Reference for ultralytics/engine/validator.py
Note
This file is available at https://github.com/ultralytics/ultralytics/blob/main/ultralytics/engine/validator.py. If you spot a problem please help fix it by contributing a Pull Request 🛠️. Thank you 🙏!
ultralytics.engine.validator.BaseValidator
BaseValidator.
A base class for creating validators.
Attributes:
Name | Type | Description |
---|---|---|
args |
SimpleNamespace
|
Configuration for the validator. |
dataloader |
DataLoader
|
Dataloader to use for validation. |
pbar |
tqdm
|
Progress bar to update during validation. |
model |
Module
|
Model to validate. |
data |
dict
|
Data dictionary. |
device |
device
|
Device to use for validation. |
batch_i |
int
|
Current batch index. |
training |
bool
|
Whether the model is in training mode. |
names |
dict
|
Class names. |
seen |
Records the number of images seen so far during validation. |
|
stats |
Placeholder for statistics during validation. |
|
confusion_matrix |
Placeholder for a confusion matrix. |
|
nc |
Number of classes. |
|
iouv |
(torch.Tensor): IoU thresholds from 0.50 to 0.95 in spaces of 0.05. |
|
jdict |
dict
|
Dictionary to store JSON validation results. |
speed |
dict
|
Dictionary with keys 'preprocess', 'inference', 'loss', 'postprocess' and their respective batch processing times in milliseconds. |
save_dir |
Path
|
Directory to save results. |
plots |
dict
|
Dictionary to store plots for visualization. |
callbacks |
dict
|
Dictionary to store various callback functions. |
Parameters:
Name | Type | Description | Default |
---|---|---|---|
dataloader
|
DataLoader
|
Dataloader to be used for validation. |
None
|
save_dir
|
Path
|
Directory to save results. |
None
|
pbar
|
tqdm
|
Progress bar for displaying progress. |
None
|
args
|
SimpleNamespace
|
Configuration for the validator. |
None
|
_callbacks
|
dict
|
Dictionary to store various callback functions. |
None
|
Source code in ultralytics/engine/validator.py
__call__
Executes validation process, running inference on dataloader and computing performance metrics.
Source code in ultralytics/engine/validator.py
105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 |
|
add_callback
build_dataset
check_stats
eval_json
finalize_metrics
get_dataloader
Get data loader from dataset path and batch size.
get_desc
get_stats
init_metrics
match_predictions
Matches predictions to ground truth objects (pred_classes, true_classes) using IoU.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
pred_classes
|
Tensor
|
Predicted class indices of shape(N,). |
required |
true_classes
|
Tensor
|
Target class indices of shape(M,). |
required |
iou
|
Tensor
|
An NxM tensor containing the pairwise IoU values for predictions and ground of truth |
required |
use_scipy
|
bool
|
Whether to use scipy for matching (more precise). |
False
|
Returns:
Type | Description |
---|---|
Tensor
|
Correct tensor of shape(N,10) for 10 IoU thresholds. |