• Yashas Samaga B L's avatar
    Merge pull request #16063 from YashasSamaga:cuda4dnn-shortcut-unequal · d85e67d3
    Yashas Samaga B L authored
    support eltwise sum with different number of input channels in CUDA backend
    
    * add shortcut primitive
    
    * add offsets in shortcut kernel
    
    * skip tests involving more than two inputs
    
    * remove redundant modulus operation
    
    * support multiple inputs
    
    * remove whole file indentation
    
    * skip acc in0 trunc test if weighted
    
    * use shortcut iff channels are unequal
    d85e67d3
Name
Last commit
Last update
..
activation.hpp Loading commit data...
batch_norm.hpp Loading commit data...
concat.hpp Loading commit data...
const.hpp Loading commit data...
convolution.hpp Loading commit data...
crop_and_resize.hpp Loading commit data...
eltwise.hpp Loading commit data...
inner_product.hpp Loading commit data...
lrn.hpp Loading commit data...
max_unpooling.hpp Loading commit data...
normalize_bbox.hpp Loading commit data...
padding.hpp Loading commit data...
permute.hpp Loading commit data...
pooling.hpp Loading commit data...
prior_box.hpp Loading commit data...
region.hpp Loading commit data...
reorg.hpp Loading commit data...
reshape.hpp Loading commit data...
resize.hpp Loading commit data...
roi_pooling.hpp Loading commit data...
scale_shift.hpp Loading commit data...
shortcut.hpp Loading commit data...
shuffle_channel.hpp Loading commit data...
slice.hpp Loading commit data...
softmax.hpp Loading commit data...
split.hpp Loading commit data...
transpose_convolution.hpp Loading commit data...