You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
 
 
nihuini a3a2548aa2 initial fp16s fp16a shader build system 7 years ago
..
absval.comp initial fp16s fp16a shader build system 7 years ago
absval_pack4.comp initial fp16s fp16a shader build system 7 years ago
batchnorm.comp [WIP] vulkan compute (#618) 7 years ago
batchnorm_pack4.comp massive simd optimize in compute shader (#772) 7 years ago
binaryop.comp fix binaryop shader binding, use shared buffer state, fix blob copy in non-light mode, fix #817 7 years ago
binaryop_pack4.comp fix binaryop shader binding, use shared buffer state, fix blob copy in non-light mode, fix #817 7 years ago
clip.comp clip shader 7 years ago
clip_pack4.comp clip shader 7 years ago
concat.comp copy buffer has offset alignment limit, re-implement concat as compute pipeline 7 years ago
concat_pack4.comp copy buffer has offset alignment limit, re-implement concat as compute pipeline 7 years ago
concat_pack4to1.comp copy buffer has offset alignment limit, re-implement concat as compute pipeline 7 years ago
convolution.comp [WIP] vulkan compute (#618) 7 years ago
convolution_1x1s1d1.comp [WIP] vulkan compute (#618) 7 years ago
convolution_pack1to4.comp add convolution pack1to4 pack4to1 7 years ago
convolution_pack4.comp massive simd optimize in compute shader (#772) 7 years ago
convolution_pack4to1.comp add convolution pack1to4 pack4to1 7 years ago
convolutiondepthwise.comp massive simd optimize in compute shader (#772) 7 years ago
convolutiondepthwise_group.comp group convolution packing family 7 years ago
convolutiondepthwise_group_pack1to4.comp group convolution packing family 7 years ago
convolutiondepthwise_group_pack4.comp group convolution packing family 7 years ago
convolutiondepthwise_group_pack4to1.comp group convolution packing family 7 years ago
convolutiondepthwise_pack4.comp massive simd optimize in compute shader (#772) 7 years ago
crop.comp crop shader 7 years ago
crop_pack4.comp crop shader 7 years ago
deconvolution.comp implement deconvolution vulkan family support 7 years ago
deconvolution_pack1to4.comp implement deconvolution vulkan family support 7 years ago
deconvolution_pack4.comp implement deconvolution vulkan family support 7 years ago
deconvolution_pack4to1.comp implement deconvolution vulkan family support 7 years ago
deconvolutiondepthwise.comp implement depthwise deconvolution vulkan, fix top blob state 7 years ago
deconvolutiondepthwise_group.comp group deconvolution packing family 7 years ago
deconvolutiondepthwise_group_pack1to4.comp group deconvolution packing family 7 years ago
deconvolutiondepthwise_group_pack4.comp group deconvolution packing family 7 years ago
deconvolutiondepthwise_group_pack4to1.comp group deconvolution packing family 7 years ago
deconvolutiondepthwise_pack4.comp implement depthwise deconvolution vulkan, fix top blob state 7 years ago
dropout.comp [WIP] vulkan compute (#618) 7 years ago
dropout_pack4.comp massive simd optimize in compute shader (#772) 7 years ago
eltwise.comp [WIP] vulkan compute (#618) 7 years ago
eltwise_pack4.comp massive simd optimize in compute shader (#772) 7 years ago
flatten.comp flatten image 7 years ago
flatten_pack4.comp flatten image 7 years ago
innerproduct.comp fix name conflict on ios 7 years ago
innerproduct_pack1to4.comp fix name conflict on ios 7 years ago
innerproduct_pack4.comp fix name conflict on ios 7 years ago
innerproduct_pack4to1.comp fix name conflict on ios 7 years ago
interp.comp interp vulkan 7 years ago
interp_pack4.comp interp vulkan 7 years ago
lrn_norm.comp fix name conflict on ios 7 years ago
lrn_norm_across_channel_pack4.comp fix name conflict on ios 7 years ago
lrn_norm_within_channel_pack4.comp fix name conflict on ios 7 years ago
lrn_square_pad.comp add lrn shader 7 years ago
lrn_square_pad_across_channel_pack4.comp lrn norm across channel pack4, rename member name with pipeline prefix 7 years ago
lrn_square_pad_within_channel_pack4.comp lrn norm across channel pack4, rename member name with pipeline prefix 7 years ago
packing_1to4.comp packing vec and image shader 7 years ago
packing_4to1.comp packing vec and image shader 7 years ago
padding.comp add lrn shader 7 years ago
padding_pack4.comp add lrn shader 7 years ago
permute.comp permute shader 7 years ago
permute_pack4to1.comp priorbox shader, fix permute order 1 on image, fix potential staging memory leak 7 years ago
pooling.comp pooling full padding 7 years ago
pooling_global.comp massive simd optimize in compute shader (#772) 7 years ago
pooling_global_pack4.comp massive simd optimize in compute shader (#772) 7 years ago
pooling_pack4.comp pooling full padding 7 years ago
prelu.comp prelu shader 7 years ago
prelu_pack4.comp prelu shader 7 years ago
priorbox.comp priorbox shader, fix permute order 1 on image, fix potential staging memory leak 7 years ago
priorbox_mxnet.comp reshape shader family 7 years ago
relu.comp [WIP] vulkan compute (#618) 7 years ago
relu_pack4.comp massive simd optimize in compute shader (#772) 7 years ago
reorg.comp reorg shader 7 years ago
reorg_pack1to4.comp reorg shader 7 years ago
reorg_pack4.comp reorg shader 7 years ago
reshape.comp reshape shader family 7 years ago
reshape_pack1to4.comp reshape shader family 7 years ago
reshape_pack4.comp reshape shader family 7 years ago
reshape_pack4to1.comp reshape shader family 7 years ago
scale.comp [WIP] vulkan compute (#618) 7 years ago
scale_pack4.comp massive simd optimize in compute shader (#772) 7 years ago
shufflechannel.comp shufflechannel shader 7 years ago
shufflechannel_pack4.comp shufflechannel shader 7 years ago
sigmoid.comp add absval sigmoid tanh shader 7 years ago
sigmoid_pack4.comp add absval sigmoid tanh shader 7 years ago
softmax_div_sum.comp fix softmax axis order on 3-dim, fix caffe reshape conversion, regenerate ssd param 7 years ago
softmax_div_sum_pack4.comp fix softmax axis order on 3-dim, fix caffe reshape conversion, regenerate ssd param 7 years ago
softmax_exp_sub_max.comp fix softmax axis order on 3-dim, fix caffe reshape conversion, regenerate ssd param 7 years ago
softmax_exp_sub_max_pack4.comp fix softmax axis order on 3-dim, fix caffe reshape conversion, regenerate ssd param 7 years ago
softmax_reduce_max.comp fix softmax axis order on 3-dim, fix caffe reshape conversion, regenerate ssd param 7 years ago
softmax_reduce_max_pack4.comp fix softmax axis order on 3-dim, fix caffe reshape conversion, regenerate ssd param 7 years ago
softmax_reduce_sum.comp fix softmax axis order on 3-dim, fix caffe reshape conversion, regenerate ssd param 7 years ago
softmax_reduce_sum_pack4.comp fix softmax axis order on 3-dim, fix caffe reshape conversion, regenerate ssd param 7 years ago
tanh.comp add absval sigmoid tanh shader 7 years ago
tanh_pack4.comp add absval sigmoid tanh shader 7 years ago
unaryop.comp massive simd optimize in compute shader (#772) 7 years ago
unaryop_pack4.comp massive simd optimize in compute shader (#772) 7 years ago