YOLOv8 Distributed¶
" YoloV8 base detector class. Modified to support PyTorch DDP framework
YOLOV8_Distributed
¶
Bases: BaseDetector
Distributed YoloV8 detector class. This class provides utility methods for loading the model, generating results, and performing batch image detections.
Source code in PytorchWildlife/models/detection/ultralytics_based/yolov8_distributed.py
25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 |
|
__init__(weights=None, device='cpu', url=None, transform=None)
¶
Initialize the YOLOV8 detector.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
weights
|
str
|
Path to the model weights. Defaults to None. |
None
|
device
|
str
|
Device for model inference. Defaults to "cpu". |
'cpu'
|
url
|
str
|
URL to fetch the model weights. Defaults to None. |
None
|
Source code in PytorchWildlife/models/detection/ultralytics_based/yolov8_distributed.py
batch_image_detection(loader, batch_size, global_rank, local_rank, output_dir, det_conf_thres=0.2, checkpoint_frequency=1000)
¶
Perform batch image detection using the YOLOV8 model.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
loader
|
DataLoader
|
DataLoader for input images. |
required |
batch_size
|
int
|
Size of the batch for detection. |
required |
global_rank
|
int
|
Global rank of the process. |
required |
local_rank
|
int
|
Local rank of the process. |
required |
output_dir
|
str
|
Directory to save detection results. |
required |
det_conf_thres
|
float
|
Confidence threshold for detections. Defaults to 0.2. |
0.2
|
checkpoint_frequency
|
int
|
Frequency of saving intermediate results. Defaults to 1000. |
1000
|
Source code in PytorchWildlife/models/detection/ultralytics_based/yolov8_distributed.py
130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 |
|
results_generation(preds, img_id, id_strip=None)
¶
Generate results for detection based on model predictions.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
preds
|
Results
|
Model predictions. |
required |
img_id
|
str
|
Image identifier. |
required |
id_strip
|
str
|
Strip specific characters from img_id. Defaults to None. |
None
|
Returns:
Name | Type | Description |
---|---|---|
dict |
dict
|
Dictionary containing image ID, detections, and labels. |