run the evaluate.py

[LiouCZ]

problem: tensorflow.python.framework.errors_impl.InvalidArgumentError: Can not squeeze dim[3], expected a dimension of 1, got 3

the label image`s result is diffrent from tf.image and PIL

[Xchangjiang]

Have you solved the problem? I had the same problem

[BillGreenHand]

@LiouCZ Have you solved the problem? I had the same problem

[LiouCZ]

maybe You should add the channel number parameter in the decode_image method of your proccessing.py code

------------------ 原始邮件 ------------------ 发件人: "BillGreenHand"[email protected]; 发送时间: 2019年7月30日(星期二) 下午4:29 收件人: "rishizek/tensorflow-deeplab-v3-plus"[email protected]; 抄送: "刘宸哲"[email protected]; "Mention"[email protected]; 主题: Re: [rishizek/tensorflow-deeplab-v3-plus] run the evaluate.py (#53)

@LiouCZ Have you solved the problem? I had the same problem

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

[BillGreenHand]

@LiouCZ Thank you for your reply. What about is the result of your training?

[LiouCZ]

not good

------------------ 原始邮件 ------------------ 发件人: "BillGreenHand"[email protected]; 发送时间: 2019年8月5日(星期一) 上午8:34 收件人: "rishizek/tensorflow-deeplab-v3-"[email protected]; 抄送: "刘宸哲"[email protected]; "Mention"[email protected]; 主题: Re: [rishizek/tensorflow-deeplab-v3-plus] run the evaluate.py (#53)

@LiouCZ Thank you for your reply. What about is the result of your training?

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