yahuuu

Results 13 comments of yahuuu

Adding tensorflow summary metrics support for Tensorboard

@starkcn I'm nobody, but I meet the problems of @dpsm, U could solve like this: ax3.plot(range(args.epoch_start_i, epoch+1, 1), avg_iou_per_epoch)

WinMLRunner.exe. Evaluating ..[FAILED]

Hi @ryanlai2, This is the pytorch [model](https://drive.google.com/file/d/1Nf1ZxeJZJL8Qx9KadcYYyEmmlKhTADxX/view) I'm using. This is a pre-trained model released by the [MODNet community](https://github.com/ZHKKKe/MODNet/tree/master/demo/video_matting/custom). I referenced the official [ONNX](https://github.com/onnx/tutorials/blob/master/tutorials/PytorchCaffe2SuperResolution.ipynb) conversion code, pytorch -> onnx in...

WinMLRunner.exe. Evaluating ..[FAILED]

opset_version = 12, WinMLRunner v1.2.2.zip Waiting for your answer.

Integer tflite model slow than float32 model

> Hi@ yahuuu ! > Could you please try on latest stable version of TF 2.6 and let us know if this is still an issue.Thanks! @mohantym Glad to receive...

Integer tflite model slow than float32 model

The type of filter is int8 array , I updated `converter.inference_input_type = tf.int8` to `converter.inference_input_type = tf.uint8` in script, but still got int8 array. How can I get uint8 filter...

Integer tflite model slow than float32 model

> Hi @yahuuu , I also have this int tflite slower than float tflite, and mine is much slower actually. I checked my model with Netron, and except the input...

Integer tflite model slow than float32 model

@MeghnaNatraj I try to modify the input data type to int8 when I quantize the model, but meet error : """ Cannot set tensor: Got value of type UINT8 but...

Integer tflite model slow than float32 model

@mohantym Sorry I don't think it is the reason for the version.

检测后识别

> 你的检测结果是好的吗，为什么我的检测结果很差，可以邮件交流吗？[[email protected]](mailto:[email protected]) 我的检测很好，看你的场景吧，[email protected]

请教大师， 深度学习通过数百万的数据学习到的是海量的特征还是具有兼容性的少量特征

@woshi91 我认为是后者兼容性的少量特征，您现在怎么看。