-
Notifications
You must be signed in to change notification settings - Fork 388
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Problem of test the model on the single image? #391
Comments
@tensor-flower crnn_syn90k_saved_model/1是给tfservering用的模型 你测试单张图 需要下载ckpt模型文件 例如中文模型在这里 https://www.dropbox.com/sh/z22xsn4byddalv3/AAAiIxAHJKbqy44M73ow5znSa?dl=0 |
font{
line-height: 1.6;
}
ul,ol{
padding-left: 20px;
list-style-position: inside;
}
您好,有英文模型权重的地址吗,readme里边的失效了
On 03/27/2020 14:42,MaybeShewill-CV<[email protected]> wrote:
@Timthony 可以参考 #390
—You are receiving this because you were mentioned.Reply to this email directly, view it on GitHub, or unsubscribe.
|
@Timthony 英文的我这几天找时间重新上传下 之前上传的好像是个错误的权重文件:) |
font{
line-height: 1.6;
}
ul,ol{
padding-left: 20px;
list-style-position: inside;
}
好的,太感谢了,这个网站的链接是要科学上网吗,还是链接有问题,都打不开我这里。
On 03/27/2020 14:46,MaybeShewill-CV<[email protected]> wrote:
@Timthony 英文的我这几天找时间重新上传下 之前上传的好像是个错误的权重文件:)
—You are receiving this because you were mentioned.Reply to this email directly, view it on GitHub, or unsubscribe.
|
@Timthony 对 dropbox可能需要科学上网:) |
font{
line-height: 1.6;
}
ul,ol{
padding-left: 20px;
list-style-position: inside;
}
好的,感谢,等您重新上传了英文的模型我再试试。
On 03/27/2020 15:24,MaybeShewill-CV<[email protected]> wrote:
@Timthony 对 dropbox可能需要科学上网:)
—You are receiving this because you were mentioned.Reply to this email directly, view it on GitHub, or unsubscribe.
|
好的,感谢,但是这个和之前的模型网址是一样的,不知道有没有上传错误。
…---Original---
From: "MaybeShewill-CV"<[email protected]>
Date: Fri, Mar 27, 2020 22:09 PM
To: "MaybeShewill-CV/CRNN_Tensorflow"<[email protected]>;
Cc: "Mention"<[email protected]>;"呆"<[email protected]>;
Subject: Re: [MaybeShewill-CV/CRNN_Tensorflow] Problem of test the model on the single image? (#391)
@Timthony 模型链接已更新 https://www.dropbox.com/sh/y4eaunamardibnd/AAB4h8NkakASDoc6Ek4knEGIa?dl=0 可以下载尝试:)
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or unsubscribe.
|
和之前一样的方式加载模型报错了。显示:ValueError: The passed save_path is not a valid checkpoint: /Users/tianhangz/Desktop/work/tianchi/chencode/CRNN_Tensorflow/model/crnn2/shadownet.ckpt
…------------------ 原始邮件 ------------------
发件人: "MaybeShewill-CV"<[email protected]>;
发送时间: 2020年3月27日(星期五) 晚上10:09
收件人: "MaybeShewill-CV/CRNN_Tensorflow"<[email protected]>;
抄送: "781068447"<[email protected]>; "Mention"<[email protected]>;
主题: Re: [MaybeShewill-CV/CRNN_Tensorflow] Problem of test the model on the single image? (#391)
@Timthony 模型链接已更新 https://www.dropbox.com/sh/y4eaunamardibnd/AAB4h8NkakASDoc6Ek4knEGIa?dl=0 可以下载尝试:)
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or unsubscribe.
|
@Timthony 1.地址一样 但是模型文件不一样么 2. 你是怎么调用的 贴个command出来吧 |
在调用tf.train.Saver#save时,如果使用的路径是绝对路径,那么保存的checkpoint里面用的就是绝对路径;如果使用的是相对路径,那么保存的checkpoint里面用的就是相对路径。正确的方法应该是使用相对路径进行保存,这样才能保证较好的可移植性。如果使用相对路径,复制到本地之后,会报找不到文件的错误。不知道是不是保存的时候的问题。
…------------------ 原始邮件 ------------------
发件人: "MaybeShewill-CV"<[email protected]>;
发送时间: 2020年3月27日(星期五) 晚上10:09
收件人: "MaybeShewill-CV/CRNN_Tensorflow"<[email protected]>;
抄送: "781068447"<[email protected]>; "Mention"<[email protected]>;
主题: Re: [MaybeShewill-CV/CRNN_Tensorflow] Problem of test the model on the single image? (#391)
@Timthony 模型链接已更新 https://www.dropbox.com/sh/y4eaunamardibnd/AAB4h8NkakASDoc6Ek4knEGIa?dl=0 可以下载尝试:)
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or unsubscribe.
|
python tools/test_shadownet.py --image_path data/test_images/test_01.jpg --weights_path model/crnn_synth90k2/shadownet.ckpt --char_dict_path data/char_dict/char_dict_en.json --ord_map_dict_path data/char_dict/ord_map_en.json python tools/test_shadownet.py --image_path data/test_images/test_01.jpg --weights_path model/crnn_synth90k2/shadownet.ckpt-80000 --char_dict_path data/char_dict/char_dict_en.json --ord_map_dict_path data/char_dict/ord_map_en.json 换成第二个时候可以了,经过测试现在输出也是准确的了,感谢! |
这个英文的模型对数字也具有识别能力吗? |
@Timthony 1.是因为我上传的模型文件换了名字 没有同步更新readme 明天更新下 2.对数字有一定识别能力 但是主要要看你的应用场景和这个训练数据中的数据的domain gap是不是过大:) |
@Timthony 你可以看下synth90k的数据集 就知道什么问题了:) |
看了下网站上synth90k的例子应该全是英文字符的,去不了学校没资源训练新模型--。 |
@Timthony 有部分数字 但是比较少:) |
@Timthony 你可以试试中文模型 中文模型中的数字貌似还能多一点:) |
中文模型对英文有没有识别能力,我的主要是数字和英文。
…---Original---
From: "MaybeShewill-CV"<[email protected]>
Date: Sat, Mar 28, 2020 21:06 PM
To: "MaybeShewill-CV/CRNN_Tensorflow"<[email protected]>;
Cc: "Mention"<[email protected]>;"呆"<[email protected]>;
Subject: Re: [MaybeShewill-CV/CRNN_Tensorflow] Problem of test the model on the single image? (#391)
@Timthony 你可以试试中文模型 中文模型中的数字貌似还能多一点:)
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or unsubscribe.
|
@Timthony 那你可以尝试synthtext生成一部分训练数据 试试看:) |
好的,太感谢了,都试试,没gpu自己训练太麻烦T_T
…---Original---
From: "MaybeShewill-CV"<[email protected]>
Date: Sat, Mar 28, 2020 21:15 PM
To: "MaybeShewill-CV/CRNN_Tensorflow"<[email protected]>;
Cc: "Mention"<[email protected]>;"呆"<[email protected]>;
Subject: Re: [MaybeShewill-CV/CRNN_Tensorflow] Problem of test the model on the single image? (#391)
@Timthony 那你可以尝试synthtext生成一部分训练数据 试试看:)
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or unsubscribe.
|
@Timthony 好的 没有别的问题我就close了:) |
好的,-^_^- |
您好,我把中文权重下载下来后,没有shadownet.ckpt 文件,只有checkpoint,shadownet.ckpt-322000.data-00000-of-00001,shadownet.ckpt-322000.index,shadownet.ckpt-322000.meta四个文件,这怎么解决呢 |
shadownet.ckpt consists of hadownet.ckpt-322000.data-00000-of-00001,shadownet.ckpt-322000.index,shadownet.ckpt-322000.meta |
If you want to test a single image you can do it with
python tools/test_shadownet.py --image_path PATH/TO/IMAGE
--weights_path PATH/TO/MODEL_WEIGHTS
--char_dict_path PATH/TO/CHAR_DICT_PATH
--ord_map_dict_path PATH/TO/ORD_MAP_PATH
"--weights_path PATH/TO/MODEL_WEIGHTS"
Whether the selection of weights can be used directly use "model/crnn_syn90k_saved_model/1"?
If can, I encountered some errors.
The text was updated successfully, but these errors were encountered: