Amish Garg

Results 12 comments of Amish Garg

Hi, TensorFlow Lite Flutter Plugin [am15h/tflite_flutter_plugin](https://github.com/am15h/tflite_flutter_plugin/) has been published under the guidance of TensorFlow Lite Team. It is similar to the TFLite Java API and also includes all the mobile-specific...

Thanks for the analysis @FelixBruebach. NormalizeOp is an expensive operation. I don't think it can be optimized any further, therefore if you can use a quantized model rather than float,...

Thanks @FelixBruebach. Glad that you are able to achieve better results. I will need to investigate the differences and check if this procedure can be made compatible with the current...

If you are asking for a wrapper to directly pass CameraImage as a parameter, instead of using these https://github.com/am15h/object_detection_flutter/blob/master/lib/utils/image_utils.dart, probably we can add that support. However, the conversion is required...

I am truly sorry for the late reply. Hello @maylad31, BGR input is not supported by TensorImage. You can manually convert to BGR image and load that to TensorBuffer ```...

@matheper, @maylad31 You can get [image ](https://pub.dev/packages/image)from tensorbuffer that has **BGR** data using the following code, ``` static Image convertTensorBufferToImage(TensorBuffer buffer, Image image) { if (buffer.getDataType() != TfLiteType.uint8) { throw...

Temporarily duplicate this function https://github.com/am15h/tflite_flutter_helper/blob/master/lib/src/image/image_conversions.dart#L10-L46 (Only for your particular use case right now) you can remove the ``` if (buffer.getDataType() != TfLiteType.uint8) { throw UnsupportedError( "Converting TensorBuffer of type ${buffer.getDataType()}...

Glad to hear that your problem got resolved. Please open a pull request if you want to contribute. That would be very helpful

@bazinac We will need more flexibility here, along with your changes. Thanks a lot for your contribution. I will make changes on top of these and merge them.

Hi @prakashssp077, Can you please share some reproducible code.