Bedapudi Praneeth comments

Results 81 comments of


                                            Bedapudi Praneeth

Cannot run example code.

At the moment, these tensorflow versions are not supported. I will update the README with the exact versions of tensorflow and keras with which this library works.

Docker container Error

Hi, been super busy with other things, so very delayed reply. It is fixed now and also newer model is pushed

Error: no available backend found. ERR: [wasm] RangeError: Out of memory, [cpu] Error: previous call to 'initWasm()' failed., [webnn] Error: previous call to 'initWasm()' failed.

Can't help much here. Onnx support is limited may be. You can try using tfjs, but will need to manually export the pytorch model and use something like https://github.com/Hyuto/yolov8-tfjs

Detection of the larger model is worse

@Sascha353 hi, still in the process of testing the models and also adding some more models. I will be able to give full clarity after few days

Convert to Pytorch and how to load the pytorch models, i.e.,"320n.pt"

you can load them using ultralytics repo

Model Unsupported model IR version: 10, max supported IR version: 9

you can upgrade your onnxruntime or export with a older onnx version

Docker curl multipart/form-data not possible with every Language

> Is there any way to just use the normal file post command instead of multi file post? I is not possible for some languages to use the multi part...

Docker curl multipart/form-data not possible with every Language

@ItsDedSec00 you can write a http server in the middle of fastdeploy docker and appinventor which accepts the base64 and does multiform internally.

Docker curl multipart/form-data not possible with every Language

base64 is not supported at the moment.

Error Image Classification on Files with Cyrillic Characters in Filepath

you can simply rename the files temporarily or pass file object /np