xdobro23/YOLOv8-16bit
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ultralytics 8.0.158 add benchmarks to coverage (#4432)

Browse Source 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Yonghye Kwon <developer.0hye@gmail.com>
This commit is contained in:
Glenn Jocher
2023-08-20 20:52:30 +02:00
committed by GitHub
parent 495806565d
commit 87ce15d383
51 changed files with 352 additions and 482 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
ultralytics/engine/exporter.py
View File

@ -484,7 +484,7 @@ class Exporter:
classifier_config = ct.ClassifierConfig(list(self.model.names.values())) if self.args.nms else None
model = self.model
elif self.model.task == 'detect':
model = iOSDetectModel(self.model, self.im) if self.args.nms else self.model
model = IOSDetectModel(self.model, self.im) if self.args.nms else self.model
else:
if self.args.nms:
LOGGER.warning(f"{prefix} WARNING ⚠️ 'nms=True' is only available for Detect models like 'yolov8n.pt'.")
@ -846,12 +846,11 @@ class Exporter:
out0, out1 = iter(spec.description.output)
if MACOS:
from PIL import Image
img = Image.new('RGB', (w, h)) # img(192 width, 320 height)
# img = torch.zeros((*opt.img_size, 3)).numpy() # img size(320,192,3) iDetection
img = Image.new('RGB', (w, h)) # w=192, h=320
out = model.predict({'image': img})
out0_shape = out[out0.name].shape
out1_shape = out[out1.name].shape
else: # linux and windows can not run model.predict(), get sizes from pytorch output y
out0_shape = out[out0.name].shape # (3780, 80)
out1_shape = out[out1.name].shape # (3780, 4)
else: # linux and windows can not run model.predict(), get sizes from PyTorch model output y
out0_shape = self.output_shape[2], self.output_shape[1] - 4 # (3780, 80)
out1_shape = self.output_shape[2], 4 # (3780, 4)
@ -963,11 +962,11 @@ class Exporter:
callback(self)
class iOSDetectModel(torch.nn.Module):
"""Wrap an Ultralytics YOLO model for iOS export."""
class IOSDetectModel(torch.nn.Module):
"""Wrap an Ultralytics YOLO model for Apple iOS CoreML export."""
def __init__(self, model, im):
"""Initialize the iOSDetectModel class with a YOLO model and example image."""
"""Initialize the IOSDetectModel class with a YOLO model and example image."""
super().__init__()
b, c, h, w = im.shape # batch, channel, height, width
self.model = model
@ -981,21 +980,3 @@ class iOSDetectModel(torch.nn.Module):
"""Normalize predictions of object detection model with input size-dependent factors."""
xywh, cls = self.model(x)[0].transpose(0, 1).split((4, self.nc), 1)
return cls, xywh * self.normalize # confidence (3780, 80), coordinates (3780, 4)
def export(cfg=DEFAULT_CFG):
"""Export a YOLOv model to a specific format."""
cfg.model = cfg.model or 'yolov8n.yaml'
cfg.format = cfg.format or 'torchscript'
from ultralytics import YOLO
model = YOLO(cfg.model)
model.export(**vars(cfg))
if __name__ == '__main__':
"""
CLI:
yolo mode=export model=yolov8n.yaml format=onnx
"""
export()

6
ultralytics/engine/predictor.py
View File

@ -138,12 +138,14 @@ class BasePredictor:
return self.model(im, augment=self.args.augment, visualize=visualize)
def pre_transform(self, im):
"""Pre-transform input image before inference.
"""
Pre-transform input image before inference.
Args:
im (List(np.ndarray)): (N, 3, h, w) for tensor, [(h, w, 3) x N] for list.
Return: A list of transformed imgs.
Returns:
(list): A list of transformed images.
"""
same_shapes = all(x.shape == im[0].shape for x in im)
auto = same_shapes and self.model.pt