[FEATURE]: 图片搜索服务qps很低

[yylstudy]

Is there an existing issue for this?

• I have searched the existing issues

Is your feature request related to a problem? Please describe.

towhee：0.9.0
milvus：2.0.0
img-search-server：towhee
以官方例子搭建图片搜索服务，发现qps只有1左右
https://github.com/milvus-io/bootcamp/tree/master/solutions/image/reverse_image_search/quick_deploy
查看了img-search-server服务的源码，去除了相关的async的代码，相关代码如下

最终发现，resnet50_extract_feat方法是单线程的，这个有什么办法能提升图片转向量的性能呢，希望得到回答，非常谢谢！

Describe the solution you'd like

No response

Describe alternatives you've considered

No response

Anything else?

No response

[shiyu22]

Hi @yylstudy, you can try to update the Resnet50 in encode.py with the following code:

Note that you need to install towhee with pip install towhee==1.0.0rc1. And will release 1.0.0 later.

from towhee import pipe, ops


class Resnet50:
    def __init__(self):
        self.image_embedding_pipe = (
            pipe.input('path')
                .map('path', 'img', ops.image_decode.cv2_rgb())
                .map('img', 'embedding', ops.image_embedding.timm(model_name='resnet50'))
                .map('embedding', 'embedding', ops.towhee.np_normalize())
                .output('embedding')
            )

    def resnet50_extract_feat(self, img_path):
        feat = self.image_embedding_pipe(img_path)
        return feat.get()[0]

The new towhee code will just load the pipeline just one time.

[yylstudy]

@shiyu22 你好，麻烦再请问下，性能现在是没问题了，但是用上面代码测试后发现distance会变得非常大，之前都是
0.1~1.x之间，这个是为什么呢，谢谢

[yylstudy]

现在milvus版本为v2.0.2，distance的值大小是否与milvus版本有关系

[shiyu22]

现在milvus版本为v2.0.2，distance的值大小是否与milvus版本有关系

No, it's because there is no normalization of the vector. I will add np_normalize() for it.

[shiyu22]

Hi @yylstudy, you can try to update the Resnet50 in encode.py with the following code:

Note that you need to install towhee with pip install towhee==1.0.0rc1. And will release 1.0.0 later.

from towhee import pipe, ops


class Resnet50:
    def __init__(self):
        self.image_embedding_pipe = (
            pipe.input('path')
                .map('path', 'img', ops.image_decode.cv2_rgb())
                .map('img', 'embedding', ops.image_embedding.timm(model_name='resnet50'))
                .map('embedding', 'embedding', ops.towhee.np_normalize())
                .output('embedding')
            )

    def resnet50_extract_feat(self, img_path):
        feat = self.image_embedding_pipe(img_path)
        return feat.get()[0]

The new towhee code will just load the pipeline just one time.

@yylstudy can you try it again?

And if it fixed your issue, can you submit a PR to modify the encode.py and be our contributor?

[yylstudy]

@shiyu22 非常感谢，解决了我的问题，去除async后，现在qps从原先的1到达30+了，基于此issue我提交了一个pr，不好意思我之前还未提交过pr，麻烦你看下是否符合规范，再次感谢您！

[shiyu22]

It's my pleasure:) And thanks for your contribution.

[Theodore Teach]

你这个图搜图的效果怎么样？我在用这个的时候发现把已经导入进去的图截取一部分进行搜索，搜不出来之前完整的图片。

[codingjaguar]

cropping image may cause significant change of the semantic. so it's not surprising to not return the original full picture.