1727 Commits

Author	SHA1	Message	Date
xiongkun	2200f30052	fix sot-slow problem (#2976) ... * fix sot-slow problem * fix format * add comment	2023-09-18 17:27:01 +08:00
feifei-111	9bcb71ab81	Fix resnext model, split main logic with guard (#2956) ... * update * update * update	2023-09-18 17:25:57 +08:00
zhangyubo0722	ef796960c0	support http pretrained	2023-09-12 17:45:39 +08:00
zhenming lin	98935e0bb7	Add ML-Decoder Support (#2957) ... * 添加ML-Decoder，并使其可以在Arch作用域下控制 * 添加MultiLabelAsymmetricLoss * 添加MultiLabelMAP评价方式，并避免其在回合内计算，每回合计算一次，节约时间 * 添加COCO2017数据集格式转换脚本 * 添加OneCycleLR学习率调度策略 * 添加ResNet50_ml_decoder * 添加ResNet_ml_decoder * 添加ResNet_ml_decoder * 添加ResNet_ml_decoder preprocess * 添加ResNet_ml_decoder * 添加ResNet_ml_decoder * 直接从model中拉class_num参数 * fix message error * fix message error * 给出基于inference model预测的文档 * 融合cutout使其具有随机生成填充值的能力 * 更正变量名称 * 更新configs * 更新README * fix bugs * fix bugs * update * update * update	2023-09-08 16:17:35 +08:00
zhangyubo0722	cdecc0b437	fix hgnet kwargs (#2949)	2023-09-01 23:36:58 +08:00
zhangyubo0722	ed67436647	del head_init_scale (#2947)	2023-09-01 20:15:54 +08:00
zhangyubo0722	d7a7d3e5e1	fix topk bug (#2945)	2023-09-01 19:28:17 +08:00
zhangyubo0722	74a33b7f50	fix gbk (#2941)	2023-09-01 17:49:33 +08:00
gaotingquan	b3fcc98610	to be compatible with training and evaluation	2023-08-29 16:11:16 +08:00
zhangyubo0722	f3b2b2f4ad	[uapi]Save predict result (#2926) ... * sava predict result	2023-08-29 14:32:07 +08:00
gaotingquan	ae96c979eb	always log 'topk=1' when k < output_dims to ensure consistent log formatting	2023-08-28 17:01:49 +08:00
Tingquan Gao	eddba911b1	modify some default hyperparams to adapt to fine-tune downstream tasks (#2921) ... 1. unset EMA because of the relatively small size of most downstream dataset; 2. use mean and std of IMN.	2023-08-25 22:02:21 +08:00
Tingquan Gao	1f8a830b58	fix model name (#2908) ... * fix model name * fix: bug when distillation	2023-08-23 14:55:17 +08:00
Tingquan Gao	0675971d0b	rm fluid api (#2907)	2023-08-11 15:51:42 +08:00
Tingquan Gao	962c540ca4	debug: when using Piecewise.learning_rate while total epochs < 30 (#2901)	2023-08-07 15:26:49 +08:00
Tingquan Gao	907e5f7832	support Piecewise.learning_rate (#2898)	2023-08-04 12:14:19 +08:00
wuyefeilin	83adff2acc	add dataset alias for PaddleX (#2893)	2023-08-02 10:41:25 +08:00
Tingquan Gao	607a07cb28	compatible with the AMP.use_amp field in config (#2889)	2023-07-28 17:48:52 +08:00
Tingquan Gao	bb1596b8c3	compatibility with python 3.11 (#2878)	2023-07-20 10:50:52 +08:00
cuicheng01	4da6f35bf2	support infer nested directory images	2023-06-29 19:43:40 +08:00
baocheny	75a5bb17ba	add 2 more custom devices intel_gpu and apple mps	2023-06-29 19:42:38 +08:00
baocheny	3d0c0eb59d	add 2 more custom devices intel_gpu and apple mps	2023-06-29 19:42:38 +08:00
Bobholamovic	bda65e0c87	Remove ClasModels_general_quantization.yaml	2023-06-26 14:20:38 +08:00
Bobholamovic	de5c4e1b1c	Change vdl dir	2023-06-26 14:20:38 +08:00
Bobholamovic	b4f10436cf	Rename variable	2023-06-26 14:20:38 +08:00
Bobholamovic	d6137854e2	Accommodate UAPI	2023-06-26 14:20:38 +08:00
gaotingquan	07b597f56e	increase bs to avoid oom	2023-06-06 11:19:01 +08:00
gaotingquan	caa6393cd4	set drop_last to False in train data	2023-06-06 11:19:01 +08:00
gaotingquan	cf5d629a64	fix	2023-06-06 11:19:01 +08:00
gaotingquan	4643fdee09	update pretrained url	2023-06-06 11:19:01 +08:00
mmglove	dd9b186e82	ppcls/utils/profiler.py	2023-06-05 21:23:35 +08:00
mmglove	54d27a1204	fix profiler	2023-06-05 21:23:35 +08:00
mmglove	259c0ca9de	fix profiler	2023-06-05 21:23:35 +08:00
gaotingquan	bdfa1feb2f	update for amp config refactoring	2023-05-29 19:52:09 +08:00
gaotingquan	09817fe859	complete amp args	2023-05-29 19:52:09 +08:00
gaotingquan	b3f7e3b974	unify comments	2023-05-29 19:52:09 +08:00
gaotingquan	8405882f11	debug	2023-05-29 19:52:09 +08:00
gaotingquan	0f86c55576	add amp args, use_amp=False	2023-05-29 19:52:09 +08:00
gaotingquan	2d8346cd3b	fix _init_amp when export	2023-05-29 19:52:09 +08:00
gaotingquan	f67cfe2c2a	fix ema: set_value() -> paddle.assign()	2023-05-26 15:40:48 +08:00
gaotingquan	2823e48be5	fix head_init_scale	2023-05-26 15:40:48 +08:00
gaotingquan	042d1e7ef8	fix layer key name for dynamic lr in adamwdl optimizer	2023-05-26 15:40:48 +08:00
gaotingquan	80ae9079cd	add clip finetune config	2023-05-26 15:40:48 +08:00
gaotingquan	6d924f85ee	fix for clip ... 1. fix bias_attr to False for conv of PatchEmbed; 2. support return_tokens_mean for Head of CLIP; 3. support remove_cls_token_in_forward for CLIP; 4. support head_init_scale argument for ViT backbone; 5. support get_num_layers() and no_weight_decay() for ViT backbone.	2023-05-26 15:40:48 +08:00
gaotingquan	74e6c8aa33	add fp32 and ampo2 ultra configs	2023-05-25 16:57:16 +08:00
gaotingquan	f469dfe8d2	decrease bs	2023-05-25 16:57:16 +08:00
gaotingquan	53ac4675ad	warmup 5 epochs	2023-05-25 16:57:16 +08:00
gaotingquan	c2802b90aa	increase bs, num_workers to speed up	2023-05-25 16:57:16 +08:00
gaotingquan	b2ba6994a0	add ultra configs	2023-05-25 16:57:16 +08:00
gaotingquan	14d06fb6bd	support AMP.use_amp arg	2023-05-25 16:16:02 +08:00