- 25 2月, 2020 1 次提交
-
-
由 Yuan Shuai 提交于
-
- 24 2月, 2020 5 次提交
-
-
由 yiicy 提交于
update mask detection demo
-
由 石晓伟 提交于
-
由 cc 提交于
* Support lac model, fix bug for argmax lod_reset, test=develop
-
由 xiebaiyuan 提交于
-
由 Yuan Shuai 提交于
[LITE][OPENCL] support fp16 for cl_image_converter, layout, activation all OpenCL image kernel. test=develop (#2964) * [LITE][OPENCL] support fp16 for cl_image_converter, layout, activation image kernel. test=develop * add conv, depthwise and UT. test=develop * add pool, conv, nearest_interp kernel. test=develop * support fp16 for scale, reshape, concat, fc buffer opencl kernel. test=develop * refactor for mul opencl buffer kernel. test=develop * support fp16 for elementwise_mul opecl image kernel. test=develop * support fp16 for elementwise_mul opencl image kernel. test=develop * support fp16 for ele_add, fuse_ele_add_act opencl kernel. test=develop * rename io_copy. test=develop * mobilenetv1,v2 passed on 855. test=develop * fix opt for opencl. test=develop
-
- 22 2月, 2020 3 次提交
-
-
由 yiicy 提交于
fix tiny_publish link error when open LOG
-
由 huzhiqiang 提交于
-
由 HappyAngel 提交于
-
- 21 2月, 2020 4 次提交
-
-
由 hong19860320 提交于
-
由 huzhiqiang 提交于
-
由 huzhiqiang 提交于
-
由 xiaogang 提交于
fix: move quant op to basic
-
- 20 2月, 2020 7 次提交
-
-
由 cc 提交于
skip fusing quantized conv2d + relu6 for now
-
由 Yuan Shuai 提交于
-
由 zhupengyang 提交于
-
由 huzhiqiang 提交于
-
由 Wilber 提交于
Optimize cuda kernel and remove io_copy added by default due to missing fetch_cuda kernel
-
由 yiicy 提交于
add multiclass_nms2 kernel, test=develop
-
由 HappyAngel 提交于
* fix caliberate error, values from [-128, 127] to [-127, 127], test=develop * add classify demo and detection demo, test=develop
-
- 19 2月, 2020 3 次提交
-
-
由 huzhiqiang 提交于
-
由 cc 提交于
* add weight quant for combined model after optimized, test=develop
-
由 Wilber 提交于
* fix compile. test=develop
-
- 18 2月, 2020 7 次提交
-
-
由 huzhiqiang 提交于
-
由 huzhiqiang 提交于
-
由 huzhiqiang 提交于
-
由 cc 提交于
* make full_publish to fix link bug in mask demo
-
由 HappyAngel 提交于
add cv docs, test=document_fix
-
由 yiicy 提交于
-
由 cc 提交于
-
- 17 2月, 2020 2 次提交
- 16 2月, 2020 1 次提交
-
-
由 huzhiqiang 提交于
-
- 15 2月, 2020 2 次提交
-
-
由 huzhiqiang 提交于
-
由 Yuan Shuai 提交于
* mobilenetv1/v2,mnasnet,yolonano,sr models passed with opencl image2d kernel. test=develop * Fix gflag shape define. test=develop
-
- 14 2月, 2020 5 次提交
-
-
由 huzhiqiang 提交于
-
由 GaoWei8 提交于
* Replace Softsign Eigen with c implementation test=develop
-
由 Yiqun Liu 提交于
* Optimize softmax. When the input tensor is 2-D and axis is 1, there is no need to resize. * Optimize the gru, avoid calling Tensor::Slice. test=develop * Remove a std::vector in softmax. test=develop * Define CalculateSeqWidth to get the width of a sequence. test=develop
-
由 huzhiqiang 提交于
-
由 Yuan Shuai 提交于
* comment All opencl buffer kernels. test=develop * refactor conv, depthwise into one routing selection. test=develop
-