Paddle

Commit Graph

Author	SHA1	Message	Date
Shang Zhizhou	8084b7594b	fix batchnorm when inpu dims < 3 (#31933 ) * fix batchnorm when inpu dims < 3 * add unittest for batchnorm dims = 2	5 years ago
zlsh80826	64ee255ffd	[Paddle-TRT] yolobox (#31755 ) * yolobox converter and plugin * yolobox unittest * add dynamic shape restriction * fix git merge log	5 years ago
zlsh80826	e3a38d790a	[Paddle-TRT] roi_align_plugin (#31732 ) * add roi_align_plugin * add roi align unit_test * add roi align serialization * remove roi align static plugin because of batch dim issue * refine roi align unittest and add fp16/serialization * add trt roi align condition to op_teller * refine error message * remove unnecessary reshape layer	5 years ago
zlsh80826	bfb5cf5567	[Paddle-TRT] trt affine channel converter (#31628 ) * trt affine channel converter * add trt affine channel base test * add trt affine channel NHWC * remove asterisk for python2 compatibility * trt affine channel converter * add trt affine channel base test * add trt affine channel NHWC * remove asterisk for python2 compatibility * fix rebase * move LodTensor to Tensor * add dbg info * affine channel converter only support NCHW * scale,bias are parameters, use create_parameters api * reduce test input size to not exceed the timelimit of ci * refine affine channel unittest and add serialization/dynamic test * change super to InferencePassTest for python2 compatibility * change super to InferencePassTest for python2 compatibility * fix affine channel fp16 serialize setting	5 years ago
zlsh80826	01aa252624	[Paddle-TRT] multiclass nms (#31742 ) * add multiclass_nms * add multiclass_nms unittest * add default enable_tensorrt_oss option * refine multiclas nms unittest and add serialization/dynamic test * change super to InferencePassTest for python2 compatibility * refine multiclass nms unittest * move out dynamic shape test due to ci timelimit	5 years ago
zlsh80826	bfced39eb6	[Paddle-TRT] nearest_interp op (#31626 ) * nearest_interp op converter w/ dynamic/static * fix data_layout include * add trt nearest unit_test * add nearest_interp NHWC test * update trt nearest interp nhwc testcase * remove asterisk for python2 compatibility * add empty line to prevent conflict * nearest_interp op converter w/ dynamic/static * fix data_layout include * add trt nearest unit_test * add nearest_interp NHWC test * update trt nearest interp nhwc testcase * remove asterisk for python2 compatibility * add empty line to prevent conflict * change the priority of out_h, out_w	5 years ago
zlsh80826	fe241fd02f	[Paddle-TRT] gather converter (#31640 ) * trt gather converter * add trt gather unit_test	5 years ago
Shang Zhizhou	50ac7dbfd0	Trt elementwise plugin serialize (#31587 ) * add serialize unittest * fix element_op trt plugin serialize bug	5 years ago
Pei Yang	32211fe9c4	TRT conv2d converter support SAME padding (#31379 )	5 years ago
Pei Yang	2e9e3fad15	add n-d input support for trt scale converter (#31316 ) * add n-d input support for trt scale converter * add flatten for ut * fix dims	5 years ago
jakpiase	2f1165342b	OneDNN hardswish integration (#30211 )	5 years ago
Pei Yang	00b09e86ac	[Paddle-TRT] support group_norm (#31040 ) * add group norm plugin * fix compile problems * move concat axis check to trt op teller * add nbDims for scale and bias nv dims * add group norm unit test * fix unittest * add trt version restriction for group norm op teller * fix unittest	5 years ago
Pei Yang	9b54fe4154	add trt transpose and flatten converter (#31022 )	5 years ago
Adam Osewski	4f066e316e	Layer normalization fuse pass. (#30721 )	5 years ago
Shang Zhizhou	b909450994	fix trt plugin clone and initialize bugs in TRT7.1+ (#30709 ) * fix trt plugin clone and initialize bugs * fix unit test error * enable trt in ci py3 * update unittest timeout	5 years ago
Shang Zhizhou	200ee33df8	fix unittest random error (#30808 )	5 years ago
Qi Li	1f5841c2a0	[ROCM] update cmake and dockerfile, test=develop (#30598 )	5 years ago
jakpiase	edc06c6a1b	Added fc + activation fuse pass (currently only gelu, sigmoid and tanh are supported) (#29772 )	5 years ago
Pei Yang	2480bdef6c	change hard_swish from plugin to layer (#29177 ) * change hard_swish from plugin to layer * add ut when threshold != scale	5 years ago
Shang Zhizhou	225a9c4ed8	Fix unittest (#29412 ) * fix tensorrt unittest precision error * fix unittest precision error. test_trt_subgraph_pass && test_trt_dynamic_shape_transformer_prune	5 years ago
Pei Yang	f860de4af7	support clip op trt converter (#29411 )	5 years ago
Shang Zhizhou	b9e76a0103	detect tensorRT plugin fp16 in runtime (#27933 ) * remove -DSUPPORTS_CUDA_FP16 in cuda.cmake * comile with cuda9 * add some unittest * notest;test=coverage * add unittest for trt plugin swish && split * update ernie unittest * fix some error message * remove repeated judgement of CUDA version in mbEltwiseLayerNormOpConverter * fix comile errror when CUDA_ARCH_NAME < Pascal" * fix comile error * update unittest timeout * compile with cuda9 * update error msg * fix code style * add some comments * add define IF_CUDA_ARCH_SUPPORT_FP16 * rename IF_CUDA_ARCH_SUPPORT_FP16 to CUDA_ARCH_FP16_SUPPORTED	5 years ago
joanna.wozna.intel	8c0ea4bffe	Add bf16 matmul, fc, elementwise add and mul (#28729 ) * Add bf16 matmul, fc, elementwise add and mul * Correct unit test	5 years ago
joanna.wozna.intel	2cb71c0cde	Add checkpoint to quantize (#28612 ) * Add checkpoint to quantize * Change bfloat16 option	5 years ago
lidanqing	804271cff9	Op version python mkldnn_inplace test (#28354 ) * add mkldnn inplace op version test * update mkldnn_inplace fuse pass * update the inplace test	5 years ago
Shang Zhizhou	8699f38d08	裁剪transformer模型trt支持；修复tensorRT不支持DeletePass的bug (#28517 ) * skip_layernorm_op done * add unittest * slice op convertor support trt < 6 * skip_layernorm only work in ernie	5 years ago
lidanqing	0fc181dbd0	[Fix bug] If the pass name is not found, IsCompatible should return false (#28475 )	5 years ago
YUNSHEN XIE	ba0756325a	exec ut no more than 15s 1 (#28439 ) * disable ut test_parallel_executor_fetch_isolated_var,test=document_fix * test for limiting ut exec time as 15S * fix an error caused by cannot find ut * fix some error * can not find test_transformer * fix error caused by ut not run in windows * fix error caused by Compiler Options * fix error caused by setting timeout value as 15 in python/paddle/tests/CMakeLists.txt * setting timeout value to 120s for old ut * add the timeout value setting * fix error caused by ut only run in coverage_ci * add analyzer_transformer_profile_tester * fix some error * fix some error * fix error with inference option * fix error with inference option setting as ON_INFER * add some ut to set timeout * modified some option * fix error * fix some timeout error * fix error * fix error * fix timeout for test_analyzer_bfloat16_resnet50 * fix error * setting timeout properity for some ut * first pr for new ut timeout as 15S	5 years ago
lidanqing	12b9587be5	Add conv_bias pass version python test (#28278 ) * add conv_bias pass version test * update according to reviews	5 years ago
Shang Zhizhou	ea851796e5	TensorRT中ernie模型推理性能优化，支持变长输入 (#28367 ) * fp16 result ok * change -DWITH_NVINFER_PLUGIN toconfig.EnableTensorRtOSS * auto detect special slice op converter for ernie with trt oss * ernie oss only support fp16 * fix special_slice_plugin serialize bug * matmul in tensorrt ok * ernie unittest ok * add matmul tensorrt unittest * remove demo code	5 years ago
Adam Osewski	7db747d9e8	oneDNN BatchNorm + Act fusion pass. (#27912 )	6 years ago
chentianyu03	d05058d268	Remove and reorganize the alias of APIs (#27717 ) * modify cond while_loop to paddle.static.nn.cond * modify crop_tensor to paddle.crop * modify Variable to paddle.static.Variable * remove nn.beam_search, nn.beam_search_decode, nn.gather_tree * remove bpr_loss, center_loss, rank_loss, smooth_l1, teacher_student_sigmoid_loss, edit_distance, sampled_softmax_with_cross_entropy in nn.functional * remove apis in nn.functional.learn_rate.py * remove pool2d, pool3d, adaptive_pool2d, adaptive_pool3d in nn.functional * remove apis in nn.functional.vision * remove erf, soft_relu in nn.functional.activation * remove apis in nn.functional.extension * remove nn.functional.rnn * remove hash from nn.functional.lod * remove row_conv from nn.functional.extension * remove one_hot, pad2d, pad_constant_like from nn.functional.common * remove nn.gather_tree, nn.BilinearTensorProduct, nn.Pool2D, nn.Pad2D * remove apis from optimizer.__init * remove tensor.creation.fill_constant * remove elementwise_mul in nn.functional.common and modify to paddle.multiply * remove tensor.stat.reduce_mean * remove reduce_all, reduce_any in tensor.logic * remove apis in tensor.math * remove apis in tensor.__init__ * remove has_inf, has_nan in tensor.search * remove apis in framework.__init__ * remove apis in paddle.__init__ * remove apis in nn.functional.__init__ * modify removed alias apis to raw api in doc and unittests * fix remove grid_sample bug * modify removed alias apis to raw api in doc and unittests * modify removed alias apis to raw api in doc and unittests * modify removed alias apis to raw api in doc and unittests * modify removed alias apis to raw api in doc and unittests * modify removed alias apis to raw api in doc and unittests * modify removed alias apis to raw api in doc and unittests * delete alias api relastions in doc * reserve paddle.compat, paddle.sysconfig * remove unittest for paddle.reduce_all, paddle.reduce_any * modify removed alias apis to raw api in doc and unittests * recover paddle.save and paddle.load * resolve conflicts * fix sample code missing paddle.enable_static() bug * fix sample code missing paddle.enable_static() bug * fix to_string sample code error	6 years ago
Pei Yang	8a4f85feb9	Add unittests and OP version registry for quant_conv2d_dequant_fuse_pass (#27689 )	6 years ago
Pei Yang	ae6e40a7fd	Add unittests and OP version registry for tensorrt_subgraph_pass (#27544 ) * add unittests and op version register for tensorrt_subgraph_pass * rename to test_trt_subgraph_pass.py * fix softmax converter diff when padding dim=1	6 years ago
cc	c5c13473c6	Add compatibility check for four mkldnn pass (#27364 ) * Add pass compatibility check for four mkldnn pass, test=develop	6 years ago
Wilber	3d5522146e	register seq_concat_fc_fuse pass. (#27479 )	6 years ago
Shang Zhizhou	d93661942e	fix bug sequececonv_eltadd_relu_fuse_pass (#27404 ) * fix bug sequececonv_eltadd_relu_fuse_pass, output error when sequence_conv's padding_start > 0 * fix seqconv_eltadd_relu_fuse_pass unitest error	6 years ago
Wilber	39546aa2f3	Add pass compatible and unit test. (#27377 )	6 years ago
Pei Yang	fd7ab4e63c	register pass compatibility (#27357 ) * pass compatibility * add compatibility registry * add unittests for different padding * add assert * drop errmsg	6 years ago
haozech	7e6dfcf9b2	Add 3 pass version check (#27283 )	6 years ago
Shang Zhizhou	3c11717988	add op version checker to ir passes (#27329 )	6 years ago
Shang Zhizhou	47fdc60ecc	Optimize slice trt plugin (#26970 ) * optimize slice TRT plugin This patch removes unnecessary barrier for data transfer of needed offset, so data transfer can be overlap with GPU kernel execution. This patch also fixes incorrect name of slice plugin. That is, replaces "layernorm" with "slice" test=develop * add serialize/deserialize to slice plugin * add static shape slice trt plugin * fix slice trt op convertor dynamic shape bug * fix format by clang-format * fix pylint format error * fix problems commented by peiyang Co-authored-by: Ryan Jeng <rjeng@nvidia.com>	6 years ago
Wilber	f827665ae6	[Pass Compatible] Bind python compatible. (#27262 )	6 years ago
Shang Zhizhou	e6e2e53782	Optimize error report (#27254 ) * optimize errror report * add test case for pad op converter * fix some spelling mistake commented by peiyang	6 years ago
Yiqun Liu	1be6bf45ae	Add assign to fusion_group and enhance inplace execution in fusion_group. (#26121 )	6 years ago
Peihan	885e88552a	resolve inference_pass_test input lodtensor case, test=develop (#25541 ) * refine infer ir pass tests, test=develop * commit to change copy_from_cpu input to np array, test=develop	6 years ago
Yiqun Liu	9ed16a4347	Fix random fail because of precision problem in unittest of fusion_group (#25051 )	6 years ago
liu zhengxi	971ebb2657	decrease the input size for test_transpose_flatten_concat_fuse_pass, test=develop (#24992 )	6 years ago
Yiqun Liu	6b464f969a	Add an operator node in unittest to make the fusing result unique. (#24617 )	6 years ago
石晓伟	e396c47850	try to resolve the inference_pass_test, test=develop (#24172 )	6 years ago

1 2

70 Commits (develop)