• Adam Rogowiec's avatar
    [ONNX] GlobalLpPool operator (#2476) · d357cb92
    Adam Rogowiec authored
    * Utility functions for calculating Lp norm.
    
    * Use functor object as a reduction operation.
    
    * Use new api of make_ng_reduction_op.
    
    * Use utility norm functions for reduction operations.
    
    * Onnx GlobalLpPool operator.
    
    * Ensure correct shapes after lp_norm reduction.
    
    * Remove unused function overload.
    
    * Fix shapes and tensor types.
    
    * Unit tests.
    
    * Update comments.
    
    * Update supported ops status table.
    
    * Fix: take absolute value of input tensor elements.
    
    * UT: with odd value p-norm.
    
    * Fix: move taking abs value into respective lp-norm functions.
    
    * Fix clang -Wdocumentation-unknown-command error.
    
    * Update supported op status table with new Jira ticket for Erf op.
    
    * Update supported_ops status table.
    
    * Update interface of make_ng_reduction_op - accept std::function object.
    
    * Update to use new make_ng_reduction_op api.
    
    * Remove unused header.
    
    * Fix errors on CentOS.
    d357cb92
Name
Last commit
Last update
..
add_abc.onnx [ONNX] Support for Split op (#1377)
add_abc_initializers.onnx [ONNX] Support for initializers without corresponding inputs (#2406)
add_bcast.onnx [ONNX] Numpy style binary broadcasting (#1549)
addmul_abc.onnx [ONNX] Gemm operator (#1465)
argmax_int32.onnx [NGCPU-339] UT for ArgMin ArgMax with int32 input data type. (#2256)
argmin_int32.onnx [NGCPU-339] UT for ArgMin ArgMax with int32 input data type. (#2256)
argmin_no_keepdims.onnx [ONNX] Add ArgMin/Max operators (#1898)
average_pool_2d.onnx [ONNX] Average and Max Pooling (#1489)
average_pool_2d_pads.onnx [ONNX] Average and Max Pooling (#1489)
batchnorm_default.onnx [ONNX] Batchnorm operation (#1396)
concat.onnx [ONNX] Concat operator (#1524)
conv2d_dilation_assym_pads_strides.onnx [ONNX] Fix convolution errors (#2025)
conv3d_bias.onnx [ONNX] Fix convolution errors (#2025)
conv_transpose_w_groups.onnx [ONNX] ConvTranspose with groups. (#2289)
conv_with_strides_and_asymmetric_padding.onnx [ONNX] Code cleanup (#1476)
conv_with_strides_no_padding.onnx [ONNX] Conv operation (#1472)
conv_with_strides_padding.onnx [ONNX] Conv operation (#1472)
conv_with_strides_padding_bias.onnx [ONNX] Conv operation (#1472)
cosh.onnx [ONNX] Add hyperbolic functions support (#2402)
custom_operator.onnx [ONNX] Support for initializers without corresponding inputs (#2406)
custom_operator_default_domain.onnx [ONNX] Support for initializers without corresponding inputs (#2406)
depth_to_space.onnx [ONNX] DepthToSpace operator. (#2342)
depth_to_space_bad_blocksize.onnx [ONNX] DepthToSpace operator. (#2342)
depth_to_space_chw.onnx [ONNX] DepthToSpace operator. (#2342)
depth_to_space_no_blocksize.onnx [ONNX] DepthToSpace operator. (#2342)
div.onnx Loading commit data...
elu.onnx Loading commit data...
flatten.onnx Loading commit data...
gemm_abc.onnx Loading commit data...
global_lp_pool_p0.onnx Loading commit data...
global_lp_pool_p1.onnx Loading commit data...
global_lp_pool_p2.onnx Loading commit data...
global_lp_pool_p3.onnx Loading commit data...
initializer_wo_input.onnx Loading commit data...
leaky_relu.onnx Loading commit data...
lstm_fwd_with_clip.onnx Loading commit data...
malformed.onnx Loading commit data...
matmul.onnx Loading commit data...
matmul_vec_ten3d.onnx Loading commit data...
max.onnx Loading commit data...
max_pool_2d_pads.onnx Loading commit data...
mean.onnx Loading commit data...
min_two_inputs.onnx Loading commit data...
missing_input.onnx Loading commit data...
missing_op_domain.onnx Loading commit data...
one_hot_axis.onnx Loading commit data...
one_hot_no_axis.onnx Loading commit data...
override_op.onnx Loading commit data...
prelu.onnx Loading commit data...
reduce_l1.onnx Loading commit data...
reduce_l2.onnx Loading commit data...
reduce_log_sum.onnx Loading commit data...
reduce_log_sum_exp.onnx Loading commit data...
reduce_max.onnx Loading commit data...
reduce_mean.onnx Loading commit data...
reduce_min.onnx Loading commit data...
reduce_prod.onnx Loading commit data...
reduce_sum.onnx Loading commit data...
reduce_sum_square.onnx Loading commit data...
relu.onnx Loading commit data...
reshape_extended_dims.onnx Loading commit data...
reshape_negative_dim.onnx Loading commit data...
reshape_negative_with_zero_dims.onnx Loading commit data...
reshape_output_shape_as_input.onnx Loading commit data...
reshape_reduced_dims.onnx Loading commit data...
reshape_reordered_dims.onnx Loading commit data...
reshape_single_dim.onnx Loading commit data...
selu.onnx Loading commit data...
shape.onnx Loading commit data...
sigmoid.onnx Loading commit data...
sign.onnx Loading commit data...
sinh.onnx Loading commit data...
softmax.onnx Loading commit data...
softplus.onnx Loading commit data...
space_to_depth.onnx Loading commit data...
space_to_depth_bad_blocksize.onnx Loading commit data...
space_to_depth_chw.onnx Loading commit data...
space_to_depth_no_blocksize.onnx Loading commit data...
split_equal_parts_2d.onnx Loading commit data...
split_equal_parts_default.onnx Loading commit data...
split_variable_parts_2d.onnx Loading commit data...
squeeze_duplicate_axes.onnx Loading commit data...
sub.onnx Loading commit data...
sum.onnx Loading commit data...
sum_one_input.onnx Loading commit data...
sum_opset8.onnx Loading commit data...
tanh.onnx Loading commit data...
thresholded_relu.onnx Loading commit data...
top_k.onnx Loading commit data...
unsqueeze.onnx Loading commit data...
unsupported_op.onnx Loading commit data...
where.onnx Loading commit data...