258 Commits

Author	SHA1	Message	Date
gaotingquan	b033661bcf	tipc: VAN_tiny -> VAN_B0	2022-10-20 18:49:44 +08:00
0x45f	cde853bfa7	Polish benchmark_train.sh for dynamicTostatic	2022-10-19 14:55:32 +08:00
gaotingquan	d7014129f1	tipc: set DataLoader.Train.sampler.shuffle=False ... benchmark needs the field to set Global.print_batch_step=1. Check file "./test_tipc/benchmark_train.sh#L76" for details.	2022-10-17 11:24:57 +08:00
cuicheng01	4438acfda8	Merge pull request #2361 from TingquanGao/dev/tipc_fix_log_path ... turn off the mkldnn and trt in ConvNeXt infer	2022-09-29 14:07:24 +08:00
gaotingquan	9f64ff6c1c	tipc: turn off mkldnn and trt ... it will time out when turn on trt or mkldnn	2022-09-29 05:22:44 +00:00
gaotingquan	be434dc66c	tipc: fix the inference model name	2022-09-29 11:16:22 +08:00
gaotingquan	b55791f696	tipc: styling code	2022-09-28 13:33:19 +00:00
zhengya01	091cb607f6	fix tipc log	2022-09-23 18:53:35 +08:00
zhengya01	8897aba3d0	fix tipc ptq log	2022-09-23 18:53:35 +08:00
gaotingquan	69b53bc95f	tipc: modify the statistical range of log ... the ips is unstable in the first 50 iter when training lite modle.	2022-09-21 13:58:00 +08:00
gaotingquan	983d512a45	tipc: fix the keyword of ShiTu model ... In benchmark_train mode, the config name is benchmark.txt. So the keyword of ShiTu should be model_name instead of the config name.	2022-09-19 14:30:54 +08:00
HydrogenSulfate	42758f5463	fix benchmark train's config for GeneralRecognitionV2, and polish TIPC docs	2022-09-14 08:54:22 +00:00
gaotingquan	dafcb5cddf	tipc: fix log path for GeneralRecognition	2022-09-14 10:44:29 +08:00
qili93	b1c2350a26	[TIPC] add more scripts change, test=develop	2022-09-13 15:03:14 +08:00
cuicheng01	ec21470a35	Merge pull request #2258 from TingquanGao/dev/tipc_fix_log_path ... tipc: fix log path	2022-09-10 00:06:54 +08:00
gaotingquan	7e239952a8	tipc: set num_workers to 4 ... The benchmark requires threads num to be set 4 when DALI is used for best performance. And the param num_workers is not worked before commit 80c10bb99503eeb349a5d676bd0af4908a74b425.	2022-09-09 10:10:18 +00:00
qili93	0d9ddc0812	[TIPC] add scripts for npu and xpu, test=develop	2022-09-09 02:39:48 +08:00
gaotingquan	0cea550455	tipc: fix log path	2022-09-08 10:57:03 +00:00
gaotingquan	2700beea82	tipc: fix log path	2022-09-08 08:15:33 +00:00
gaotingquan	fb669a05b8	tipc: fix log path	2022-09-06 13:25:09 +00:00
gaotingquan	b3d26a987d	tipc: fix log path	2022-09-05 15:57:49 +00:00
gaotingquan	44b55fb67c	tipc: paddle2onnx --enable_dev_version=False	2022-09-05 19:04:20 +08:00
HydrogenSulfate	4ee9dd49e0	fix small bug in prepare.sh	2022-09-04 14:22:44 +00:00
HydrogenSulfate	c449ba3420	add fleet chain and update inference_rec.yaml and corresponding output for feature_extraction.md	2022-09-04 14:20:07 +00:00
HydrogenSulfate	4620cfb9bc	fix typo in config files	2022-09-04 13:52:58 +00:00
HydrogenSulfate	94b48ac568	add cpp serving & cpp infer chain, update TIPC docs	2022-09-04 13:42:53 +00:00
HydrogenSulfate	38e78b0c81	add paddle2onnx_infer chain	2022-09-01 03:12:11 +00:00
HydrogenSulfate	a8278e84c4	add pact chain	2022-09-01 03:01:51 +00:00
HydrogenSulfate	6adee2720f	add ptq infer	2022-09-01 02:52:24 +00:00
HydrogenSulfate	d2ffc5e408	add lite_train_lite_infer chain	2022-08-31 17:28:48 +00:00
gaotingquan	2f5c0c71da	fix: replace ResNet50.yaml with ResNet50_amp_O2_ultra.yaml when AMPO2 ... It is needed that use dali, NHWC and 4 channels when training ResNet50 with AMPO2	2022-08-26 10:59:16 +08:00
gaotingquan	ea66adbec1	fix: need install paddleclas whl	2022-08-26 10:59:16 +08:00
root	5810695672	tipc: set num_wokers=12	2022-08-05 14:34:14 +08:00
root	b77a431451	tipc: set num workers=12 iff fp16	2022-08-05 14:34:14 +08:00
root	81b42f627b	tipc: rm useless bs	2022-08-05 14:34:14 +08:00
root	430fbd5df9	tipc: support fp32/fp16 training benchmark of PP-Shitu	2022-08-05 14:34:14 +08:00
root	a7f124042b	mv	2022-08-05 14:34:14 +08:00
root	483c0383e5	tipc: set bs=256 to avoid oom	2022-08-05 14:34:14 +08:00
root	b9de09e547	tipc: set num_wokers=12	2022-08-05 14:34:14 +08:00
gaotingquan	7990fe5767	tipc: set num_wokers=8	2022-08-05 14:34:14 +08:00
gaotingquan	3d1fb324a3	tipc: support AMP O2	2022-08-05 14:34:14 +08:00
gaotingquan	595a6c5bcf	format code style	2022-08-05 14:34:14 +08:00
gaotingquan	ac1c206d4a	tipc: support benchmark with fp32/fp16 training	2022-08-05 14:34:14 +08:00
cuicheng01	b1f0d6d083	Merge pull request #1908 from flytocc/PeleeNet_PR ... add PeleeNet	2022-07-14 17:50:54 +08:00
Walter	c5b5b34306	Merge pull request #2151 from RainFrost1/develop ... 修复benchmark中bs过大时导致log过少的问题	2022-07-14 14:21:40 +08:00
dongshuilong	46532c446b	fix train list bug for benchmark	2022-07-14 03:35:50 +00:00
cuicheng01	1fccb35be7	Merge branch 'develop' into PeleeNet_PR	2022-07-14 10:47:06 +08:00
cuicheng01	1bbe4b5ed1	Merge pull request #1885 from flytocc/ConvNeXt ... ConvNext & EMA & gradient accumulation	2022-07-14 10:45:25 +08:00
HydrogenSulfate	3dfc42bed0	set eval_during_train=False and save_interval=2 to reduce checkpoint storage	2022-07-13 19:36:32 +08:00
HydrogenSulfate	e66447b3a8	skip python inference when test for mainbody_det	2022-07-13 18:07:50 +08:00