diff --git a/configs/yolov8/README.md b/configs/yolov8/README.md index b7e5f93e9daba27a4e5fe9495f387c51bd93ef0c..93b1fc7862864b974ea1f28463eaf298c7ea2eb3 100644 --- a/configs/yolov8/README.md +++ b/configs/yolov8/README.md @@ -7,7 +7,7 @@ Ultralytics YOLOv8, developed by Ultralytics, is a cutting-edge, state-of-the-art (SOTA) model that builds upon the success of previous YOLO versions and introduces new features and improvements to further boost performance and flexibility. YOLOv8 is designed to be fast, accurate, and easy to use, making it an excellent choice for a wide range of object detection, image segmentation and image classification tasks.
- + YOLOv8-P5 model structure
diff --git a/projects/easydeploy/backbone/common.py b/projects/easydeploy/backbone/common.py index d4af65a77821f620834ab30f4efbb950fb22928c..617875bd979a5b9150e476544090777118087a0b 100644 --- a/projects/easydeploy/backbone/common.py +++ b/projects/easydeploy/backbone/common.py @@ -2,6 +2,7 @@ import torch import torch.nn as nn from torch import Tensor + class DeployC2f(nn.Module): def __init__(self, *args, **kwargs): @@ -9,7 +10,7 @@ class DeployC2f(nn.Module): def forward(self, x: Tensor) -> Tensor: x_main = self.main_conv(x) - x_main = [x_main, x_main[:,self.mid_channels:,...]] + x_main = [x_main, x_main[:, self.mid_channels:, ...]] x_main.extend(blocks(x_main[-1]) for blocks in self.blocks) x_main.pop(1) return self.final_conv(torch.cat(x_main, 1))