nn Module
Ultralytics nn module contains 3 main components:
- AutoBackend: A module that can run inference on all popular model formats
- BaseModel:
BaseModel
class defines the operations supported by tasks like Detection and Segmentation - modules: Optimized and reusable neural network blocks built on PyTorch.
AutoBackend
Bases: nn.Module
Source code in ultralytics/nn/autobackend.py
21 22 23 24 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 |
|
__init__(weights='yolov8n.pt', device=torch.device('cpu'), dnn=False, data=None, fp16=False, fuse=True)
Ultralytics YOLO MultiBackend class for python inference on various backends
Parameters:
Name | Type | Description | Default |
---|---|---|---|
weights |
the path to the weights file. Defaults to yolov8n.pt |
'yolov8n.pt'
|
|
device |
The device to run the model on. |
torch.device('cpu')
|
|
dnn |
If you want to use OpenCV's DNN module to run the inference, set this to True. Defaults to |
False
|
False data: a dictionary containing the following keys: fp16: If true, will use half precision. Defaults to False fuse: whether to fuse the model or not. Defaults to True
Supported format and their usage
Platform | weights |
---|---|
PyTorch | *.pt |
TorchScript | *.torchscript |
ONNX Runtime | *.onnx |
ONNX OpenCV DNN | *.onnx --dnn |
OpenVINO | *.xml |
CoreML | *.mlmodel |
TensorRT | *.engine |
TensorFlow SavedModel | *_saved_model |
TensorFlow GraphDef | *.pb |
TensorFlow Lite | *.tflite |
TensorFlow Edge TPU | *_edgetpu.tflite |
PaddlePaddle | *_paddle_model |
Source code in ultralytics/nn/autobackend.py
23 24 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 |
|
forward(im, augment=False, visualize=False)
Runs inference on the given model
Parameters:
Name | Type | Description | Default |
---|---|---|---|
im |
the image tensor |
required | |
augment |
whether to augment the image. Defaults to False |
False
|
|
visualize |
if True, then the network will output the feature maps of the last convolutional layer. |
False
|
Defaults to False
Source code in ultralytics/nn/autobackend.py
234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 |
|
from_numpy(x)
from_numpy
converts a numpy array to a tensor
Parameters:
Name | Type | Description | Default |
---|---|---|---|
x |
the numpy array to convert |
required |
warmup(imgsz=(1, 3, 640, 640))
Warmup model by running inference once
Parameters:
Name | Type | Description | Default |
---|---|---|---|
imgsz |
the size of the image you want to run inference on. |
(1, 3, 640, 640)
|
Source code in ultralytics/nn/autobackend.py
BaseModel
Bases: nn.Module
The BaseModel class is a base class for all the models in the Ultralytics YOLO family.
Source code in ultralytics/nn/tasks.py
19 20 21 22 23 24 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 |
|
forward(x, profile=False, visualize=False)
forward
is a wrapper for_forward_once
that runs the model on a single scale
Parameters:
Name | Type | Description | Default |
---|---|---|---|
x |
the input image |
required | |
profile |
whether to profile the model. Defaults to False |
False
|
|
visualize |
if True, will return the intermediate feature maps. Defaults to False |
False
|
Returns:
Type | Description |
---|---|
The output of the network. |
Source code in ultralytics/nn/tasks.py
fuse()
It takes a model and fuses the Conv2d() and BatchNorm2d() layers into a single layer
Returns:
Type | Description |
---|---|
The model is being returned. |
Source code in ultralytics/nn/tasks.py
info(verbose=False, imgsz=640)
Prints model information
Parameters:
Name | Type | Description | Default |
---|---|---|---|
verbose |
if True, prints out the model information. Defaults to False |
False
|
|
imgsz |
the size of the image that the model will be trained on. Defaults to 640 |
640
|
Source code in ultralytics/nn/tasks.py
load(weights)
This function loads the weights of the model from a file
Parameters:
Name | Type | Description | Default |
---|---|---|---|
weights |
The weights to load into the model. |
required |
Source code in ultralytics/nn/tasks.py
Modules
TODO