How to assign the model id and model version in batch_input_params.json ?
Hello,
I want to know how to assign the model id and model version in batch_input_params.json.
Is there any reference about it ?
Thanks!
Tagged:
The discussion has been closed due to inactivity. To continue with the topic, please feel free to post a new discussion.
Comments
你好,
模型相關的參數如 model_id, image resolution, model input dimension, class list等相關參數
請問我應該修改哪個文件 ?
謝謝!
Hi Albert Chung,
For the first question, if you want to modified the json file, you can refer here :
B. How to configure the
batch_input_params.json
?For the second question, I use PLUS kl720_demo_generic_inference as example. You can modify the descriptor.
As for the class list, in our YOLO example, you can refer this: http://doc.kneron.com/docs/#plus/introduction/yolo_object_name_mapping/
Thanks.
Hi Otis Hsieh,
感謝您的說明
目前使用model id 為 KNERON_YOLOV5S_640_640_3
跑 704x480 及 640x640影片的偵測框還算正常
但是跑1920x1080 影片出現偵測框往下偏移的現象
確定過_image_width 和 _image_height 和影片相同
postprocess 在dongle處理
是否是postprocess 的設定問題 , 該如何來修改這部分 ?
謝謝您!
Hi Albert Chung,
這部分是因為720在inference之前
圖片preprocess的部分會把圖片resize成跟model size相同
所以不足的部分會進行Padding,
以你的例子來說,1920X1080會等比例resize成640X360,然後padding上 640-360=280
但是padding有上限255,所以會導致最後的bounding box會有些許偏移
我們有個kl720_demo_generic_inference_crop的code,
他可以crop圖片中的特定區域,進行inference
包括你要crop區域的數量,以及他們的座標 / 長寬
看你的場景需求調整,謝謝