1069 Commits (eb932f717af2e4260d82c19f182d2a7d91f6b127)

Author	SHA1	Message	Date
shippingwang	eb932f717a	add cosine decay op, test=develop	7 years ago
Tao Luo	a2a0251db0	Merge pull request #15681 from chengduoZH/refine_api_doc ... Refine the doc of reshape, stack	7 years ago
chengduozh	1e46ab2e3e	follow comment ... test=develop	7 years ago
Dun	f7b768d364	fix group_norm (#15727) ... * fix group_norm * test=develop	7 years ago
Tao Luo	25ec6a2cfd	Merge pull request #15657 from qingqing01/fix_bn_api ... Fix batch_norm API for data_layout.	7 years ago
chengduozh	ba223e9566	doc refine ... test=develop	7 years ago
chengduozh	03f091a9d3	fix api doc ... test=develop	7 years ago
sneaxiy	7e399b0628	rename ... test=develop	7 years ago
sneaxiy	4a1c65ebee	merge origin ... test=develop	7 years ago
sneaxiy	f85245b409	test=develop	7 years ago
Dang Qingqing	01d9bf9264	Fix batch_norm API for data_layout. ... test=develop	8 years ago
kolinwei	6f0f8045f6	Revert "Async double buffered py reader"	8 years ago
jerrywgz	ceb412b0ae	speed up box coder in CPU, test=develop	8 years ago
Dun	db8fcf6b95	Merge pull request #15296 from cjld/async_double_buffered_py_reader ... Async double buffered py reader	8 years ago
jerrywgz	4eb44380a6	Merge branch 'develop' into add_clip_op	8 years ago
Xin Pan	30cc8b7a92	Merge pull request #15554 from heavengate/yolo_loss_darknet ... Yolo loss darknet	8 years ago
chengduo	c4b9eac11a	fix threshold_relu_op (#15594) ... test=develop	8 years ago
Yiqun Liu	16d54f7f23	Return parent_idx in beam_search op (#15520) ... * Refine beam_search_op to output an extra parent_idx tensor. test=develop * Fix the unittest test_beam_search_op. test=develop * Fix the merging mistake. test=develop	8 years ago
jerrywgz	72ee3c6232	Merge pull request #15398 from jerrywgz/add_axis_for_boxcoder ... Add axis for boxcoder	8 years ago
jerrywgz	e402c0ec7d	test=develop	8 years ago
jerrywgz	334f697da9	test=develop	8 years ago
Kaipeng Deng	d3eeb92bba	Merge pull request #15491 from tink2123/new_align_corners ... add align_corners and align_mode for image_resize	8 years ago
jerrywgz	3046799ecd	Merge branch 'develop' into add_clip_op	8 years ago
dengkaipeng	733bb82ec0	downsample -> downsample_ratio. test=develop	8 years ago
dengkaipeng	577424e5ec	use darknet loss and trick	8 years ago
dengkaipeng	af124dcdf6	fix API error	8 years ago
tink2123	20200e126d	fix some typo test=develop	8 years ago
tink2123	2b89f59055	add attr use_label_smooth test=develop	8 years ago
dengkaipeng	8218e30176	add gtscore. test=develop	8 years ago
dengkaipeng	32d533c2cd	cache obj_mask and gt_match_mask. test=develop	8 years ago
dengkaipeng	e7e4f084e5	ignore pred overlap gt > 0.7. test=develop	8 years ago
dengkaipeng	db8ff57a61	remove useless code and update doc. test=develop	8 years ago
dengkaipeng	0c4acc8305	imporve yolo loss implement. test=develop	8 years ago
dengkaipeng	192d293854	use stable Sigmoid Cross Entropy implement. test=develop	8 years ago
jerrywgz	7bc8481c62	Merge pull request #15418 from jerrywgz/refine_nms ... Refine nms	8 years ago
jerrywgz	aaf756272f	remove inplace arg, test=develop	8 years ago
tink2123	a0c63f1106	add align_flag ... test=develop	8 years ago
ruri	88bd7e1a61	Merge pull request #15027 from shippingwang/shufflechannel ... Add Shuffle Channel Operator	8 years ago
tink2123	b64cdaf6dc	modified default parameters ... test=develop	8 years ago
jerrywgz	466a10dcdd	refine code, test=develop	8 years ago
乔龙飞 Qiao Longfei	c58555067e	Merge pull request #14731 from jacquesqiao/optimize-cpp-reader ... Optimize cpp reader	8 years ago
jerrywgz	a39240c3b6	add attr variance for box coder, test=develop	8 years ago
Dun Liang	db9e700ba1	default use pin place && test=develop	8 years ago
Yiqun Liu	3008fa1261	Add the CUDA kernel for beam_search op (#15020) ... * Refine the beam_search op and test. * A basic CUDA implementation of beam_search for small batch_size. * Implement CUDA kernel for beam_search_op. * Use multiple CUDA threads in the same block to select the top beam. * Update the python api of beam_search op. * Enable extend function in CPU kernel of beam_search op. * Unify the CUDA codes. test=develop * Unify the CPU kernel of beam_search op. * Ensure the seletced items of beam_search_op's CPU kernel sorted by scores. * Update the description of beam_search in API.spec. * Enable the use of CUDA kernel in beam_search op. * Exclude the beam_search's CUDA unittest when there is no CUDA gpu, and delete some debuging statements. test=develop * Follow comments. test=develop * Call the CPU kernel for beam_search op when batch_size > 4. test=develop * Remove the except of is_empty op in PrepareData. test=develop	8 years ago
tink2123	78145c7dff	modified some comments ... test=develop	8 years ago
tangwei12	5cfc40dea8	nce add check sample lables, test=develop (#15463) ... * nce add check sample lables, test=develop	8 years ago
tink2123	e448bdb298	modified some comments ... test=develop	8 years ago
tink2123	88744e4ab8	fixed some errors ... test=develop	8 years ago
jerrywgz	6dfd789bfc	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into refine_nms	8 years ago
jerrywgz	6928f8318f	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into add_axis_for_boxcoder	8 years ago