High-Resolution-Remote-Sensing-Semantic-Segmentation-PyTorch

High-Resolution-Remote-Sensing-Semantic-Segmentation-PyTorch copied to clipboard

RuntimeError: CUDA error

9

RuntimeError: CUDA error: device-side assert triggered CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. 代码中错误定位在trainer.training(epoch)和writer.add_scalar('train_loss',...

Jzli03

error: no module name gid_classes

4

# from class_names import gid_classes In the **dataset.py** file, the line **4**: > ```python >from class_names import gid_classes >``` But the file **class_names.py** just have the **def fifteen_classes** and **def...

AirHighway

很多文件png、jpg、pth缺少，很难训练

lkp520

Mixup()

1

self.mixup_transform = sync_transforms.Mixup() sync_transforms.py中没有Mixup()这个函数啊

ChineseHuang

Mixup

1

HI，there is no mixup!

Hanson0910

报错 self.train_dataset = RSDataset(class_name, root=args.train_data_root, mode='train', sync_transforms=sync_transform) TypeError: __init__() got multiple values for argument 'root'

2

请问这个情况是为什么？

taochx

训练了一步后会出现gpu现存不足?

3

原始图片大小：2448*2448 切片大小：512*512 batch-size:16 GPU为3090，显存：24G

yuxin7

加载断点path

5

resnet.load_state_dict((torch.load("/root/data/others/yaoganbisai/code_6_7/models/pretrained_model/resnet50-19c8e357.pth"))) if args.model == 'deeplabv3_version_1'中，设置了path之后，会报错。错误在上面。这个resnet里面的pth是怎么生成的。

MLS2021

请问怎么获得您在github上贴的那种预测图？有代码参考嘛，我在test.py文件中获得的预测图结果不对

hhzxy

self.mixup_transform = sync_transforms.Mixup()请问这个问题，是需要将Mixup()直接去掉嘛

thesusu