Ren-Yi Huang

Unsupported operations when applying tfmot

1

Hi, I'm trying to apply tfmot for [an implementation of BiSeNetV2](https://github.com/VXallset/BiSeNet_V2.Tensorflow), when executing `tfmot.quantization.keras.quantize_model`, I meet errors with the following operations: tf.reduce_mean: Layer tf.math.reduce_mean: is not supported. You can quantize...

[conversion issue] Convert tiny-yolov3 from darknet format to Caffe format

3

Hi, I'm trying to convert a tiny-yolov3 model from .weight to .Caffemodel, and the models are from the author's website: [https://pjreddie.com/darknet/yolo/](url) I followed the tutorial in [https://github.com/eric612/MobileNet-YOLO/tree/master/models/darknet_yolov3](url), and darknet53 YOLOv3...

Hi, Currently I'm trying to follow the setting of expansion rate which is mentioned in MobileNetv2 paper, so I've trained a model from scratch with my dataset. The mAP of...

Hi, is it possible to get the content of output blob from any layer in a model, for example, conv1 or conv2? I've read the code in yolo_detect.cpp, but it...

Error message while executing inference with NPU

3

Hi, We adopted two methods to compile our ArmNN inference code, the first method is compiling via Makefile and the other one is via CMakeLists. We logged the execution time...

Profile execution time on NPU

3

HI, I'm trying to evaluate the execution speed of ArmNN inference on a NPU, I added the code snippet of `profilerManager` according to `ProfilerTests.cpp`: ``` // assign armnn::EthosNBackendID() to armnn::Optimize...

Noisy inference results with TF2 int8 tflite models

8

Hi, I'm migrating our segmentation model from TensorFlow1 to TensorFlow2, and the model is retrained with [TensorFlow quantization aware training technique](https://www.tensorflow.org/model_optimization/guide/quantization/training); however, the inference results of TF2 tflite model from...

Hi, Thank you for providing the awesome repository! I tried to change the dataset from COCO to Pascal VOC 2007; however, the [link](https://www.dropbox.com/s/sy1mwbaquxobv8i/VOC.zip?dl=0&file_subpath=%2FVOC) provided in "Notes on Pascal VOC experiment"...

## Question Apply SEC_LEVEL_TYPE.NONE on TenSeal context. ## Further Information I'm trying to apply different CKKS parameters into TenSeal context. In order to skip the parameter check which throws: "ValueError:...

Hi, I’m trying to compare CKKS scheme between Pyfhel and TenSeal in Python. The experiment settings are: 128 security level Polynomial degree (N) = 8192 First Mod Size (Q0) =...