deep-learning-for-image-processing

deep-learning-for-image-processing copied to clipboard

Roadmap - 2022 (规划中)

40

图像分类： - [x] RepVGG - [x] ConvNeXt 目标检测： - [x] 补上YOLOv4网络讲解 - [x] 补上YOLOv5网络讲解（没有论文） - [x] 补上YOLOX网络讲解 - [x] 补上Faster RCNN换backbone视频 - [x] FCOS 模型讲解 语义分割： - [x] DeepLab V3...

WZMIAOMIAO

# 训练的结果：  # 权重文件：  # 运行预测文件报错： 

heart6622

分布式初始化问题

1

采用您的代码，在初始化的时候，设置2块GPU可见，没问题。当我设置4块时，就会卡在 dist.barrier()。 这是什么问题?

MrLeizy

Test results: https://github.com/cclauss/deep-learning-for-image-processing/actions

cclauss

Traceback (most recent call last): File "train.py", line 124, in main(opt) File "train.py", line 87, in main train_loss, train_acc = train_one_epoch(model=model, File "F:\ImageClassification\EmotionClassification\utils.py", line 142, in train_one_epoch accu_num += torch.eq(pred_classes,...

XuJ1E

可以讲解下一个通用的目标检测grad-cam

2

swjtulinxi

怎么才能按train.txt里的顺序训练

1

我看现在好像是随机的

wch243294382

训练自己数据集检测时出现画图颜色的错误

1

Traceback (most recent call last): File "D:\software\Python\project\faster_rcnn\predict-dianchi.py", line 152, in main() File "D:\software\Python\project\faster_rcnn\predict-dianchi.py", line 103, in main plot_img = draw_objs(original_img, File "D:\software\Python\project\faster_rcnn\draw_box_utils.py", line 146, in draw_objs draw.line([(left, top), (left, bottom),...

DeaLong

使用swin-transformer里的predict.py和官方swin_tiny_patch4_window7_224.pth模型预测没结果；

2

**System information** * Have I written custom code: * OS Platform(e.g., window10 or Linux Ubuntu 16.04): * Python version: * Deep learning framework and version(e.g., Tensorflow2.1 or Pytorch1.3): * Use...

LegendSun0

在torch >= 2.0中移除了名为“torch._six”的模块 coco_eval.py文件可能需要一些修改

2

**System information** * Have I written custom code:Yes * OS Platform(e.g., window10 or Linux Ubuntu 16.04):window10 * Python version:3.7 * Deep learning framework and version(e.g., Tensorflow2.1 or Pytorch1.3):Pytorch2.1.0+cu121(Colab) * Use...

leocn3