Alan-Turing-Ko

Wrong calculation in pooling layer. < pooling3x3s2_max >

1

**Function: pooling3x3s2_max ( arm/impl/pooling_arm_impl.cpp )** **Layer Definition:** layer { name: "Pooling1" type: "Pooling" bottom: "Convolution3" top: "Pooling1" pooling_param { pool: MAX kernel_size: 3 stride: 2 } } **Input dim: 1,...

Help!! Crash in Net init.

1

Thanks for the great library. I want to run mobilenet (in benchmark example) on ARM in jni and model was converted successfully. I follow the arm inference example classification.cpp. Model...

Wrong shape of input tensor.

1

Thanks for the great library. I want to run my model on ARM and model was converted successfully. I follow the arm inference example classification.cpp. Model loaded successfully and graph.get_outs()...

Quantizing Accuracy consideration.

9

Hi @majianjia. Thank you for your quick response everytime. I have had accuracy test of my model using your framework. It had got 99.2% using by caffe framework, but in...

Memory optimization in ZeroPadding, Cropping layer.

1

Hi majianjia. With your kind support of ZeroPadding layer, I deployed my caffe model successfully. Now I am trying to deploy my model on memory constraint chip, and I found...

Help me!!! CL_INVALID_KERNEL

2

A/MACE: buffer_to_image.cc:175 Check failed: error == CL_SUCCESS error: CL_INVALID_KERNEL :75:33: error: use of type 'half4' requires cl_khr_fp16 extension to be enabled Why I got this error. Hope to any help.