The list of metrics to compute, store, and return to the user. |
None
|
allow_retries
|
bool
|
Option to retry previously failed evaluations. |
= False
|
timeout
|
float
|
The number of seconds the client should wait until raising a timeout. |
None
|
Returns:
Type | Description |
---|---|
Evaluation
|
A job object that can be used to track the status of the job and get the metrics of it upon completion |
Source code in valor/coretypes.py
1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 |
|
valor.Model.evaluate_text_generation(datasets, metrics_to_return, filters=None, llm_api_params=None, metric_params=None)
Start a classification evaluation job.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
datasets
|
Union[Dataset, List[Dataset]]
|
The dataset or list of datasets to evaluate against. |
required |
metrics_to_return
|
List[MetricType]
|
The list of metrics to compute, store, and return to the user. This is not optional for text generation evaluations. |
required |
filters
|
Filter
|
Optional set of constraints to filter evaluation by. |
None
|
llm_api_params
|
Dict[str, Union[str, dict]]
|
A dictionary of parameters for the LLM API. |
None
|
metric_params
|
Dict[MetricType, Dict[str, Any]]
|
A dictionary of parameters for the metrics used in the evaluation. The keys should be the metrics and the values should be dictionaries of parameters for those metrics. |
None
|
Returns:
Type | Description |
---|---|
Evaluation
|
A job object that can be used to track the status of the job and get the metrics of it upon completion. |
Source code in valor/coretypes.py
1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 |
|
valor.Model.finalize_inferences(dataset)
Finalizes the model over a dataset such that new predictions cannot be added to it.
valor.Model.get(name, connection=None)
classmethod
Retrieves a model from the back end database.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
name
|
str
|
The name of the model. |
required |
connection
|
ClientConnnetion
|
An optional Valor client object for interacting with the API. |
None
|
Returns:
Type | Description |
---|---|
Union[Model, None]
|
The model or 'None' if it doesn't exist. |
Source code in valor/coretypes.py
valor.Model.get_evaluations(metrics_to_sort_by=None, *_, timeout=None)
Get all evaluations associated with a given model.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
metrics_to_sort_by
|
dict[str, str | dict[str, str]]
|
An optional dict of metric types to sort the evaluations by. |
None
|
timeout
|
float
|
The number of seconds the client should wait until raising a timeout. |
None
|
Returns:
Type | Description |
---|---|
List[Evaluation]
|
A list of |
Source code in valor/coretypes.py
valor.Model.get_labels()
Get all labels associated with a given model.
Returns:
Type | Description |
---|---|
List[Label]
|
A list of |
Source code in valor/coretypes.py
valor.Model.get_prediction(dataset, datum)
Get a particular prediction.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
dataset
|
Union[Dataset, str]
|
The dataset the datum belongs to. |
required |
datum
|
Union[Datum, str]
|
The desired datum. |
required |
Returns:
Type | Description |
---|---|
Union[Prediction, None]
|
The matching prediction or 'None' if it doesn't exist. |