Ops

  • affine_channel
  • anchor_generator
  • arg_max
  • assign
  • assign_value
  • attention_padding_mask
  • axpy
  • batch_norm
  • beam_search
  • beam_search_decode
  • bilinear_interp
  • box_clip
  • box_coder
  • calib
  • calib_once
  • cast
  • collect_fpn_proposals
  • concat
  • conditional_block
  • conv2d
  • conv2d_transpose
  • crop
  • decode_bboxes
  • density_prior_box
  • depthwise_conv2d
  • distribute_fpn_proposals
  • dropout
  • elementwise_add
  • elementwise_div
  • elementwise_max
  • elementwise_mul
  • elementwise_sub
  • equal
  • exp
  • expand
  • fake_channel_wise_dequantize_max_abs
  • fake_dequantize_max_abs
  • fake_quantize_dequantize_moving_average_abs_max
  • fake_quantize_moving_average_abs_max
  • fake_quantize_range_abs_max
  • fc
  • feed
  • fetch
  • fill_constant
  • fill_constant_batch_size_like
  • flatten
  • flatten2
  • floor
  • fusion_elementwise_add_activation
  • fusion_elementwise_div_activation
  • fusion_elementwise_max_activation
  • fusion_elementwise_mul_activation
  • fusion_elementwise_sub_activation
  • gather
  • generate_proposals
  • graph_op
  • greater_equal
  • greater_than
  • gru
  • gru_unit
  • hard_sigmoid
  • im2sequence
  • increment
  • instance_norm
  • io_copy
  • io_copy_once
  • is_empty
  • layer_norm
  • layout
  • layout_once
  • leaky_relu
  • less_equal
  • less_than
  • lod_reset
  • log
  • logical_and
  • logical_not
  • logical_or
  • logical_xor
  • lookup_table
  • lookup_table_v2
  • lrn
  • match_matrix_tensor
  • matmul
  • mean
  • merge_lod_tensor
  • mul
  • multiclass_nms
  • nearest_interp
  • negative
  • norm
  • notequal
  • pad2d
  • pool2d
  • power
  • prelu
  • prior_box
  • range
  • read_from_array
  • reduce_max
  • reduce_mean
  • reduce_prod
  • reduce_sum
  • relu
  • relu6
  • relu_clipped
  • reshape
  • reshape2
  • roi_align
  • rsqrt
  • scale
  • search_aligned_mat_mul
  • search_attention_padding_mask
  • search_fc
  • search_grnn
  • search_group_padding
  • search_seq_arithmetic
  • search_seq_depadding
  • search_seq_fc
  • search_seq_softmax
  • sequence_arithmetic
  • sequence_concat
  • sequence_expand
  • sequence_expand_as
  • sequence_pool
  • sequence_reshape
  • sequence_reverse
  • sequence_softmax
  • sequence_topk_avg_pooling
  • shape
  • shuffle_channel
  • sigmoid
  • slice
  • softmax
  • softsign
  • split
  • split_lod_tensor
  • sqrt
  • square
  • squeeze
  • squeeze2
  • stack
  • swish
  • tanh
  • top_k
  • transpose
  • transpose2
  • uniform_random
  • unsqueeze
  • unsqueeze2
  • var_conv_2d
  • while
  • write_to_array
  • yolo_box

Kernels

Host kernels

  • feed
  • fetch
  • flatten
  • flatten2
  • multiclass_nms
  • reshape
  • reshape2

ARM kernels

  • affine_channel
  • anchor_generator
  • arg_max
  • assign
  • assign_value
  • axpy
  • batch_norm
  • beam_search
  • beam_search_decode
  • bilinear_interp
  • box_clip
  • box_coder
  • cast
  • collect_fpn_proposals
  • concat
  • conditional_block
  • conv2d
  • conv2d_transpose
  • crop
  • decode_bboxes
  • density_prior_box
  • depthwise_conv2d
  • distribute_fpn_proposals
  • dropout
  • elementwise_add
  • elementwise_div
  • elementwise_max
  • elementwise_mul
  • elementwise_sub
  • equal
  • exp
  • expand
  • fc
  • fill_constant
  • fill_constant_batch_size_like
  • floor
  • fusion_elementwise_add_activation
  • fusion_elementwise_div_activation
  • fusion_elementwise_max_activation
  • fusion_elementwise_mul_activation
  • fusion_elementwise_sub_activation
  • gather
  • generate_proposals
  • greater_equal
  • greater_than
  • gru
  • gru_unit
  • hard_sigmoid
  • im2sequence
  • increment
  • instance_norm
  • is_empty
  • layer_norm
  • layout
  • layout_once
  • leaky_relu
  • less_equal
  • less_than
  • lod_reset
  • log
  • logical_and
  • logical_not
  • logical_or
  • logical_xor
  • lookup_table
  • lookup_table_v2
  • lrn
  • matmul
  • merge_lod_tensor
  • mul
  • nearest_interp
  • negative
  • norm
  • not_equal
  • pad2d
  • pool2d
  • power
  • prelu
  • prior_box
  • range
  • read_from_array
  • reduce_max
  • reduce_mean
  • reduce_prod
  • relu
  • relu6
  • relu_clipped
  • roi_align
  • rsqrt
  • scale
  • sequence_expand
  • sequence_pool
  • sequence_softmax
  • shape
  • shuffle_channel
  • sigmoid
  • slice
  • softmax
  • split
  • split_lod_tensor
  • squeeze
  • squeeze2
  • stack
  • swish
  • tanh
  • top_k
  • transpose
  • transpose2
  • unsqueeze
  • unsqueeze2
  • while
  • write_to_array
  • yolo_box

X86 kernels

  • batch_norm
  • cast
  • concat
  • conv2d
  • depthwise_conv2d
  • dropout
  • elementwise_add
  • elementwise_sub
  • fc
  • fill_constant_batch_size_like
  • gather
  • gelu
  • gru
  • layer_norm
  • match_matrix_tensor
  • matmul
  • mul
  • pool2d
  • reduce_sum
  • relu
  • reshape
  • reshape2
  • scale
  • search_aligned_mat_mul
  • search_attention_padding_mask
  • search_fc
  • search_grnn
  • search_group_padding
  • search_seq_arithmetic
  • search_seq_depadding
  • search_seq_fc
  • search_seq_softmax
  • sequence_arithmetic
  • sequence_concat
  • sequence_expand_as
  • sequence_pool
  • sequence_reverse
  • sequence_topk_avg_pooling
  • shape
  • slice
  • softmax
  • softsign
  • square
  • squeeze
  • squeeze2
  • stack
  • tanh
  • transpose
  • transpose2
  • var_conv_2d

CUDA kernels

  • attention_padding_mask
  • bilinear_interp
  • calib
  • concat
  • conv
  • dropout
  • elementwise_add
  • fusion_elementwise_add_activation
  • fusion_elementwise_mul_activation
  • elementwise_mul
  • feed
  • io_copy
  • layout
  • layout_once
  • leaky_relu
  • lookup_table
  • match_matrix_tensor
  • mul
  • nearest_interp
  • pool2d
  • relu
  • scale
  • search_aligned_mat_mul
  • search_fc
  • search_grnn
  • search_group_padding
  • search_seq_depadding
  • search_seq_fc
  • sequence_arithmetic
  • sequence_concat
  • sequence_pool
  • sequence_reverse
  • sequence_topk_avg_pooling
  • softmax
  • transpose
  • var_conv_2d
  • yolo_box

OpenCL kernels

  • conv2d
  • depthwise_conv2d
  • elementwise_add
  • fc
  • fusion_elementwise_add_activation
  • layout
  • layout_once
  • io_copy
  • io_copy_once
  • mul
  • pool2d
  • relu