Prateek Gupta

@zlelik try to convert your onnx model to tflite by following this- [https://pypi.org/project/onnx2tf/](url)

I have also faced the same error in Colab for training with W6 weight file-  But changing the above-mentioned could not solve the error.

@Feanor1021 Yes, follow this PR for conversion- [https://github.com/WongKinYiu/yolov7/pull/1968](url)

By following the PR, I was able to convert my yolov7-tiny based custom model in the tflite formats. The given PR, gives the output file in int8, int16, float16, float32...

@apcarita have you tried this PR for tflite conversion: [https://github.com/roboflow/rf-detr/pull/45](url)

> seems to work for me, will test on device and update. thanks ! how is the performance of the tflite model in mobile device?

yolov7_training.pt, yolov7x_training.pt are trained on 640x640. Rest are 1280x1280.

@Makuu6 it must be around 11.9 MB. Reparameterization will not reduce its size so much. You can convert it to its int8 TFLite format, which will have a size of...

@pkgoogle I think the broken installation issue is still there in platforms like colab and kaggle. Since it has been many months, any timeline when it will be fixed?