search

knazeri / edge-connect

EdgeConnect: Structure Guided Image Inpainting using Edge Prediction, ICCV 2019 https://arxiv.org/abs/1901.00212
http://openaccess.thecvf.com/content_ICCVW_2019/html/AIM/Nazeri_EdgeConnect_Structure_Guided_Image_Inpainting_using_Edge_Prediction_ICCVW_2019_paper.html
Other
2.5k stars 530 forks source link

我没跑这个代码，只是使用了它训练好的CelebA模型产生些修复数据 #133

Open zhengbowei opened 4 years ago

zhengbowei commented 4 years ago

你好，我最近也在跑这个代码。可以加你交流一下吗？我的微信：loveanshen 我的QQ：519838354 我的邮箱：519838354@qq.com 非常期待你百忙中的回复

Originally posted by @anshen666 in https://github.com/knazeri/edge-connect/issues/116#issuecomment-563930148

anshen666 commented 4 years ago

你好，我可以和你交流一下吗？？？？我也就想用那个模型，可以加你微信或者QQ吗？

------------------ 原始邮件 ------------------ 发件人: "zhengbowei"<notifications@github.com>; 发送时间: 2019年12月11日(星期三) 下午4:23 收件人: "knazeri/edge-connect"<edge-connect@noreply.github.com>; 抄送: "迷迭香"<519838354@qq.com>;"Mention"<mention@noreply.github.com>; 主题: [knazeri/edge-connect] 我没跑这个代码，只是使用了它训练好的CelebA模型产生些修复数据 (#133)

你好，我最近也在跑这个代码。可以加你交流一下吗？我的微信：loveanshen 我的QQ：519838354 我的邮箱：519838354@qq.com 非常期待你百忙中的回复

Originally posted by @anshen666 in #116 (comment)

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

OYWALT commented 2 years ago

您好，我在使用预训练模型是出现了一个error，不知道诸位在使用模型时是否遇到 D:\GRADUATE\DCGAN\edge-connect-master>python test.py --checkpoints ./pretrainedModel/places2 --input ./examples/places2/images --mask ./examples/places2/masks --output ./results/places2 D:\GRADUATE\DCGAN\edge-connect-master\src\config.py:8: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details. self._dict = yaml.load(self._yaml) C:\Users\16272\AppData\Roaming\Python\Python38\site-packages\torchvision\models_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead. warnings.warn( C:\Users\16272\AppData\Roaming\Python\Python38\site-packages\torchvision\models_utils.py:223: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing weights=VGG19_Weights.IMAGENET1K_V1. You can also use weights=VGG19_Weights.DEFAULT to get the most up-to-date weights. warnings.warn(msg)

start testing...

loading error: ./examples/places2/images\places2_01.png Traceback (most recent call last): File "D:\GRADUATE\DCGAN\edge-connect-master\src\dataset.py", line 42, in getitem item = self.load_item(index) File "D:\GRADUATE\DCGAN\edge-connect-master\src\dataset.py", line 72, in load_item mask = self.load_mask(img, index) File "D:\GRADUATE\DCGAN\edge-connect-master\src\dataset.py", line 150, in load_mask return func(*args, kwargs) File "C:\Users\16272\AppData\Roaming\Python\Python38\site-packages\skimage\color\colorconv.py", line 875, in rgb2gray rgb = _prepare_colorarray(rgb) File "C:\Users\16272\AppData\Roaming\Python\Python38\site-packages\skimage\color\colorconv.py", line 140, in _prepare_colorarray raise ValueError(msg) ValueError: the input array must have size 3 along channel_axis, got (256, 256)** 如果有遇到并解决的，希望能得到您的指点，麻烦您了！

CindyzhangKexin commented 1 year ago

您好，我在使用预训练模型是出现了一个error，不知道诸位在使用模型时是否遇到 D:\GRADUATE\DCGAN\edge-connect-master>python test.py --checkpoints ./pretrainedModel/places2 --input ./examples/places2/images --mask ./examples/places2/masks --output ./results/places2 D:\GRADUATE\DCGAN\edge-connect-master\src\config.py:8: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details. self._dict = yaml.load(self._yaml) C:\Users\16272\AppData\Roaming\Python\Python38\site-packages\torchvision\models_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead. warnings.warn( C:\Users\16272\AppData\Roaming\Python\Python38\site-packages\torchvision\models_utils.py:223: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing weights=VGG19_Weights.IMAGENET1K_V1. You can also use weights=VGG19_Weights.DEFAULT to get the most up-to-date weights. warnings.warn(msg)

start testing...

loading error: ./examples/places2/images\places2_01.png Traceback (most recent call last): File "D:\GRADUATE\DCGAN\edge-connect-master\src\dataset.py", line 42, in getitem item = self.load_item(index) File "D:\GRADUATE\DCGAN\edge-connect-master\src\dataset.py", line 72, in load_item mask = self.load_mask(img, index) File "D:\GRADUATE\DCGAN\edge-connect-master\src\dataset.py", line 150, in load_mask return func(*args, kwargs) File "C:\Users\16272\AppData\Roaming\Python\Python38\site-packages\skimage\color\colorconv.py", line 875, in rgb2gray rgb = _prepare_colorarray(rgb) File "C:\Users\16272\AppData\Roaming\Python\Python38\site-packages\skimage\color\colorconv.py", line 140, in _prepare_colorarray raise ValueError(msg) ValueError: the input array must have size 3 along channel_axis, got (256, 256)** 如果有遇到并解决的，希望能得到您的指点，麻烦您了！

请问这个问题你解决了吗？