Paddle

Author	SHA1	Message	Date
guomingz	630c1e8317	This PR improve performance of prior_box op about 1.25x faster on CPU. (#15909 ) * This PR improve performance of prior_box op about 1.25x faster on CPU. * Test Env:SKX 8180 with fake data on 28 threads(bs=1). * The below table shows the ~25% improvement which generated by [eval_tp_fake_data.py](https://github.com/PaddlePaddle/Paddle/issues/15618#issuecomment-464613976). \| Type \|Event \| Calls \| Total \| Min. \| Max. \| Ave. \| Ratio.\| \| ---------------- \| ------------------ \| ---- \| ------- \| -------- \| -------- \| ------------ \| -------- \| \| w/ optimization \| thread0::prior_box \| 6000 \| 921.201 \| 0.110572 \| 0.383402 \| 0.153533 \| 0.084585 \| \| w/o optimization \| thread0::prior_box \| 6000 \| 1151.85 \| 0.102276 \| 0.426702 \| 0.191976 \| 0.103337 \| test=develop * Fix the style issue. test=develop	7 years ago
qingqing01	48a5cccbcd	Fix debug mode in prior_box_op (#15702 ) * Fix debug mode in prior_box_op * Refine code	7 years ago
baiyf	be2d9dc2b8	Add prior_box output order control (#12032 ) * Add flag to set prior_box output order.	7 years ago
baiyf	43b6d4f8cb	put detection op together (#10595 )	8 years ago