用deeplabv3训练效果太差

[jiaxinshiwo]

请问一下有没有用自己数据集训练的，分割结果好差，有没有什么改进的方法

[andrew-begain]

@jiaxinshiwo 麻烦请教一下训练的代码有跑通吗？RuntimeError: Failed downloading url https://hangzh.s3.amazonaws.com/encoding/models/resnet50-25c4b509.zip这个resnet预训练模型您是怎么下载的啊？谢谢

[jiaxinshiwo]

就是因为预加载的下不下来，所以效果不是特别好发自我的华为手机-------- 原始邮件 --------发件人： andrew-begain [email protected]日期： 2020年5月25日周一 08:58收件人： Tramac/awesome-semantic-segmentation-pytorch [email protected]抄送： jiaxin wang [email protected], Mention [email protected]主 题： Re: [Tramac/awesome-semantic-segmentation-pytorch] 用deeplabv3训练效果太差 (#129)

@jiaxinshiwo 麻烦请教一下训练的代码有跑通吗？RuntimeError: Failed downloading url https://hangzh.s3.amazonaws.com/encoding/models/resnet50-25c4b509.zip这个resnet预训练模型您是怎么下载的啊？谢谢

—You are receiving this because you were mentioned.Reply to this email directly, view it on GitHub, or unsubscribe.

[andrew-begain]

就是因为预加载的下不下来，所以效果不是特别好发自我的华为手机-------- 原始邮件 --------发件人： andrew-begain [email protected]日期： 2020年5月25日周一 08:58收件人： Tramac/awesome-semantic-segmentation-pytorch [email protected]抄送： jiaxin wang [email protected], Mention [email protected]主 题： Re: [Tramac/awesome-semantic-segmentation-pytorch] 用deeplabv3训练效果太差 (#129) @jiaxinshiwo 麻烦请教一下训练的代码有跑通吗？RuntimeError: Failed downloading url https://hangzh.s3.amazonaws.com/encoding/models/resnet50-25c4b509.zip这个resnet预训练模型您是怎么下载的啊？谢谢 —You are receiving this because you were mentioned.Reply to this email directly, view it on GitHub, or unsubscribe.

哦哦，好的，谢谢回复

[molalasue]

你好，我用deeplab v3+ 训练出现了下面的错误： File "train.py", line 326, in trainer = Trainer(args) File "train.py", line 162, in init aux=args.aux, norm_layer=BatchNorm2d).to(self.device) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/model_zoo.py", line 122, in get_segmentation_model return modelsmodel File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/deeplabv3_plus.py", line 127, in get_deeplabv3_plus model = DeepLabV3Plus(datasets[dataset].NUM_CLASS, backbone=backbone, pretrained_base=pretrained_base, **kwargs) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/deeplabv3_plus.py", line 38, in init self.pretrained = get_xception(pretrained=pretrained_base, output_stride=output_stride, **kwargs) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/base_models/xception.py", line 390, in get_xception model.load_state_dict(torch.load(get_model_file('xception', root=root))) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/model_store.py", line 68, in get_model_file raise ValueError('Model file is not found. Downloading or trainning.') ValueError: Model file is not found. Downloading or trainning.

请问你有出现这样的错误吗，是怎么解决的呀？

[lurending711]

你好，我用deeplab v3+ 训练出现了下面的错误： File "train.py", line 326, in trainer = Trainer(args) File "train.py", line 162, in init aux=args.aux, norm_layer=BatchNorm2d).to(self.device) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/model_zoo.py", line 122, in get_segmentation_model return modelsmodel File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/deeplabv3_plus.py", line 127, in get_deeplabv3_plus model = DeepLabV3Plus(datasets[dataset].NUM_CLASS, backbone=backbone, pretrained_base=pretrained_base, **kwargs) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/deeplabv3_plus.py", line 38, in init self.pretrained = get_xception(pretrained=pretrained_base, output_stride=output_stride, **kwargs) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/base_models/xception.py", line 390, in get_xception model.load_state_dict(torch.load(get_model_file('xception', root=root))) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/model_store.py", line 68, in get_model_file raise ValueError('Model file is not found. Downloading or trainning.') ValueError: Model file is not found. Downloading or trainning.

请问你有出现这样的错误吗，是怎么解决

你好，我也出现相同的问题，请问拟解决了吗？

[jiaxinshiwo]

你好，我用deeplab v3+ 训练出现了下面的错误： File "train.py", line 326, in trainer = Trainer(args) File "train.py", line 162, in init aux=args.aux, norm_layer=BatchNorm2d).to(self.device) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/model_zoo.py", line 122, in get_segmentation_model return modelsmodel File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/deeplabv3_plus.py", line 127, in get_deeplabv3_plus model = DeepLabV3Plus(datasets[dataset].NUM_CLASS, backbone=backbone, pretrained_base=pretrained_base, **kwargs) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/deeplabv3_plus.py", line 38, in init self.pretrained = get_xception(pretrained=pretrained_base, output_stride=output_stride, **kwargs) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/base_models/xception.py", line 390, in get_xception model.load_state_dict(torch.load(get_model_file('xception', root=root))) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/model_store.py", line 68, in get_model_file raise ValueError('Model file is not found. Downloading or trainning.') ValueError: Model file is not found. Downloading or trainning. 请问你有出现这样的错误吗，是怎么解决

你好，我也出现相同的问题，请问拟解决了吗？

我之后没弄了呀

[lurending711]

好的，谢谢啊 

------------------ 原始邮件 ------------------ 发件人: "Tramac/awesome-semantic-segmentation-pytorch" @.>; 发送时间: 2021年4月22日(星期四) 晚上8:41 @.>; @.@.>; 主题: Re: [Tramac/awesome-semantic-segmentation-pytorch] 用deeplabv3训练效果太差 (#129)

你好，我用deeplab v3+ 训练出现了下面的错误： File "train.py", line 326, in trainer = Trainer(args) File "train.py", line 162, in init aux=args.aux, norm_layer=BatchNorm2d).to(self.device) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/model_zoo.py", line 122, in get_segmentation_model return modelsmodel File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/deeplabv3_plus.py", line 127, in get_deeplabv3_plus model = DeepLabV3Plus(datasets[dataset].NUM_CLASS, backbone=backbone, pretrained_base=pretrained_base, **kwargs) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/deeplabv3_plus.py", line 38, in init self.pretrained = get_xception(pretrained=pretrained_base, output_stride=output_stride, **kwargs) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/base_models/xception.py", line 390, in get_xception model.load_state_dict(torch.load(get_model_file('xception', root=root))) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/model_store.py", line 68, in get_model_file raise ValueError('Model file is not found. Downloading or trainning.') ValueError: Model file is not found. Downloading or trainning. 请问你有出现这样的错误吗，是怎么解决

你好，我也出现相同的问题，请问拟解决了吗？

我之后没弄了呀

— You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.

[Tramac]

好的，谢谢啊  … ------------------ 原始邮件 ------------------ 发件人: "Tramac/awesome-semantic-segmentation-pytorch" @.>; 发送时间: 2021年4月22日(星期四) 晚上8:41 @.>; @.@.>; 主题: Re: [Tramac/awesome-semantic-segmentation-pytorch] 用deeplabv3训练效果太差 (#129) 你好，我用deeplab v3+ 训练出现了下面的错误： File "train.py", line 326, in trainer = Trainer(args) File "train.py", line 162, in init aux=args.aux, norm_layer=BatchNorm2d).to(self.device) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/model_zoo.py", line 122, in get_segmentation_model return modelsmodel File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/deeplabv3_plus.py", line 127, in get_deeplabv3_plus model = DeepLabV3Plus(datasets[dataset].NUM_CLASS, backbone=backbone, pretrained_base=pretrained_base, **kwargs) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/deeplabv3_plus.py", line 38, in init self.pretrained = get_xception(pretrained=pretrained_base, output_stride=output_stride, **kwargs) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/base_models/xception.py", line 390, in get_xception model.load_state_dict(torch.load(get_model_file('xception', root=root))) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/model_store.py", line 68, in get_model_file raise ValueError('Model file is not found. Downloading or trainning.') ValueError: Model file is not found. Downloading or trainning. 请问你有出现这样的错误吗，是怎么解决 你好，我也出现相同的问题，请问拟解决了吗？ 我之后没弄了呀 — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.

可以检查一下预训练模型是否下载成功以及加载路径是否匹配

[dreamlychina]

好的，谢谢啊  … ------------------ 原始邮件 ------------------ 发件人: "Tramac/awesome-semantic-segmentation-pytorch" @.>; 发送时间: 2021年4月22日(星期四) 晚上8:41 _@**._>; _@.@.**_>; 主题: Re: [Tramac/awesome-semantic-segmentation-pytorch] 用deeplabv3训练效果太差 (#129) 你好，我用deeplab v3+ 训练出现了下面的错误： File "train.py", line 326, in trainer = Trainer(args) File "train.py", line 162, in init aux=args.aux, norm_layer=BatchNorm2d).to(self.device) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/model_zoo.py", line 122, in get_segmentation_model return modelsmodel File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/deeplabv3_plus.py", line 127, in get_deeplabv3_plus model = DeepLabV3Plus(datasets[dataset].NUM_CLASS, backbone=backbone, pretrained_base=pretrained_base, **kwargs) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/deeplabv3_plus.py", line 38, in init self.pretrained = get_xception(pretrained=pretrained_base, output_stride=output_stride, **kwargs) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/base_models/xception.py", line 390, in get_xception model.load_state_dict(torch.load(get_model_file('xception', root=root))) File "/home/xst/awesome-semantic-segmentation-pytorch-master/core/models/model_store.py", line 68, in get_model_file raise ValueError('Model file is not found. Downloading or trainning.') ValueError: Model file is not found. Downloading or trainning. 请问你有出现这样的错误吗，是怎么解决 你好，我也出现相同的问题，请问拟解决了吗？ 我之后没弄了呀 — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.

可以检查一下预训练模型是否下载成功以及加载路径是否匹配

预训练模型在哪里找？？

[violetifgarden]

那个训练权重https://hangzh.s3.amazonaws.com/encoding/models/resnet152-0d43d698.zip用迅雷下，添加到云盘