search

Oneflow-Inc / CoModels

3 stars 2 forks source link

模型适配进度（拓展） #163

Open kokuro-asahi opened 10 months ago

kokuro-asahi commented 10 months ago
总计：8+14+9+26+21+10+3+6+6+10+3+9+11+4+88=228 领域 功能 基础模型 支持方式 负责人 状态 展开数量 Onelab负责人 OneLab公开项目链接
cv classification EfficientNet_b0 flowvision ke 完成 8 li https://www.oneflow.cloud/drill/#/project/public/code?id=fa5438d8c14b8fa64429da52ea3aaa4b
cv classification EfficientNet_b1 flowvision cui 完成 8 li https://www.oneflow.cloud/drill/#/project/public/code?id=0919cef11021fa3729d9678b27bb5434
cv classification EfficientNet_b2 flowvision cui 完成 8 li https://www.oneflow.cloud/drill/#/project/public/code?id=fa8c4ace23affba27863ea9f56bbb662
cv classification EfficientNet_b3 flowvision cui 完成 8 li https://www.oneflow.cloud/drill/#/project/public/code?id=9486b2d7f8523973daf7b90d7fb9fc17
cv classification EfficientNet_b4 flowvision cui 完成 8 li https://www.oneflow.cloud/drill/#/project/public/code?id=d33198119b667ea422696576e5c67a4e
cv classification EfficientNet_b5 flowvision cui 完成 8 li https://www.oneflow.cloud/drill/#/project/public/code?id=d4c9a2d6db1a934b3896b56b92a03e74
cv classification EfficientNet_b6 flowvision cui 完成 8 li https://www.oneflow.cloud/drill/#/project/public/code?id=f9d51026c6d13eaca244a4d4c3eca1c3
cv classification EfficientNet_b7 flowvision cui 完成 8 li https://www.oneflow.cloud/drill/#/project/public/code?id=9b2d0d5ad34bf2eceff55f77007a260d
cv classification regnet_y_400mf flowvision cui 完成 14 li https://www.oneflow.cloud/drill/#/project/public/code?id=74db0fcbf0b7b42d74a5c37d1dcd8c8d
cv classification regnet_y_800mf flowvision cui 完成 14 li https://www.oneflow.cloud/drill/#/project/public/code?id=7af27966f711f8d0cf07b51d40a57992
cv classification regnet_y_1_6gf flowvision cui 完成 14 li https://www.oneflow.cloud/drill/#/project/public/code?id=579f7eb5c7d26076962e0721d1d709f9
cv classification regnet_y_3_2gf flowvision cui 完成 14 li https://www.oneflow.cloud/drill/#/project/public/code?id=5affa8b3893616466b0242397924a247
cv classification regnet_y_8gf flowvision cui 完成 14 li https://www.oneflow.cloud/drill/#/project/public/code?id=a38f54a87436578dafa7ac15927a9af9
cv classification regnet_y_16gf flowvision cui 完成 14 li https://www.oneflow.cloud/drill/#/project/public/code?id=35607cd00b6c22f5fd02254818b400ae
cv classification regnet_y_32gf flowvision cui 完成 14 li https://www.oneflow.cloud/drill/#/project/public/code?id=dfb022ad6b5b7e3b431c84e548dd53fa
cv classification regnet_x_400mf flowvision cui 完成 14 li https://www.oneflow.cloud/drill/#/project/public/code?id=ed0d790aa2d1e911a72daa7e6605a97c
cv classification regnet_x_800mf flowvision cui 完成 14 li https://www.oneflow.cloud/drill/#/project/public/code?id=d0097d4399eac0f6c31fe3dc29dacb17
cv classification regnet_x_1_6gf flowvision cui 完成 14 li https://www.oneflow.cloud/drill/#/project/public/code?id=9b2b5d00b3ff83198dfdc48a9085deb0
cv classification regnet_x_3_2gf flowvision cui 完成 14 li https://www.oneflow.cloud/drill/#/project/public/code?id=240b02c57ab1c27e98024acaf3aef70a
cv classification regnet_x_8gf flowvision cui 完成 14 li https://www.oneflow.cloud/drill/#/project/public/code?id=4e76ee1a1129ab9c2c5f903e6ffb7d39
cv classification regnet_x_16gf flowvision cui 完成 14 li https://www.oneflow.cloud/drill/#/project/public/code?id=36bca178cb147c64c3251ef38082c593
cv classification regnet_x_32gf flowvision cui 完成 14 li https://www.oneflow.cloud/drill/#/project/public/code?id=4b9bb2aa6ad9857fb31c96299fce9051
cv classification rexnetv1_1_0 flowvision cui 完成 9 li https://www.oneflow.cloud/drill/#/project/public/code?id=f8e263b706369a6846c13985edad8433
cv classification rexnetv1_1_3 flowvision cui 完成 9 li https://www.oneflow.cloud/drill/#/project/public/code?id=5acd5c7d3dcffd712779101d3af9e0ba
cv classification rexnetv1_1_5 flowvision cui 完成 9 li https://www.oneflow.cloud/drill/#/project/public/code?id=edc766c2407bb08ca908516322282a19
cv classification rexnetv1_2_0 flowvision cui 完成 9 li https://www.oneflow.cloud/drill/#/project/public/code?id=7e28ee4f9157562fa795899038da2a6e
cv classification rexnetv1_3_0 flowvision cui 完成 9 li https://www.oneflow.cloud/drill/#/project/public/code?id=44f0cd0f722917ff90e921412d2fd775
cv classification rexnet_lite_1_0 flowvision cui 完成 9 li https://www.oneflow.cloud/drill/#/project/public/code?id=8c0935ce218c7fe14721a54de380cf95
cv classification rexnet_lite_1_3 flowvision cui 完成 9 li https://www.oneflow.cloud/drill/#/project/public/code?id=44a6598a4f7ce345a5d7c3ba458eb7e4
cv classification rexnet_lite_1_5 flowvision cui 完成 9 li https://www.oneflow.cloud/drill/#/project/public/code?id=bc98489e6cc245e8348dd3289d237f97
cv classification rexnet_lite_2_0 flowvision cui 完成 9 li https://www.oneflow.cloud/drill/#/project/public/code?id=24f5e35e6056919730c4cabd354144c3
cv classification vit_tiny_patch16_224 flowvision zhang 完成 26 li https://www.oneflow.cloud/drill/#/project/public/code?id=25334d0e04ca945c25b331b67d2eb550
cv classification vit_tiny_patch16_384 flowvision zhang 完成 26 li https://www.oneflow.cloud/drill/#/project/public/code?id=e1302a0101857135ab62132d1e35aeae
cv classification vit_small_patch32_224 flowvision zhang 完成 26 li https://www.oneflow.cloud/drill/#/project/public/code?id=2648e2213ad95a43b35631ca58e0be84
cv classification vit_small_patch32_384 flowvision zhang 完成 26 li https://www.oneflow.cloud/drill/#/project/public/code?id=12768b29f94c5be820d11e9d5a3ae81f
cv classification vit_small_patch16_224 flowvision zhang 完成 26 li https://www.oneflow.cloud/drill/#/project/public/code?id=281132f74d7608078277ee4b46ef1701
cv classification vit_small_patch16_384 flowvision zhang 完成 26 li https://www.oneflow.cloud/drill/#/project/public/code?id=3f579f7f1350223ea18797a1a204c1e8
cv classification vit_base_patch32_224 flowvision zhang 完成 26 li https://www.oneflow.cloud/drill/#/project/public/code?id=18e3f3be24228e68ec8abaf3c51d1a08
cv classification vit_base_patch32_384 flowvision zhang 完成 26 li https://www.oneflow.cloud/drill/#/project/public/code?id=c76367e43afccb54509ef57a47641a2b
cv classification vit_base_patch16_384 flowvision zhang 完成 26 li https://www.oneflow.cloud/drill/#/project/public/code?id=5ef00487de1c66d4b59056aabe95e92a
cv classification vit_base_patch8_224 flowvision zhang 完成 26 li https://www.oneflow.cloud/drill/#/project/public/code?id=9b637c392fe656a10c5401cb205e5a1e
cv classification vit_base_patch16_224 flowvision 完成 26 li https://www.oneflow.cloud/drill/#/project/public/code?id=ae6f744c9a856d2f04784742f9161143
cv classification vit_large_patch32_384 flowvision zhang 完成 26 li https://www.oneflow.cloud/drill/#/project/public/code?id=96c37fd309acf0c9a007753e0782a181
cv classification vit_large_patch16_224 flowvision zhang 完成 26 li https://www.oneflow.cloud/drill/#/project/public/code?id=73350d451067d9a7164cf5f60f2915cd
cv classification vit_large_patch16_384 flowvision zhang 完成 26 li https://www.oneflow.cloud/drill/#/project/public/code?id=20efdf3e5ce3526d180e9d68f03c533a
cv classification vit_base_patch16_224_sam flowvision zhang 完成 26 li https://www.oneflow.cloud/drill/#/project/public/code?id=be4351753e1262778745eb1098c49c57
cv classification vit_base_patch32_224_sam flowvision zhang 完成 26 li https://www.oneflow.cloud/drill/#/project/public/code?id=c73d578cc1f4059e05e7367b69c69bf7
cv classification vit_tiny_patch16_224_in21k flowvision zhang 没有ImageNet 21k数据集 26
cv classification vit_small_patch32_224_in21k flowvision zhang 没有ImageNet 21k数据集 26
cv classification vit_small_patch16_224_in21k flowvision zhang 没有ImageNet 21k数据集 26
cv classification vit_base_patch32_224_in21k flowvision zhang 没有ImageNet 21k数据集 26
cv classification vit_base_patch16_224_in21k flowvision zhang 没有ImageNet 21k数据集 26
cv classification vit_base_patch8_224_in21k flowvision zhang 没有ImageNet 21k数据集 26
cv classification vit_large_patch32_224_in21k flowvision zhang 没有ImageNet 21k数据集 26
cv classification vit_large_patch16_224_in21k flowvision zhang 没有ImageNet 21k数据集 26
cv classification vit_huge_patch14_224_in21k flowvision zhang 没有ImageNet 21k数据集 26
cv classification vit_base_patch16_224_miil_in21k flowvision zhang 没有ImageNet 21k数据集 26
cv classification vit_base_patch16_224_miil flowvision zhang 完成 26 li https://www.oneflow.cloud/drill/#/project/public/code?id=21423b30bd3ea7e717c486c5c96fabe8
cv classification deit_tiny_patch16_224 flowvision zhang 完成 22 li https://www.oneflow.cloud/drill/#/project/public/code?id=13cfd9108b2f72cb92a99a846e98e6ff
cv classification deit_base_patch16_224 flowvision zhang 完成 22 li https://www.oneflow.cloud/drill/#/project/public/code?id=af5947962e7720e97a570703a9e53694
cv classification deit_base_patch16_384 flowvision zhang 完成 22 li https://www.oneflow.cloud/drill/#/project/public/code?id=606e242389cccb930249be457130dbf3
cv classification deit_tiny_distilled_patch16_224 flowvision zhang 完成 22 li https://www.oneflow.cloud/drill/#/project/public/code?id=5891ddd5f03d6af0b2aeb690ced37b5d
cv classification deit_small_distilled_patch16_224 flowvision zhang 完成 22 li https://www.oneflow.cloud/drill/#/project/public/code?id=849921cbc3a4c0b31f22203c0b60c690
cv classification deit_base_distilled_patch16_224 flowvision zhang 完成 22 li https://www.oneflow.cloud/drill/#/project/public/code?id=9a58d5387296f5673265405938ec8d65
cv classification deit_base_distilled_patch16_384 flowvision zhang 完成 22 li https://www.oneflow.cloud/drill/#/project/public/code?id=b1ebb442d627b9350681e2c8c97c74c2
cv classification deit_base_patch16_LS_224 flowvision zhang 完成 22 li https://www.oneflow.cloud/drill/#/project/public/code?id=d17491afb893e3d0ab7915f53fcb674f
cv classification deit_base_patch16_LS_224_in21k flowvision zhang 完成 22 li https://www.oneflow.cloud/drill/#/project/public/code?id=425be3891ca118082c05635fd2305914
cv classification deit_base_patch16_LS_384 flowvision cui 完成 22 li https://www.oneflow.cloud/drill/#/project/public/code?id=ff8e43ef6752f38d46c6575296d244a6
cv classification deit_base_patch16_LS_384_in21k flowvision cui 完成 22 li https://www.oneflow.cloud/drill/#/project/public/code?id=6f1deac6410a3db19d7d22befba4fc0b
cv classification deit_huge_patch14_LS_224 flowvision cui 完成 22 li https://www.oneflow.cloud/drill/#/project/public/code?id=8a5517f5f84c5f6a2497c7307c1e6899
cv classification deit_huge_patch14_LS_224_in21k flowvision cui 完成 22 li https://www.oneflow.cloud/drill/#/project/public/code?id=8a5517f5f84c5f6a2497c7307c1e6899
cv classification deit_large_patch16_LS_224_in21k flowvision cui 进行中 22 li
cv classification deit_large_patch16_LS_384_in21k flowvision cui 完成 22 li https://www.oneflow.cloud/drill/#/project/public/code?id=274caa0440f9df12e989678ed205c0d4
cv classification deit_small_patch16_LS_224_in21k flowvision cui 完成 22 li https://www.oneflow.cloud/drill/#/project/public/code?id=30fbf529f1d61ac77b72514f8e913cc8
cv classification deit_small_patch16_224 flowvision li 完成 22 li https://www.oneflow.cloud/drill/#/project/public/code?id=ffabc32455e8966ad33bb07974f194bf
cv classification deit_small_patch16_LS_384 flowvision cui 完成 22 li https://www.oneflow.cloud/drill/#/project/public/code?id=e2e3159b7bcbd13a91e7736ee6ea3960
cv classification deit_small_patch16_LS_384_in21k flowvision cui 进行中 22 li https://www.oneflow.cloud/drill/#/project/public/code?id=9be2c26a99c860a3f98c3f0a5b854e61
cv classification deit_large_patch16_LS_224 flowvision li 完成 22 li https://www.oneflow.cloud/drill/#/project/public/code?id=37ff4dabe9c2b9132e76badcabce7506
cv classification deit_small_patch16_LS_224 flowvision li 完成 22 li https://www.oneflow.cloud/drill/#/project/public/code?id=21f5789060c865a30c1eec1aade0c2c1
cv classification deit_large_patch16_LS_384 flowvision li 完成 22 li https://www.oneflow.cloud/drill/#/project/public/code?id=457dd8d362220fe32d340bfee7b7f306
cv classification mlp_mixer_s16_224 flowvision ke 无模型 10
cv classification mlp_mixer_s32_224 flowvision ke 无模型 10
cv classification mlp_mixer_b16_224 flowvision ke 完成 10 li https://www.oneflow.cloud/drill/#/project/public/code?id=6680d967c8d66d5ad6716cb3e1d4e63a
cv classification mlp_mixer_b32_224 flowvision ke 无模型 10
cv classification mlp_mixer_b16_224_in21k flowvision ke infer低 10
cv classification mlp_mixer_l16_224 flowvision ke 完成 10 li https://www.oneflow.cloud/drill/#/project/public/code?id=9d39de61bbaa96f995494981606131bf
cv classification mlp_mixer_l32_224 flowvision ke 无模型 10
cv classification mlp_mixer_l16_224_in21k flowvision ke infer低 10
cv classification mlp_mixer_b16_224_miil flowvision ke infer低 10
cv classification mlp_mixer_b16_224_miil_in21k flowvision ke infer低 10
cv classification convmixer_768_32_relu flowvision ke 完成 3 li https://www.oneflow.cloud/drill/#/project/public/code?id=ea73a6af66d18116bd17159bd43dfd09
cv classification convmixer_1024_20 flowvision ke 完成 3 li https://www.oneflow.cloud/drill/#/project/public/code?id=d4cae7556245781c1da91665be4a4a2a
cv classification convmixer_1536_20 flowvision ke 完成 3 li https://www.oneflow.cloud/drill/#/project/public/code?id=9ab2b324f3643859826de05b0e0b0b09
cv classification res2net101_26w_4s flowvision ke 完成 6 li https://www.oneflow.cloud/drill/#/project/public/code?id=cd1e229dae70bfe32e33d57798e5b62e
cv classification res2net50_14w_8s flowvision ke 完成 6 li https://www.oneflow.cloud/drill/#/project/public/code?id=ab6afe87aa33c278311d63b649f6b117
cv classification res2net50_26w_4s flowvision ke 完成 6 li https://www.oneflow.cloud/drill/#/project/public/code?id=77a0ad1c8078b75cba5d823bca361c04
cv classification res2net50_26w_6s flowvision ke 完成 6 li https://www.oneflow.cloud/drill/#/project/public/code?id=fa0a61d5d72247d22863c9392b48f89c
cv classification res2net50_26w_8s flowvision ke 完成 6 li https://www.oneflow.cloud/drill/#/project/public/code?id=156564fb425715a833a255b3736f9e9d
cv classification res2net50_48w_2s flowvision ke 完成 6 li https://www.oneflow.cloud/drill/#/project/public/code?id=1ddc5d5f68e2d3a75d9a9c8d9a59c97a
cv classification cait_M48 flowvision ke 完成 6 li https://www.oneflow.cloud/drill/#/project/public/code?id=405fc951ffa80c9dcc3a605d41587de4
cv classification cait_M36 flowvision ke 完成 6 li https://www.oneflow.cloud/drill/#/project/public/code?id=c88925b7c61385982b8b25658467ed7d
cv classification cait_S36 flowvision ke 完成 6 li https://www.oneflow.cloud/drill/#/project/public/code?id=a9165b582fca4851946455e1158fa5d5
cv classification cait_S24 flowvision ke 完成 6 li https://www.oneflow.cloud/drill/#/project/public/code?id=ef302a9ec1241961ad2d9ff21dd28a1f
cv classification cait_S24_224 flowvision ke 完成 6 li https://www.oneflow.cloud/drill/#/project/public/code?id=ef9a11c3daa419e068f913d6c1da49be
cv classification cait_XS24 flowvision ke 完成 6 li https://www.oneflow.cloud/drill/#/project/public/code?id=ec1e9e9df444a8012a699020d7876c3f
cv classification dla34 flowvision ke 完成 10 li https://www.oneflow.cloud/drill/#/project/public/code?id=92865fd08123c84dd002ad934dab9f30
cv classification dla46_c flowvision ke 完成 10 li https://www.oneflow.cloud/drill/#/project/public/code?id=4a23dbc75bd431049450b709f1e2dc82
cv classification dla46x_c flowvision ke 完成 10 li https://www.oneflow.cloud/drill/#/project/public/code?id=48e8f80f732ce1ff49401c239079799b
cv classification dla60x_c flowvision ke 完成 10 li https://www.oneflow.cloud/drill/#/project/public/code?id=72a36495db48f1f3f4830108eed027df
cv classification dla60 flowvision ke 完成 10 li https://www.oneflow.cloud/drill/#/project/public/code?id=0adcb76c0580f05ec53d87b3ed2689bb
cv classification dla60x flowvision ke 完成 10 li https://www.oneflow.cloud/drill/#/project/public/code?id=a44cc9aa071ec6171c0aae3ccc7eea69
cv classification dla102 flowvision ke 完成 10 li https://www.oneflow.cloud/drill/#/project/public/code?id=df2140e6b6ff3c0bebc2a05782bf26ff
cv classification dla102x flowvision ke 完成 10 li https://www.oneflow.cloud/drill/#/project/public/code?id=c134390359f1d99647ffc6e814b4b59a
cv classification dla102x2 flowvision ke 完成 10 li https://www.oneflow.cloud/drill/#/project/public/code?id=a1a5a8c0d0038728372b98116df242db
cv classification dla169 flowvision ke 完成 10 li https://www.oneflow.cloud/drill/#/project/public/code?id=b02b358f69982312ce01028c25325a3a
cv classification genet_small flowvision ke 完成 3 li https://www.oneflow.cloud/drill/#/project/public/code?id=32e02310d717d8fa2c6841cf44b1b398
cv classification genet_normal flowvision ke 完成 3 li https://www.oneflow.cloud/drill/#/project/public/code?id=d0ff57b9dd41286da62eeff48365f393
cv classification genet_large flowvision ke 完成 3 li https://www.oneflow.cloud/drill/#/project/public/code?id=e395406e16ce22f84d5c6c75945da24c
cv classification hrnet_w18_small flowvision ke 完成 9 li https://www.oneflow.cloud/drill/#/project/public/code?id=1fd560ba809b25931f26285ee87fbd01
cv classification hrnet_w18_small_v2 flowvision ke 完成 9 li https://www.oneflow.cloud/drill/#/project/public/code?id=ed3a0a67216e00c5e16ca68297e2e51c
cv classification hrnet_w18 flowvision ke 完成 9 li https://www.oneflow.cloud/drill/#/project/public/code?id=477afc03da45d95475c585087263aa16
cv classification hrnet_w30 flowvision ke 完成 9 li https://www.oneflow.cloud/drill/#/project/public/code?id=b7830e267e11d1c24dc2e1f809815b58
cv classification hrnet_w32 flowvision ke 完成 9 li https://www.oneflow.cloud/drill/#/project/public/code?id=02b78b105d109ee2d73b141a84131d5d
cv classification hrnet_w40 flowvision ke 完成 9 li https://www.oneflow.cloud/drill/#/project/public/code?id=c4ebccc6d6c51c4726268327bf0d1277
cv classification hrnet_w44 flowvision ke 完成 9 li https://www.oneflow.cloud/drill/#/project/public/code?id=4ad93af70e75ad40b35b3a4037b42cd2
cv classification hrnet_w48 flowvision ke 完成 9 li https://www.oneflow.cloud/drill/#/project/public/code?id=5260c81e98fb3e315b211143e9fc3d1f
cv classification hrnet_w64 flowvision ke 完成 9 li https://www.oneflow.cloud/drill/#/project/public/code?id=f16740051ea0350f2c4a7cdbcf3f03c4
cv classification fan_vit_tiny flowvision zhang 完成 12 li https://www.oneflow.cloud/drill/#/project/public/code?id=5fdc757c88feab49cf3cd5321e191fcc
cv classification fan_vit_small flowvision zhang 完成 12 li https://www.oneflow.cloud/drill/#/project/public/code?id=f5e4fc22ddab8c1bacf86bc06b1b4f3a
cv classification fan_vit_large flowvision zhang 没有模型 12 li
cv classification fan_hybrid_tiny flowvision zhang 完成 12 li https://www.oneflow.cloud/drill/#/project/public/code?id=91286420dfed2958fcdaa44947f5fdd6
cv classification fan_hybrid_small flowvision zhang 完成 12 li https://www.oneflow.cloud/drill/#/project/public/code?id=0f6c5f287e19e86199d1c651353683bc
cv classification fan_hybrid_base flowvision zhang 完成 12 li https://www.oneflow.cloud/drill/#/project/public/code?id=dc39a54b6125b8a025d8ee9aa9a56d7e
cv classification fan_hybrid_large flowvision zhang 没有模型 12 li
cv classification fan_base_18_p16_224 flowvision li 完成 12 li https://www.oneflow.cloud/drill/#/project/public/code?id=f6af8debe2b2cac9ac6a78b6640131fd
cv classification fan_hybrid_base_in22k_1k flowvision zhang 完成 12 li https://www.oneflow.cloud/drill/#/project/public/code?id=4e48d6211354973f5a25d684e55e204b
cv classification fan_hybrid_base_in22k_1k_384 flowvision zhang 完成 12 li https://www.oneflow.cloud/drill/#/project/public/code?id=727170a01151d1b960dae29560aefd1b
cv classification fan_hybrid_large_in22k_1k flowvision zhang 完成 12 li https://www.oneflow.cloud/drill/#/project/public/code?id=8fa9548610a845ebde39fe4a9e36e680
cv classification fan_hybrid_large_in22k_1k_384 flowvision zhang 完成 12 li https://www.oneflow.cloud/drill/#/project/public/code?id=932d7f4b229527e61eeedc46d90f77c3
cv classification pvt_small flowvision ke 完成 4 li https://www.oneflow.cloud/drill/#/project/public/code?id=6f2d36e01ff216a91e884e106cc61b01
cv classification pvt_tiny flowvision zhang 完成 4 li https://www.oneflow.cloud/drill/#/project/public/code?id=68109071b32382961de42e6b2f6d38b1
cv classification pvt_medium flowvision zhang 完成 4 li https://www.oneflow.cloud/drill/#/project/public/code?id=f90ccd277fd99b91728907fbf4ad6052
cv classification pvt_large flowvision zhang 完成 4 li https://www.oneflow.cloud/drill/#/project/public/code?id=6b5533383abbf289ab905a6f902b3bbb
cv classification regionvit_base flowvision ke 完成 li https://www.oneflow.cloud/drill/#/project/public/code?id=8a772ef77e8265dad8e4ef6699b52c61
cv classification van_base flowvision ke 完成 li https://www.oneflow.cloud/drill/#/project/public/code?id=3e9a2df19f47b4325144885e3a37cbc1
cv classification AlexNet flowvision ke 完成 li https://www.oneflow.cloud/drill/#/project/public/code?id=72080813882acf841b8de45e88102f3c 
cv classification SqueezeNet flowvision ke 完成 li https://www.oneflow.cloud/drill/#/project/public/code?id=0a5e15b73b1c8289ef43439e3fdac6ba 
cv classification SqueezeNet 1.1 flowvision ke 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=46d7e0a2ef7f55aa9cf82b37a7c530c2
cv classification VGG-11 flowvision ke 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=61c0fe736758792228d4e0bfb27beb04
cv classification VGG-11-BN flowvision ke 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=381d00d5d6ce5ca40dcedd003d98b94a
cv classification VGG-13 flowvision ke 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=9bc8a6c17172722a7e04cf74f8b3b4de
cv classification VGG-13-BN flowvision ke 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=77e3480052ab9bacd2b37caeca5885e8
cv classification VGG-16 flowvision ke 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=6166d5d2af2b1bd29edadf88b62ef975
cv classification VGG-16-BN flowvision ke 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=89ac74c572ee6833d0a70d1650e1708a
cv classification VGG-19 flowvision ke 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=12256eee1b678bbe45f8610caba00f96
cv classification VGG-19-BN flowvision ke 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=e84034d9edd66977cd70130268dda4e0
cv classification GoogLeNet flowvision zhang 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=0f49a25e9fd85d21c2ae06e200452112
cv classification Inception_V3 flowvision zhang 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=3648dac8652969bdd49848071d0f968a
cv classification ResNet-18 flowvision ke 完成 li https://www.oneflow.cloud/drill/#/project/public/code?id=52e1e7d51e9f340ee18101edac59cc6d 
cv classification ResNet-34 flowvision ke 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=7ba5a5946ee5bdade3a6ed0d421a28d1
cv classification ResNet-50 flowvision ke 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=64669893332daab2ae874dfe839abd88
cv classification ResNet-101 flowvision ke 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=d069d9ce05d84290518f1a79c8db0f15
cv classification ResNet-152 flowvision ke 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=e60699fb4e75a3c9a6efe451c3c4dc4c
cv classification ResNeXt-50 32x4d flowvision ke 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=fa231a90a53651b92b9642b56c29dd19
cv classification ResNeXt-101 32x8d flowvision ke 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=0eb0c2b9f04381e99a8ed99b0ecf6e8a
cv classification ResNeSt-50 flowvision zhang 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=3669763ea9382906b0132dfb04c50c47
cv classification ResNeSt-101 flowvision zhang 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=b3b28a3065d162df62df6144b3cc8f6e
cv classification ResNeSt-200 flowvision zhang 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=41f5ecf0e37f60b17fa697b972ab5738
cv classification ResNeSt-269 flowvision zhang 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=9d3d1ab2792a86a9d3c02887a9a3b1d2
cv classification SE-ResNet101 flowvision zhang 完成 li https://www.oneflow.cloud/drill/#/project/public/code?id=6b50454e5ef09a31c40ada924c199cf9
cv classification SE-ResNet152 flowvision zhang 完成 li https://www.oneflow.cloud/drill/#/project/public/code?id=00ffee25af16d5951ec01e6fcaba5a29
cv classification SE-ResNet50 flowvision zhang 完成 li https://www.oneflow.cloud/drill/#/project/public/code?id=87aec92114ebc62e5b29575454a29f3f
cv classification SE-ResNeXt101-32x4d flowvision zhang 完成 li https://www.oneflow.cloud/drill/#/project/public/code?id=763356489039b10c91a635f3f59e4029
cv classification SE-ResNeXt50-32x4d flowvision zhang 完成 li https://www.oneflow.cloud/drill/#/project/public/code?id=21fefb3568303b5d0328e64b76bf1bfc
cv classification SENet-154 flowvision zhang 完成 li https://www.oneflow.cloud/drill/#/project/public/code?id=eb114bd5bc28f464ee624db70abb1a30
cv classification DenseNet-121 flowvision cui 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=9383d1ee8cf6b0beb1d82e001327e7e6
cv classification DenseNet-161 flowvision cui 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=748e5cf1d4d07c3439e61102f41503d1
cv classification DenseNet-169 flowvision cui 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=2c31515668a6c3d01ac9dbe5d35f4051
cv classification DenseNet-201 flowvision cui 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=0ed8889b7be3e26a4e0b821cc584380d
cv classification ShuffleNet_V2 x0.5 flowvision cui 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=75a9ebdce52dbaea88ea921df32a36f2
cv classification ShuffleNet_V2 x1.0 flowvision cui 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=90d9a3ddcb8bafabc951742ebc4defd5
cv classification ShuffleNet_V2 x1.5 flowvision cui 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=569fe5043eda185002ab35a08d9707d7
cv classification ShuffleNet_V2 x2.0 flowvision cui 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=50d954efb04235e6b9f993cbb9492457
cv classification MobileNet_V2 flowvision cui 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=8fac67899e5bdcc0981da13c3cab1b89
cv classification MobileNet_V3 small flowvision cui 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=e5fd35642b7ac9b537110ceb70c9832a
cv classification MobileNet_V3 large flowvision cui 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=6529be091cb9c1af73fbe43f85092dee
cv classification MNASNet x0.5 flowvision cui 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=9c2419d250dc5b2d61c47fdbcbc45b23
cv classification MNASNet x0.75 flowvision cui 完成    li https://www.oneflow.cloud/drill/#/project/public/code?id=dea56da93c65719360b637a842096c7e 
cv classification MNASNet x1.0 flowvision cui 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=92dd8f01260cf7a01db8bc57f0d44cf9
cv classification MNASNet x1.3 flowvision cui 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=f09034e44f7fa3653a108a486defe1a9
cv classification GhostNet flowvision ke 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=8b02840745f682ae928da9bc618e6bb0
cv classification CrossFormer-T flowvision zhang 完成 li https://www.oneflow.cloud/drill/#/project/public/code?id=ec876cce29a7d9da57f3f01bcac57bb8
cv classification CrossFormer-S flowvision zhang 完成 li  https://www.oneflow.cloud/drill/#/project/public/code?id=31ab1b82aa32df9fd9eca0d99226c6a2
cv classification CrossFormer-B flowvision zhang 完成 li  https://www.oneflow.cloud/drill/#/project/public/code?id=ee4ecc63d59f0e26e178185adf5b70e4
cv classification CrossFormer-L flowvision zhang 完成 li  https://www.oneflow.cloud/drill/#/project/public/code?id=bc3f08aa3513464d10aab15a75a67fa5
cv classification PoolFormer-S12 flowvision zhou 完成  li https://www.oneflow.cloud/drill/#/project/public/code?id=3802898d0df4ab05479425c56cbdc5d8
cv classification PoolFormer-S24 flowvision zhang 完成  li  https://www.oneflow.cloud/drill/#/project/public/code?id=08b8873535d3179796697808cd470bba
cv classification PoolFormer-S36 flowvision zhang 完成  li https://www.oneflow.cloud/drill/#/project/public/code?id=e76ce4d08ffc55277ec18b584acf0d07 
cv classification PoolFormer-M36 flowvision zhang 完成  li  https://www.oneflow.cloud/drill/#/project/public/code?id=03654a36457379ae02da2cda230cf8ef
cv classification PoolFormer-M48 flowvision zhang 完成  li  https://www.oneflow.cloud/drill/#/project/public/code?id=52fe605fc822974a72a359c5ca68a8e2
cv classification gMLP flowvision ke 完成 li https://www.oneflow.cloud/drill/#/project/public/code?id=db86fa73ae42ec1138bbf9c282d715a7
cv classification ConvNeXt flowvision ke 完成 可拓展至：18 li https://www.oneflow.cloud/drill/#/project/public/code?id=580631c6005d96e2fc756b697264911c
cv classification LeViT flowvision ke 完成(infer低) 可拓展至:5 li https://www.oneflow.cloud/drill/#/project/public/code?id=e53b9e1e52602aa6887e8289aed2ae42
cv classification MobileViT flowvision li 进行中（infer低）
cv Semantic Segmentation fcn_resnet101_coco flowvision zhou 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=5a67c4d8f94d50904b00e1ab7dc073b0
cv Semantic Segmentation fcn_resnet50_coco flowvision zhou 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=5b958d4676e6a873a85f50f7327d5810
cv Semantic Segmentation deeplabv3_mobilenet_v3_large_coco flowvision zhou 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=7fcd75aeda576e41fcc8841a5d38c44d
cv Semantic Segmentation deeplabv3_resnet101_coco flowvision zhou 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=98a1dbe2c439f5fae5c24ba7c6109c47
cv Semantic Segmentation deeplabv3_resnet50_coco flowvision zhou 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=56ee96d906df67c2af2390d36dffb694
cv Semantic Segmentation lraspp_mobilenet_v3_large_coco flowvision zhou 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=0836620e36d9c728547fde5c08d2939d
cv Object Detection fasterrcnn_mobilenet_v3_large_320_fpn flowvision zhou 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=83955d0dbd8f6e398384297300031d40
cv Object Detection fasterrcnn_mobilenet_v3_large_fpn flowvision zhou 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=123c9a849cc8180206e8cfe42e32c7e3
cv Object Detection fasterrcnn_resnet50_fpn flowvision zhou 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=3e9d4f6d8d81dd3626ff3a2491a4ece3
cv Object Detection maskrcnn_resnet50_fpn flowvision zhou 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=bd90c25e18860ac4c4f669e0a7a2dadc
cv Object Detection retinanet_resnet50_fpn flowvision zhou 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=965abe47aeac05155363492ec6b6d6c7
cv Object Detection ssd300_vgg16 flowvision zhou 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=c677f6ab3885b5be9fd482575ee25a21
cv Object Detection ssdlite320_mobilenet_v3_large flowvision zhou 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=aacf292f065ecfbeee4b3df54bde6e55
cv Object Detection fcos_resnet50_fpn flowvision zhou 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=dd9230b9351651ffce3df71878fcb470
cv Neural Style Transfer style_transfer.fast_neural_style flowvision zhou 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=0006f425af1fee25d4dc14385a38a4e6
cv Face Recognition iresnet50 flowvision zhou 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=a61c970743904dc4773e40b0abecd064
cv Face Recognition iresnet101 flowvision zhou 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=b4804fb168d41aa3a94f83abd0019a7d
cv   VisionTransformer libai li 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=dc07b87d3a60e36d182f908e8bb660f9
nlp   SwinTransformer libai li 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=62f0d66aa7441b9f10f877176af27e7d
nlp   SwinTransformerV2 libai li 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=47260dd33f92bedfc1f024095dcbc035
nlp   ResMLP libai li 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=f76e38f8228c97ecadfe0482ed2fc06c
nlp   BERT libai li 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=c972180739924ca78d89f664b7ad135f
nlp   RoBERTa libai li 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=d3bbb391e714b1f780aac86e3aa074a9
nlp   T5 libai li 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=6152fadc8e6997f972ce1a85841daf78
nlp   GPT-2 libai li 完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=161fb0c7e6c609526b97bd30d935e1b8
nlp text_classfication Transformer CoModels maolin  完成   li https://www.oneflow.cloud/drill/#/project/public/code?id=1ad00d3d7db8c504b08345461b3999b0
nlp odd_numbers Transformer CoModels maolin 完成    li https://www.oneflow.cloud/drill/#/project/public/code?id=c6bd57e6b4f6362348783da981f6f0ff
science Equation inversion-Lorenz system PINNs CoModels zhang 完成    li https://www.oneflow.cloud/drill/#/project/public/code?id=91f8fb23498318f83dd16e0e875db6bc
science Fluid simulation-ldc PINNs CoModels zhang  完成    li https://www.oneflow.cloud/drill/#/project/public/code?id=b1914ead9370947a60b3a9c3ee60b0c0
iwkkk commented 9 months ago

hrnet_w18_small

Training ``` cd CoModels/cv/classification/hrnet_w18_small bash train.sh ``` 训练所用超参数 ``` AMP_OPT_LEVEL: '' AUG: AUTO_AUGMENT: rand-m9-mstd0.5-inc1 COLOR_JITTER: 0.4 CUTMIX: 0.0 CUTMIX_MINMAX: null MIXUP: 0.0 MIXUP_MODE: batch MIXUP_PROB: 1.0 MIXUP_SWITCH_PROB: 0.5 RECOUNT: 1 REMODE: pixel REPROB: 0.25 BASE: - '' DATA: BATCH_SIZE: 8 CACHE_MODE: part DATASET: imagenet DATA_PATH: /data/dataset/ImageNet/extract IMG_SIZE: 224 INTERPOLATION: bicubic NUM_CLASSES: 1000 NUM_WORKERS: 4 PIN_MEMORY: true SYNTHETIC_DATA: false ZIP_MODE: false EVAL_MODE: true LOCAL_RANK: 0 MODEL: ARCH: hrnet_w18_small CHECKPOINTS: null DROP_PATH_RATE: 0.1 DROP_RATE: 0.0 LABEL_SMOOTHING: 0.1 NUM_CLASSES: 1000 PRETRAINED: true RESUME: '' OUTPUT: output/hrnet_w18_small/default PRINT_FREQ: 50 SAVE_FREQ: 1 SEED: 42 TAG: default TEST: CROP: true SEQUENTIAL: false THROUGHPUT_MODE: false TRAIN: ACCUMULATION_STEPS: 0 AUTO_RESUME: false BASE_LR: 0.01 CLIP_GRAD: 5.0 EPOCHS: 90 LR_SCHEDULER: DECAY_EPOCHS: 30 DECAY_RATE: 0.1 MILESTONES: - 150 - 225 NAME: step MIN_LR: 3.125e-07 OPTIMIZER: BETAS: - 0.9 - 0.999 EPS: 1.0e-08 MOMENTUM: 0.9 NAME: sgd START_EPOCH: 0 USE_CHECKPOINT: false WARMUP_EPOCHS: 0 WARMUP_LR: 5.0e-07 WEIGHT_DECAY: 0.0001 ```
Inference ``` cd CoModels/cv/classification/hrnet_w18_small bash infer.sh ```
训练过程（3 epochs） * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/77448166/033c933b-97a1-41a8-8e08-8c035f34863f)
推理结果 INFO * Acc@1 72.089 Acc@5 90.502 INFO Accuracy of the network on the 6250 test images: 72.1%
iwkkk commented 9 months ago

hrnet_w18_small_v2

Training ``` cd CoModels/cv/classification/hrnet_w18_small_v2 bash train.sh ``` 训练所用超参数 ``` AMP_OPT_LEVEL: '' AUG: AUTO_AUGMENT: rand-m9-mstd0.5-inc1 COLOR_JITTER: 0.4 CUTMIX: 0.0 CUTMIX_MINMAX: null MIXUP: 0.0 MIXUP_MODE: batch MIXUP_PROB: 1.0 MIXUP_SWITCH_PROB: 0.5 RECOUNT: 1 REMODE: pixel REPROB: 0.25 BASE: - '' DATA: BATCH_SIZE: 8 CACHE_MODE: part DATASET: imagenet DATA_PATH: /data/dataset/ImageNet/extract IMG_SIZE: 224 INTERPOLATION: bicubic NUM_CLASSES: 1000 NUM_WORKERS: 4 PIN_MEMORY: true SYNTHETIC_DATA: false ZIP_MODE: false EVAL_MODE: true LOCAL_RANK: 0 MODEL: ARCH: hrnet_w18_small_v2 CHECKPOINTS: null DROP_PATH_RATE: 0.1 DROP_RATE: 0.0 LABEL_SMOOTHING: 0.1 NUM_CLASSES: 1000 PRETRAINED: true RESUME: '' OUTPUT: output/hrnet_w18_small_v2/default PRINT_FREQ: 50 SAVE_FREQ: 1 SEED: 42 TAG: default TEST: CROP: true SEQUENTIAL: false THROUGHPUT_MODE: false TRAIN: ACCUMULATION_STEPS: 0 AUTO_RESUME: false BASE_LR: 0.01 CLIP_GRAD: 5.0 EPOCHS: 90 LR_SCHEDULER: DECAY_EPOCHS: 30 DECAY_RATE: 0.1 MILESTONES: - 150 - 225 NAME: step MIN_LR: 3.125e-07 OPTIMIZER: BETAS: - 0.9 - 0.999 EPS: 1.0e-08 MOMENTUM: 0.9 NAME: sgd START_EPOCH: 0 USE_CHECKPOINT: false WARMUP_EPOCHS: 0 WARMUP_LR: 5.0e-07 WEIGHT_DECAY: 0.0001 ```
Inference ``` cd CoModels/cv/classification/hrnet_w18_small_v2 bash infer.sh ```
训练过程（2 epochs） * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/77448166/e5f49c59-e072-4bb0-bca6-99327616ffe0)
推理结果 INFO * Acc@1 74.831 Acc@5 92.277 INFO Accuracy of the network on the 6250 test images: 74.8%
iwkkk commented 9 months ago

hrnet_w30

Training ``` cd CoModels/cv/classification/hrnet_w30 bash train.sh ``` 训练所用超参数 ``` AMP_OPT_LEVEL: '' AUG: AUTO_AUGMENT: rand-m9-mstd0.5-inc1 COLOR_JITTER: 0.4 CUTMIX: 0.0 CUTMIX_MINMAX: null MIXUP: 0.0 MIXUP_MODE: batch MIXUP_PROB: 1.0 MIXUP_SWITCH_PROB: 0.5 RECOUNT: 1 REMODE: pixel REPROB: 0.25 BASE: - '' DATA: BATCH_SIZE: 8 CACHE_MODE: part DATASET: imagenet DATA_PATH: /data/dataset/ImageNet/extract IMG_SIZE: 224 INTERPOLATION: bicubic NUM_CLASSES: 1000 NUM_WORKERS: 4 PIN_MEMORY: true SYNTHETIC_DATA: false ZIP_MODE: false EVAL_MODE: true LOCAL_RANK: 0 MODEL: ARCH: hrnet_w30 CHECKPOINTS: null DROP_PATH_RATE: 0.1 DROP_RATE: 0.0 LABEL_SMOOTHING: 0.1 NUM_CLASSES: 1000 PRETRAINED: true RESUME: '' OUTPUT: output/hrnet_w30/default PRINT_FREQ: 50 SAVE_FREQ: 1 SEED: 42 TAG: default TEST: CROP: true SEQUENTIAL: false THROUGHPUT_MODE: false TRAIN: ACCUMULATION_STEPS: 0 AUTO_RESUME: false BASE_LR: 0.01 CLIP_GRAD: 5.0 EPOCHS: 90 LR_SCHEDULER: DECAY_EPOCHS: 30 DECAY_RATE: 0.1 MILESTONES: - 150 - 225 NAME: step MIN_LR: 3.125e-07 OPTIMIZER: BETAS: - 0.9 - 0.999 EPS: 1.0e-08 MOMENTUM: 0.9 NAME: sgd START_EPOCH: 0 USE_CHECKPOINT: false WARMUP_EPOCHS: 0 WARMUP_LR: 5.0e-07 WEIGHT_DECAY: 0.0001 ```
Inference ``` cd CoModels/cv/classification/hrnet_w30 bash infer.sh ```
训练过程（1 epoch） * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/77448166/faa88857-0603-48cf-9d97-375cdf3e0211)
推理结果 INFO * Acc@1 78.090 Acc@5 94.142 INFO Accuracy of the network on the 6250 test images: 78.1%
iwkkk commented 9 months ago

hrnet_w32

Training ``` cd CoModels/cv/classification/hrnet_w32 bash train.sh ``` 训练所用超参数 ``` AMP_OPT_LEVEL: '' AUG: AUTO_AUGMENT: rand-m9-mstd0.5-inc1 COLOR_JITTER: 0.4 CUTMIX: 0.0 CUTMIX_MINMAX: null MIXUP: 0.0 MIXUP_MODE: batch MIXUP_PROB: 1.0 MIXUP_SWITCH_PROB: 0.5 RECOUNT: 1 REMODE: pixel REPROB: 0.25 BASE: - '' DATA: BATCH_SIZE: 8 CACHE_MODE: part DATASET: imagenet DATA_PATH: /data/dataset/ImageNet/extract IMG_SIZE: 224 INTERPOLATION: bicubic NUM_CLASSES: 1000 NUM_WORKERS: 4 PIN_MEMORY: true SYNTHETIC_DATA: false ZIP_MODE: false EVAL_MODE: true LOCAL_RANK: 0 MODEL: ARCH: hrnet_w32 CHECKPOINTS: null DROP_PATH_RATE: 0.1 DROP_RATE: 0.0 LABEL_SMOOTHING: 0.1 NUM_CLASSES: 1000 PRETRAINED: true RESUME: '' OUTPUT: output/hrnet_w32/default PRINT_FREQ: 50 SAVE_FREQ: 1 SEED: 42 TAG: default TEST: CROP: true SEQUENTIAL: false THROUGHPUT_MODE: false TRAIN: ACCUMULATION_STEPS: 0 AUTO_RESUME: false BASE_LR: 0.01 CLIP_GRAD: 5.0 EPOCHS: 90 LR_SCHEDULER: DECAY_EPOCHS: 30 DECAY_RATE: 0.1 MILESTONES: - 150 - 225 NAME: step MIN_LR: 3.125e-07 OPTIMIZER: BETAS: - 0.9 - 0.999 EPS: 1.0e-08 MOMENTUM: 0.9 NAME: sgd START_EPOCH: 0 USE_CHECKPOINT: false WARMUP_EPOCHS: 0 WARMUP_LR: 5.0e-07 WEIGHT_DECAY: 0.0001 ```
Inference ``` cd CoModels/cv/classification/hrnet_w32 bash infer.sh ```
训练过程（1 epoch） * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/77448166/159ceda5-8b82-4df2-8fd8-068f14769080)
推理结果 INFO * Acc@1 78.197 Acc@5 94.051 INFO Accuracy of the network on the 6250 test images: 78.2%
iwkkk commented 9 months ago

hrnet_w44

Training ``` cd CoModels/cv/classification/hrnet_w44 bash train.sh ``` 训练所用超参数 ``` AMP_OPT_LEVEL: '' AUG: AUTO_AUGMENT: rand-m9-mstd0.5-inc1 COLOR_JITTER: 0.4 CUTMIX: 0.0 CUTMIX_MINMAX: null MIXUP: 0.0 MIXUP_MODE: batch MIXUP_PROB: 1.0 MIXUP_SWITCH_PROB: 0.5 RECOUNT: 1 REMODE: pixel REPROB: 0.25 BASE: - '' DATA: BATCH_SIZE: 16 CACHE_MODE: part DATASET: imagenet DATA_PATH: /data/dataset/ImageNet/extract IMG_SIZE: 224 INTERPOLATION: bicubic NUM_CLASSES: 1000 NUM_WORKERS: 8 PIN_MEMORY: true SYNTHETIC_DATA: false ZIP_MODE: false EVAL_MODE: true LOCAL_RANK: 0 MODEL: ARCH: hrnet_w44 CHECKPOINTS: null DROP_PATH_RATE: 0.1 DROP_RATE: 0.0 LABEL_SMOOTHING: 0.1 NUM_CLASSES: 1000 PRETRAINED: true RESUME: '' OUTPUT: output/hrnet_w44/default PRINT_FREQ: 50 SAVE_FREQ: 1 SEED: 42 TAG: default TEST: CROP: true SEQUENTIAL: false THROUGHPUT_MODE: false TRAIN: ACCUMULATION_STEPS: 0 AUTO_RESUME: false BASE_LR: 0.01 CLIP_GRAD: 5.0 EPOCHS: 90 LR_SCHEDULER: DECAY_EPOCHS: 30 DECAY_RATE: 0.1 MILESTONES: - 150 - 225 NAME: step MIN_LR: 6.25e-07 OPTIMIZER: BETAS: - 0.9 - 0.999 EPS: 1.0e-08 MOMENTUM: 0.9 NAME: sgd START_EPOCH: 0 USE_CHECKPOINT: false WARMUP_EPOCHS: 0 WARMUP_LR: 5.0e-07 WEIGHT_DECAY: 0.0001 ```
Inference ``` cd CoModels/cv/classification/hrnet_w44 bash infer.sh ```
训练过程（2 epochs） * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/77448166/4a2f33ed-3399-4f36-bb01-97012565ff06)
推理结果 INFO * Acc@1 78.682 Acc@5 94.244 INFO Accuracy of the network on the 3125 test images: 78.7%
iwkkk commented 9 months ago

hrnet_w40

Training ``` cd CoModels/cv/classification/hrnet_w40 bash train.sh ``` 训练所用超参数 ``` AMP_OPT_LEVEL: '' AUG: AUTO_AUGMENT: rand-m9-mstd0.5-inc1 COLOR_JITTER: 0.4 CUTMIX: 0.0 CUTMIX_MINMAX: null MIXUP: 0.0 MIXUP_MODE: batch MIXUP_PROB: 1.0 MIXUP_SWITCH_PROB: 0.5 RECOUNT: 1 REMODE: pixel REPROB: 0.25 BASE: - '' DATA: BATCH_SIZE: 16 CACHE_MODE: part DATASET: imagenet DATA_PATH: /data/dataset/ImageNet/extract IMG_SIZE: 224 INTERPOLATION: bicubic NUM_CLASSES: 1000 NUM_WORKERS: 8 PIN_MEMORY: true SYNTHETIC_DATA: false ZIP_MODE: false EVAL_MODE: true LOCAL_RANK: 0 MODEL: ARCH: hrnet_w40 CHECKPOINTS: null DROP_PATH_RATE: 0.1 DROP_RATE: 0.0 LABEL_SMOOTHING: 0.1 NUM_CLASSES: 1000 PRETRAINED: true RESUME: '' OUTPUT: output/hrnet_w40/default PRINT_FREQ: 50 SAVE_FREQ: 1 SEED: 42 TAG: default TEST: CROP: true SEQUENTIAL: false THROUGHPUT_MODE: false TRAIN: ACCUMULATION_STEPS: 0 AUTO_RESUME: false BASE_LR: 0.01 CLIP_GRAD: 5.0 EPOCHS: 90 LR_SCHEDULER: DECAY_EPOCHS: 30 DECAY_RATE: 0.1 MILESTONES: - 150 - 225 NAME: step MIN_LR: 6.25e-07 OPTIMIZER: BETAS: - 0.9 - 0.999 EPS: 1.0e-08 MOMENTUM: 0.9 NAME: sgd START_EPOCH: 0 USE_CHECKPOINT: false WARMUP_EPOCHS: 0 WARMUP_LR: 5.0e-07 WEIGHT_DECAY: 0.0001 ```
Inference ``` cd CoModels/cv/classification/hrnet_w40 bash infer.sh ```
训练过程（1 epoch） * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/77448166/f79c7d75-ebc8-45dc-a237-60df8b445249)
推理结果 INFO * Acc@1 78.648 Acc@5 94.391 INFO Accuracy of the network on the 3125 test images: 78.6%
iwkkk commented 9 months ago

hrnet_w48

Training ``` cd CoModels/cv/classification/hrnet_w48 bash train.sh ``` 训练所用超参数 ``` AMP_OPT_LEVEL: '' AUG: AUTO_AUGMENT: rand-m9-mstd0.5-inc1 COLOR_JITTER: 0.4 CUTMIX: 0.0 CUTMIX_MINMAX: null MIXUP: 0.0 MIXUP_MODE: batch MIXUP_PROB: 1.0 MIXUP_SWITCH_PROB: 0.5 RECOUNT: 1 REMODE: pixel REPROB: 0.25 BASE: - '' DATA: BATCH_SIZE: 16 CACHE_MODE: part DATASET: imagenet DATA_PATH: /data/dataset/ImageNet/extract IMG_SIZE: 224 INTERPOLATION: bicubic NUM_CLASSES: 1000 NUM_WORKERS: 8 PIN_MEMORY: true SYNTHETIC_DATA: false ZIP_MODE: false EVAL_MODE: true LOCAL_RANK: 0 MODEL: ARCH: hrnet_w48 CHECKPOINTS: null DROP_PATH_RATE: 0.1 DROP_RATE: 0.0 LABEL_SMOOTHING: 0.1 NUM_CLASSES: 1000 PRETRAINED: true RESUME: '' OUTPUT: output/hrnet_w48/default PRINT_FREQ: 50 SAVE_FREQ: 1 SEED: 42 TAG: default TEST: CROP: true SEQUENTIAL: false THROUGHPUT_MODE: false TRAIN: ACCUMULATION_STEPS: 0 AUTO_RESUME: false BASE_LR: 0.01 CLIP_GRAD: 5.0 EPOCHS: 90 LR_SCHEDULER: DECAY_EPOCHS: 30 DECAY_RATE: 0.1 MILESTONES: - 150 - 225 NAME: step MIN_LR: 6.25e-07 OPTIMIZER: BETAS: - 0.9 - 0.999 EPS: 1.0e-08 MOMENTUM: 0.9 NAME: sgd START_EPOCH: 0 USE_CHECKPOINT: false WARMUP_EPOCHS: 0 WARMUP_LR: 5.0e-07 WEIGHT_DECAY: 0.0001 ```
Inference ``` cd CoModels/cv/classification/hrnet_w48 bash infer.sh ```
训练过程（1 epoch） * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/77448166/ee83d05f-58a3-4b8e-8dda-983ed745593c)
推理结果 INFO * Acc@1 78.995 Acc@5 94.353 INFO Accuracy of the network on the 3125 test images: 79.0%
iwkkk commented 9 months ago

hrnet_w64

Training ``` cd CoModels/cv/classification/hrnet_w64 bash train.sh ``` 训练所用超参数 ``` AMP_OPT_LEVEL: '' AUG: AUTO_AUGMENT: rand-m9-mstd0.5-inc1 COLOR_JITTER: 0.4 CUTMIX: 0.0 CUTMIX_MINMAX: null MIXUP: 0.0 MIXUP_MODE: batch MIXUP_PROB: 1.0 MIXUP_SWITCH_PROB: 0.5 RECOUNT: 1 REMODE: pixel REPROB: 0.25 BASE: - '' DATA: BATCH_SIZE: 16 CACHE_MODE: part DATASET: imagenet DATA_PATH: /data/dataset/ImageNet/extract IMG_SIZE: 224 INTERPOLATION: bicubic NUM_CLASSES: 1000 NUM_WORKERS: 8 PIN_MEMORY: true SYNTHETIC_DATA: false ZIP_MODE: false EVAL_MODE: true LOCAL_RANK: 0 MODEL: ARCH: hrnet_w64 CHECKPOINTS: null DROP_PATH_RATE: 0.1 DROP_RATE: 0.0 LABEL_SMOOTHING: 0.1 NUM_CLASSES: 1000 PRETRAINED: true RESUME: '' OUTPUT: output/hrnet_w64/default PRINT_FREQ: 50 SAVE_FREQ: 1 SEED: 42 TAG: default TEST: CROP: true SEQUENTIAL: false THROUGHPUT_MODE: false TRAIN: ACCUMULATION_STEPS: 0 AUTO_RESUME: false BASE_LR: 0.01 CLIP_GRAD: 5.0 EPOCHS: 90 LR_SCHEDULER: DECAY_EPOCHS: 30 DECAY_RATE: 0.1 MILESTONES: - 150 - 225 NAME: step MIN_LR: 6.25e-07 OPTIMIZER: BETAS: - 0.9 - 0.999 EPS: 1.0e-08 MOMENTUM: 0.9 NAME: sgd START_EPOCH: 0 USE_CHECKPOINT: false WARMUP_EPOCHS: 0 WARMUP_LR: 5.0e-07 WEIGHT_DECAY: 0.0001 ```
Inference ``` cd CoModels/cv/classification/hrnet_w64 bash infer.sh ```
训练过程（1 epoch） * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/77448166/72f26c86-f79b-46aa-81b8-6edb5cb918b1)
推理结果 INFO * Acc@1 79.233 Acc@5 94.562 INFO Accuracy of the network on the 3125 test images: 79.2%
iwkkk commented 9 months ago

dla34

Training ``` cd CoModels/cv/classification/dla34 bash train.sh ``` 训练所用超参数 ``` AMP_OPT_LEVEL: '' AUG: AUTO_AUGMENT: rand-m9-mstd0.5-inc1 COLOR_JITTER: 0.4 CUTMIX: 0.0 CUTMIX_MINMAX: null MIXUP: 0.0 MIXUP_MODE: batch MIXUP_PROB: 1.0 MIXUP_SWITCH_PROB: 0.5 RECOUNT: 1 REMODE: pixel REPROB: 0.25 BASE: - '' DATA: BATCH_SIZE: 16 CACHE_MODE: part DATASET: imagenet DATA_PATH: /data/dataset/ImageNet/extract IMG_SIZE: 224 INTERPOLATION: bicubic NUM_CLASSES: 1000 NUM_WORKERS: 8 PIN_MEMORY: true SYNTHETIC_DATA: false ZIP_MODE: false EVAL_MODE: true LOCAL_RANK: 0 MODEL: ARCH: dla34 CHECKPOINTS: null DROP_PATH_RATE: 0.1 DROP_RATE: 0.0 LABEL_SMOOTHING: 0.1 NUM_CLASSES: 1000 PRETRAINED: true RESUME: '' OUTPUT: output/dla34/default PRINT_FREQ: 50 SAVE_FREQ: 1 SEED: 42 TAG: default TEST: CROP: true SEQUENTIAL: false THROUGHPUT_MODE: false TRAIN: ACCUMULATION_STEPS: 0 AUTO_RESUME: false BASE_LR: 0.001 CLIP_GRAD: 5.0 EPOCHS: 90 LR_SCHEDULER: DECAY_EPOCHS: 30 DECAY_RATE: 0.1 MILESTONES: - 150 - 225 NAME: step MIN_LR: 6.25e-07 OPTIMIZER: BETAS: - 0.9 - 0.999 EPS: 1.0e-08 MOMENTUM: 0.9 NAME: sgd START_EPOCH: 0 USE_CHECKPOINT: false WARMUP_EPOCHS: 0 WARMUP_LR: 5.0e-07 WEIGHT_DECAY: 0.0001 ```
Inference ``` cd CoModels/cv/classification/dla34 bash infer.sh ```
训练过程（3 epochs） * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/77448166/80cfaa51-c576-4ee8-98d1-7400e8afb9ab)
推理结果 INFO * Acc@1 74.488 Acc@5 92.025 INFO Accuracy of the network on the 3125 test images: 74.5%
iwkkk commented 9 months ago

dla46_c

Training ``` cd CoModels/cv/classification/dla46_c bash train.sh ``` 训练所用超参数 ``` AMP_OPT_LEVEL: '' AUG: AUTO_AUGMENT: rand-m9-mstd0.5-inc1 COLOR_JITTER: 0.4 CUTMIX: 0.0 CUTMIX_MINMAX: null MIXUP: 0.0 MIXUP_MODE: batch MIXUP_PROB: 1.0 MIXUP_SWITCH_PROB: 0.5 RECOUNT: 1 REMODE: pixel REPROB: 0.25 BASE: - '' DATA: BATCH_SIZE: 16 CACHE_MODE: part DATASET: imagenet DATA_PATH: /data/dataset/ImageNet/extract IMG_SIZE: 224 INTERPOLATION: bicubic NUM_CLASSES: 1000 NUM_WORKERS: 8 PIN_MEMORY: true SYNTHETIC_DATA: false ZIP_MODE: false EVAL_MODE: true LOCAL_RANK: 0 MODEL: ARCH: dla46_c CHECKPOINTS: null DROP_PATH_RATE: 0.1 DROP_RATE: 0.0 LABEL_SMOOTHING: 0.1 NUM_CLASSES: 1000 PRETRAINED: true RESUME: '' OUTPUT: output/dla46_c/default PRINT_FREQ: 50 SAVE_FREQ: 1 SEED: 42 TAG: default TEST: CROP: true SEQUENTIAL: false THROUGHPUT_MODE: false TRAIN: ACCUMULATION_STEPS: 0 AUTO_RESUME: false BASE_LR: 0.001 CLIP_GRAD: 5.0 EPOCHS: 90 LR_SCHEDULER: DECAY_EPOCHS: 30 DECAY_RATE: 0.1 MILESTONES: - 150 - 225 NAME: step MIN_LR: 6.25e-07 OPTIMIZER: BETAS: - 0.9 - 0.999 EPS: 1.0e-08 MOMENTUM: 0.9 NAME: sgd START_EPOCH: 0 USE_CHECKPOINT: false WARMUP_EPOCHS: 0 WARMUP_LR: 5.0e-07 WEIGHT_DECAY: 0.0001 ```
Inference ``` cd CoModels/cv/classification/dla46_c bash infer.sh ```
训练过程（2 epochs） * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/77448166/478516ad-0a7b-4b35-b388-9c2056d9000d)
推理结果 INFO * Acc@1 64.493 Acc@5 86.099 INFO Accuracy of the network on the 3125 test images: 64.5%
iwkkk commented 9 months ago

dla46x_c

Training ``` cd CoModels/cv/classification/dla46x_c bash train.sh ``` 训练所用超参数 ``` AMP_OPT_LEVEL: '' AUG: AUTO_AUGMENT: rand-m9-mstd0.5-inc1 COLOR_JITTER: 0.4 CUTMIX: 0.0 CUTMIX_MINMAX: null MIXUP: 0.0 MIXUP_MODE: batch MIXUP_PROB: 1.0 MIXUP_SWITCH_PROB: 0.5 RECOUNT: 1 REMODE: pixel REPROB: 0.25 BASE: - '' DATA: BATCH_SIZE: 16 CACHE_MODE: part DATASET: imagenet DATA_PATH: /data/dataset/ImageNet/extract IMG_SIZE: 224 INTERPOLATION: bicubic NUM_CLASSES: 1000 NUM_WORKERS: 8 PIN_MEMORY: true SYNTHETIC_DATA: false ZIP_MODE: false EVAL_MODE: true LOCAL_RANK: 0 MODEL: ARCH: dla46x_c CHECKPOINTS: null DROP_PATH_RATE: 0.1 DROP_RATE: 0.0 LABEL_SMOOTHING: 0.1 NUM_CLASSES: 1000 PRETRAINED: true RESUME: '' OUTPUT: output/dla46x_c/default PRINT_FREQ: 50 SAVE_FREQ: 1 SEED: 42 TAG: default TEST: CROP: true SEQUENTIAL: false THROUGHPUT_MODE: false TRAIN: ACCUMULATION_STEPS: 0 AUTO_RESUME: false BASE_LR: 0.001 CLIP_GRAD: 5.0 EPOCHS: 90 LR_SCHEDULER: DECAY_EPOCHS: 30 DECAY_RATE: 0.1 MILESTONES: - 150 - 225 NAME: step MIN_LR: 6.25e-07 OPTIMIZER: BETAS: - 0.9 - 0.999 EPS: 1.0e-08 MOMENTUM: 0.9 NAME: sgd START_EPOCH: 0 USE_CHECKPOINT: false WARMUP_EPOCHS: 0 WARMUP_LR: 5.0e-07 WEIGHT_DECAY: 0.0001 ```
Inference ``` cd CoModels/cv/classification/dla46x_c bash infer.sh ```
训练过程（3 epochs） * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/77448166/2ebd7794-643b-4ba0-8c0e-84354ed9234c)
推理结果 INFO * Acc@1 65.656 Acc@5 86.662 INFO Accuracy of the network on the 3125 test images: 65.7%
iwkkk commented 9 months ago

dla60

Training ``` cd CoModels/cv/classification/dla60 bash train.sh ``` 训练所用超参数 ``` AMP_OPT_LEVEL: '' AUG: AUTO_AUGMENT: rand-m9-mstd0.5-inc1 COLOR_JITTER: 0.4 CUTMIX: 0.0 CUTMIX_MINMAX: null MIXUP: 0.0 MIXUP_MODE: batch MIXUP_PROB: 1.0 MIXUP_SWITCH_PROB: 0.5 RECOUNT: 1 REMODE: pixel REPROB: 0.25 BASE: - '' DATA: BATCH_SIZE: 16 CACHE_MODE: part DATASET: imagenet DATA_PATH: /data/dataset/ImageNet/extract IMG_SIZE: 224 INTERPOLATION: bicubic NUM_CLASSES: 1000 NUM_WORKERS: 8 PIN_MEMORY: true SYNTHETIC_DATA: false ZIP_MODE: false EVAL_MODE: true LOCAL_RANK: 0 MODEL: ARCH: dla60 CHECKPOINTS: null DROP_PATH_RATE: 0.1 DROP_RATE: 0.0 LABEL_SMOOTHING: 0.1 NUM_CLASSES: 1000 PRETRAINED: true RESUME: '' OUTPUT: output/dla60/default PRINT_FREQ: 50 SAVE_FREQ: 1 SEED: 42 TAG: default TEST: CROP: true SEQUENTIAL: false THROUGHPUT_MODE: false TRAIN: ACCUMULATION_STEPS: 0 AUTO_RESUME: false BASE_LR: 0.001 CLIP_GRAD: 5.0 EPOCHS: 90 LR_SCHEDULER: DECAY_EPOCHS: 30 DECAY_RATE: 0.1 MILESTONES: - 150 - 225 NAME: step MIN_LR: 6.25e-07 OPTIMIZER: BETAS: - 0.9 - 0.999 EPS: 1.0e-08 MOMENTUM: 0.9 NAME: sgd START_EPOCH: 0 USE_CHECKPOINT: false WARMUP_EPOCHS: 0 WARMUP_LR: 5.0e-07 WEIGHT_DECAY: 0.0001 ```
Inference ``` cd CoModels/cv/classification/dla60 bash infer.sh ```
训练过程（1 epoch） * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/77448166/8c312ad6-4845-416d-82b3-894af976eb39)
推理结果 INFO * Acc@1 76.824 Acc@5 93.188 INFO Accuracy of the network on the 3125 test images: 76.8%
iwkkk commented 9 months ago

dla60x

Training ``` cd CoModels/cv/classification/dla60x bash train.sh ``` 训练所用超参数 ``` AMP_OPT_LEVEL: '' AUG: AUTO_AUGMENT: rand-m9-mstd0.5-inc1 COLOR_JITTER: 0.4 CUTMIX: 0.0 CUTMIX_MINMAX: null MIXUP: 0.0 MIXUP_MODE: batch MIXUP_PROB: 1.0 MIXUP_SWITCH_PROB: 0.5 RECOUNT: 1 REMODE: pixel REPROB: 0.25 BASE: - '' DATA: BATCH_SIZE: 16 CACHE_MODE: part DATASET: imagenet DATA_PATH: /data/dataset/ImageNet/extract IMG_SIZE: 224 INTERPOLATION: bicubic NUM_CLASSES: 1000 NUM_WORKERS: 8 PIN_MEMORY: true SYNTHETIC_DATA: false ZIP_MODE: false EVAL_MODE: true LOCAL_RANK: 0 MODEL: ARCH: dla60x CHECKPOINTS: null DROP_PATH_RATE: 0.1 DROP_RATE: 0.0 LABEL_SMOOTHING: 0.1 NUM_CLASSES: 1000 PRETRAINED: true RESUME: '' OUTPUT: output/dla60x/default PRINT_FREQ: 50 SAVE_FREQ: 1 SEED: 42 TAG: default TEST: CROP: true SEQUENTIAL: false THROUGHPUT_MODE: false TRAIN: ACCUMULATION_STEPS: 0 AUTO_RESUME: false BASE_LR: 0.001 CLIP_GRAD: 5.0 EPOCHS: 90 LR_SCHEDULER: DECAY_EPOCHS: 30 DECAY_RATE: 0.1 MILESTONES: - 150 - 225 NAME: step MIN_LR: 6.25e-07 OPTIMIZER: BETAS: - 0.9 - 0.999 EPS: 1.0e-08 MOMENTUM: 0.9 NAME: sgd START_EPOCH: 0 USE_CHECKPOINT: false WARMUP_EPOCHS: 0 WARMUP_LR: 5.0e-07 WEIGHT_DECAY: 0.0001 ```
Inference ``` cd CoModels/cv/classification/dla60x bash infer.sh ```
训练过程（1 epoch） * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/77448166/66bb2f92-0c8f-4f8c-9207-6ad279d70fb7)
推理结果 INFO * Acc@1 78.070 Acc@5 93.958 INFO Accuracy of the network on the 3125 test images: 78.1%
iwkkk commented 9 months ago

dla60x_c

Training ``` cd CoModels/cv/classification/dla60x_c bash train.sh ``` 训练所用超参数 ``` AMP_OPT_LEVEL: '' AUG: AUTO_AUGMENT: rand-m9-mstd0.5-inc1 COLOR_JITTER: 0.4 CUTMIX: 0.0 CUTMIX_MINMAX: null MIXUP: 0.0 MIXUP_MODE: batch MIXUP_PROB: 1.0 MIXUP_SWITCH_PROB: 0.5 RECOUNT: 1 REMODE: pixel REPROB: 0.25 BASE: - '' DATA: BATCH_SIZE: 16 CACHE_MODE: part DATASET: imagenet DATA_PATH: /data/dataset/ImageNet/extract IMG_SIZE: 224 INTERPOLATION: bicubic NUM_CLASSES: 1000 NUM_WORKERS: 8 PIN_MEMORY: true SYNTHETIC_DATA: false ZIP_MODE: false EVAL_MODE: true LOCAL_RANK: 0 MODEL: ARCH: dla60x_c CHECKPOINTS: null DROP_PATH_RATE: 0.1 DROP_RATE: 0.0 LABEL_SMOOTHING: 0.1 NUM_CLASSES: 1000 PRETRAINED: true RESUME: '' OUTPUT: output/dla60x_c/default PRINT_FREQ: 50 SAVE_FREQ: 1 SEED: 42 TAG: default TEST: CROP: true SEQUENTIAL: false THROUGHPUT_MODE: false TRAIN: ACCUMULATION_STEPS: 0 AUTO_RESUME: false BASE_LR: 0.001 CLIP_GRAD: 5.0 EPOCHS: 90 LR_SCHEDULER: DECAY_EPOCHS: 30 DECAY_RATE: 0.1 MILESTONES: - 150 - 225 NAME: step MIN_LR: 6.25e-07 OPTIMIZER: BETAS: - 0.9 - 0.999 EPS: 1.0e-08 MOMENTUM: 0.9 NAME: sgd START_EPOCH: 0 USE_CHECKPOINT: false WARMUP_EPOCHS: 0 WARMUP_LR: 5.0e-07 WEIGHT_DECAY: 0.0001 ```
Inference ``` cd CoModels/cv/classification/dla60x_c bash infer.sh ```
训练过程（1 epoch） * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/77448166/fbab49fe-41b8-4f91-b788-d02afb2258ea)
推理结果 INFO * Acc@1 67.549 Acc@5 88.213 INFO Accuracy of the network on the 3125 test images: 67.5%
iwkkk commented 9 months ago

dla102

Training ``` cd CoModels/cv/classification/dla102 bash train.sh ``` 训练所用超参数 ``` AMP_OPT_LEVEL: '' AUG: AUTO_AUGMENT: rand-m9-mstd0.5-inc1 COLOR_JITTER: 0.4 CUTMIX: 0.0 CUTMIX_MINMAX: null MIXUP: 0.0 MIXUP_MODE: batch MIXUP_PROB: 1.0 MIXUP_SWITCH_PROB: 0.5 RECOUNT: 1 REMODE: pixel REPROB: 0.25 BASE: - '' DATA: BATCH_SIZE: 16 CACHE_MODE: part DATASET: imagenet DATA_PATH: /data/dataset/ImageNet/extract IMG_SIZE: 224 INTERPOLATION: bicubic NUM_CLASSES: 1000 NUM_WORKERS: 8 PIN_MEMORY: true SYNTHETIC_DATA: false ZIP_MODE: false EVAL_MODE: true LOCAL_RANK: 0 MODEL: ARCH: dla102 CHECKPOINTS: null DROP_PATH_RATE: 0.1 DROP_RATE: 0.0 LABEL_SMOOTHING: 0.1 NUM_CLASSES: 1000 PRETRAINED: true RESUME: '' OUTPUT: output/dla102/default PRINT_FREQ: 50 SAVE_FREQ: 1 SEED: 42 TAG: default TEST: CROP: true SEQUENTIAL: false THROUGHPUT_MODE: false TRAIN: ACCUMULATION_STEPS: 0 AUTO_RESUME: false BASE_LR: 0.001 CLIP_GRAD: 5.0 EPOCHS: 90 LR_SCHEDULER: DECAY_EPOCHS: 30 DECAY_RATE: 0.1 MILESTONES: - 150 - 225 NAME: step MIN_LR: 6.25e-07 OPTIMIZER: BETAS: - 0.9 - 0.999 EPS: 1.0e-08 MOMENTUM: 0.9 NAME: sgd START_EPOCH: 0 USE_CHECKPOINT: false WARMUP_EPOCHS: 0 WARMUP_LR: 5.0e-07 WEIGHT_DECAY: 0.0001 ```
Inference ``` cd CoModels/cv/classification/dla102 bash infer.sh ```
训练过程（1 epoch） * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/77448166/f4cb04b9-fd8f-46f2-a8a7-7cfc73bde68e)
推理结果 INFO * Acc@1 77.711 Acc@5 93.788 INFO Accuracy of the network on the 3125 test images: 77.7%
iwkkk commented 9 months ago

dla102x

Training ``` cd CoModels/cv/classification/dla102x bash train.sh ``` 训练所用超参数 ``` AMP_OPT_LEVEL: '' AUG: AUTO_AUGMENT: rand-m9-mstd0.5-inc1 COLOR_JITTER: 0.4 CUTMIX: 0.0 CUTMIX_MINMAX: null MIXUP: 0.0 MIXUP_MODE: batch MIXUP_PROB: 1.0 MIXUP_SWITCH_PROB: 0.5 RECOUNT: 1 REMODE: pixel REPROB: 0.25 BASE: - '' DATA: BATCH_SIZE: 16 CACHE_MODE: part DATASET: imagenet DATA_PATH: /data/dataset/ImageNet/extract IMG_SIZE: 224 INTERPOLATION: bicubic NUM_CLASSES: 1000 NUM_WORKERS: 8 PIN_MEMORY: true SYNTHETIC_DATA: false ZIP_MODE: false EVAL_MODE: true LOCAL_RANK: 0 MODEL: ARCH: dla102x CHECKPOINTS: null DROP_PATH_RATE: 0.1 DROP_RATE: 0.0 LABEL_SMOOTHING: 0.1 NUM_CLASSES: 1000 PRETRAINED: true RESUME: '' OUTPUT: output/dla102x/default PRINT_FREQ: 50 SAVE_FREQ: 1 SEED: 42 TAG: default TEST: CROP: true SEQUENTIAL: false THROUGHPUT_MODE: false TRAIN: ACCUMULATION_STEPS: 0 AUTO_RESUME: false BASE_LR: 0.001 CLIP_GRAD: 5.0 EPOCHS: 90 LR_SCHEDULER: DECAY_EPOCHS: 30 DECAY_RATE: 0.1 MILESTONES: - 150 - 225 NAME: step MIN_LR: 6.25e-07 OPTIMIZER: BETAS: - 0.9 - 0.999 EPS: 1.0e-08 MOMENTUM: 0.9 NAME: sgd START_EPOCH: 0 USE_CHECKPOINT: false WARMUP_EPOCHS: 0 WARMUP_LR: 5.0e-07 WEIGHT_DECAY: 0.0001 ```
Inference ``` cd CoModels/cv/classification/dla102x bash infer.sh ```
训练过程（2 epochs） * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/77448166/c866eb78-1c52-4af2-9580-5ed86c8d6050)
推理结果 INFO * Acc@1 78.283 Acc@5 94.101 INFO Accuracy of the network on the 3125 test images: 78.3%
Drlifei commented 9 months ago

deit_large_patch16_LS_224

cd CoModels/cv/classification/deit_large_patch16_LS_224
bash train.sh
训练所用超参数 
DATA:
  BATCH_SIZE: 32
  DATASET: imagenet
  DATA_PATH: /data/dataset/ImageNet/extract
  IMG_SIZE: 224

MODEL:
  PRETRAINED: True
  LABEL_SMOOTHING: 0.11

TRAIN:
  START_EPOCH: 0
  EPOCHS: 90
  WARMUP_EPOCHS: 30
  WEIGHT_DECAY: 0.3
  BASE_LR: 1e-4
  WARMUP_LR: 5e-7

  LR_SCHEDULER:
    NAME: step

  OPTIMIZER:
    NAME: sgd
    MOMENTUM: 0.9

Inference ``` cd CoModels/cv/classification/deit_large_patch16_LS_224 bash infer.sh ```
训练过程 * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/144590379/253d98dc-1055-4bc1-a3cf-f49f2f0c72c4)
推理结果 ![image](https://github.com/Oneflow-Inc/CoModels/assets/144590379/8e48086f-8925-4245-a0ab-f6ce9b25f50e)
Drlifei commented 9 months ago

deit_small_patch16_LS_224

cd CoModels/cv/classification/deit_small_patch16_LS_224
bash train.sh
训练所用超参数 
DATA:
  BATCH_SIZE: 32
  DATASET: imagenet
  DATA_PATH: /data/dataset/ImageNet/extract
  IMG_SIZE: 224

MODEL:
  PRETRAINED: True
  LABEL_SMOOTHING: 0.11

TRAIN:
  START_EPOCH: 0
  EPOCHS: 90
  WARMUP_EPOCHS: 30
  WEIGHT_DECAY: 0.3
  BASE_LR: 1e-4
  WARMUP_LR: 5e-7

  LR_SCHEDULER:
    NAME: step

  OPTIMIZER:
    NAME: sgd
    MOMENTUM: 0.9

Inference ``` cd CoModels/cv/classification/deit_small_patch16_LS_224 bash infer.sh ```
训练过程 * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/144590379/39eb3215-9532-4864-9239-d4cfb7914b40)
推理结果 ![image](https://github.com/Oneflow-Inc/CoModels/assets/144590379/c2814fff-cdca-443d-83e6-5bb46dd150f3)
Drlifei commented 9 months ago

deit_large_patch16_LS_384

cd CoModels/cv/classification/deit_large_patch16_LS_384
bash train.sh
训练所用超参数 
DATA:
  BATCH_SIZE: 32
  DATASET: imagenet
  DATA_PATH: /data/dataset/ImageNet/extract
  IMG_SIZE: 224

MODEL:
  PRETRAINED: True
  LABEL_SMOOTHING: 0.11

TRAIN:
  START_EPOCH: 0
  EPOCHS: 90
  WARMUP_EPOCHS: 30
  WEIGHT_DECAY: 0.3
  BASE_LR: 1e-4
  WARMUP_LR: 5e-7

  LR_SCHEDULER:
    NAME: step

  OPTIMIZER:
    NAME: sgd
    MOMENTUM: 0.9

Inference ``` cd CoModels/cv/classification/deit_large_patch16_LS_384 bash infer.sh ```
训练过程 * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/144590379/20554506-9b0b-4f98-8eb1-3f90e1888b52)
推理结果 ![image](https://github.com/Oneflow-Inc/CoModels/assets/144590379/ba254a05-aa2f-4dff-b33e-db8cc02b1c2e)
Drlifei commented 9 months ago

deit_small_patch16_LS_384

cd CoModels/cv/classification/deit_small_patch16_LS_384
bash train.sh
训练所用超参数 
DATA:
  BATCH_SIZE: 32
  DATASET: imagenet
  DATA_PATH: /data/dataset/ImageNet/extract
  IMG_SIZE: 224

MODEL:
  PRETRAINED: True
  LABEL_SMOOTHING: 0.11

TRAIN:
  START_EPOCH: 0
  EPOCHS: 90
  WARMUP_EPOCHS: 30
  WEIGHT_DECAY: 0.3
  BASE_LR: 1e-4
  WARMUP_LR: 5e-7

  LR_SCHEDULER:
    NAME: step

  OPTIMIZER:
    NAME: sgd
    MOMENTUM: 0.9

Inference ``` cd CoModels/cv/classification/deit_small_patch16_LS_384 bash infer.sh ```
训练过程 * 训练日志 ： ![企业微信截图_17004598591082](https://github.com/Oneflow-Inc/CoModels/assets/144590379/1846c484-795c-4387-bf5b-df147986dc61) ![image](https://github.com/Oneflow-Inc/CoModels/assets/144590379/9d9e6b2e-7dc8-4675-b0ce-b414baba68a5)
推理结果 ![image](https://github.com/Oneflow-Inc/CoModels/assets/144590379/9d9e6b2e-7dc8-4675-b0ce-b414baba68a5)
akeeei commented 9 months ago

Fan-ViT-small

cd CoModels/cv/classification/fan_vit_small
bash train.sh
训练所用超参数 
DATA:
  BATCH_SIZE: 64
  DATASET: imagenet
  DATA_PATH: /data/dataset/ImageNet/extract
  IMG_SIZE: 224

MODEL:
  PRETRAINED: True
  LABEL_SMOOTHING: 0.11

TRAIN:
  START_EPOCH: 0
  EPOCHS: 90
  WARMUP_EPOCHS: 30
  WEIGHT_DECAY: 0.3
  BASE_LR: 1e-4
  WARMUP_LR: 5e-7

  LR_SCHEDULER:
    NAME: step

  OPTIMIZER:
    NAME: sgd
    MOMENTUM: 0.9

Inference ``` cd CoModels/cv/classification/fan_vit_small bash infer.sh ```
训练过程 * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/98879022/92f9e1c8-779a-44a4-836d-6e979f28ced4) * 训练结果 ： ``` INFO * Acc@1 82.238 Acc@5 96.037 INFO Accuracy of the network on the 196 test images: 82.2% INFO Max accuracy: 82.24% INFO Training time 2:23:30 ```
推理结果 ``` INFO * Acc@1 82.471 Acc@5 96.216 INFO Accuracy of the network on the 1563 test images: 82.5% INFO throughput averaged with 30 times INFO batch_size 32 throughput 217.21194210108126 ```
akeeei commented 9 months ago

Fan-ViT-tiny

cd CoModels/cv/classification/fan_vit_tiny
bash train.sh
训练所用超参数 
DATA:
  BATCH_SIZE: 32
  DATASET: imagenet
  DATA_PATH: /data/dataset/ImageNet/extract
  IMG_SIZE: 224

MODEL:
  PRETRAINED: True
  LABEL_SMOOTHING: 0.11

TRAIN:
  START_EPOCH: 0
  EPOCHS: 90
  WARMUP_EPOCHS: 30
  WEIGHT_DECAY: 0.3
  BASE_LR: 1e-4
  WARMUP_LR: 5e-7

  LR_SCHEDULER:
    NAME: step

  OPTIMIZER:
    NAME: sgd
    MOMENTUM: 0.9

Inference ``` cd CoModels/cv/classification/fan_vit_tiny bash infer.sh ```
训练过程 * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/98879022/fd9506c2-85c5-48f8-9a66-4dd03c853bd1) * 训练结果 ： ``` INFO * Acc@1 79.013 Acc@5 94.487 INFO Accuracy of the network on the 391 test images: 79.0% INFO Max accuracy: 79.01% INFO Training time 3:24:50 ```
推理结果 ``` INFO * Acc@1 79.122 Acc@5 94.610 INFO Accuracy of the network on the 1563 test images: 79.1% INFO throughput averaged with 30 times INFO batch_size 32 throughput 357.83025676395147 ```
akeeei commented 9 months ago

fan_hybrid_base_in22k_1k

cd CoModels/cv/classification/fan_hybrid_base_in22k_1k
bash train.sh
训练所用超参数 
DATA:
  BATCH_SIZE: 32
  DATASET: imagenet
  DATA_PATH: /data/dataset/ImageNet/extract
  IMG_SIZE: 224

MODEL:
  PRETRAINED: True
  LABEL_SMOOTHING: 0.11

TRAIN:
  START_EPOCH: 0
  EPOCHS: 90
  WARMUP_EPOCHS: 30
  WEIGHT_DECAY: 0.3
  BASE_LR: 1e-4
  WARMUP_LR: 5e-7

  LR_SCHEDULER:
    NAME: step

  OPTIMIZER:
    NAME: sgd
    MOMENTUM: 0.9

Inference ``` cd CoModels/cv/classification/fan_hybrid_base_in22k_1k bash infer.sh ```
训练过程 * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/98879022/d9094f07-4798-4b43-9aaa-ec5ec06e2447) * 训练结果 ： ``` INFO * Acc@1 85.136 Acc@5 97.407 INFO Accuracy of the network on the 391 test images: 85.1% INFO Max accuracy: 85.14% INFO Training time 1:44:25 ```
推理结果 ``` INFO * Acc@1 85.483 Acc@5 97.516 INFO Accuracy of the network on the 1563 test images: 85.5% INFO throughput averaged with 30 times INFO batch_size 32 throughput 158.6908637349492 ```
iwkkk commented 9 months ago

dla169

Training ``` cd CoModels/cv/classification/dla169 bash train.sh ``` 训练所用超参数 ``` AMP_OPT_LEVEL: '' AUG: AUTO_AUGMENT: rand-m9-mstd0.5-inc1 COLOR_JITTER: 0.4 CUTMIX: 0.0 CUTMIX_MINMAX: null MIXUP: 0.0 MIXUP_MODE: batch MIXUP_PROB: 1.0 MIXUP_SWITCH_PROB: 0.5 RECOUNT: 1 REMODE: pixel REPROB: 0.25 BASE: - '' DATA: BATCH_SIZE: 32 CACHE_MODE: part DATASET: imagenet DATA_PATH: /data/dataset/ImageNet/extract IMG_SIZE: 224 INTERPOLATION: bicubic NUM_CLASSES: 1000 NUM_WORKERS: 8 PIN_MEMORY: true SYNTHETIC_DATA: false ZIP_MODE: false EVAL_MODE: true LOCAL_RANK: 0 MODEL: ARCH: dla169 CHECKPOINTS: null DROP_PATH_RATE: 0.1 DROP_RATE: 0.0 LABEL_SMOOTHING: 0.1 NUM_CLASSES: 1000 PRETRAINED: true RESUME: '' OUTPUT: output/dla169/default PRINT_FREQ: 50 SAVE_FREQ: 1 SEED: 42 TAG: default TEST: CROP: true SEQUENTIAL: false THROUGHPUT_MODE: false TRAIN: ACCUMULATION_STEPS: 0 AUTO_RESUME: false BASE_LR: 0.001 CLIP_GRAD: 5.0 EPOCHS: 90 LR_SCHEDULER: DECAY_EPOCHS: 30 DECAY_RATE: 0.1 MILESTONES: - 150 - 225 NAME: step MIN_LR: 1.25e-06 OPTIMIZER: BETAS: - 0.9 - 0.999 EPS: 1.0e-08 MOMENTUM: 0.9 NAME: sgd START_EPOCH: 0 USE_CHECKPOINT: false WARMUP_EPOCHS: 0 WARMUP_LR: 5.0e-07 WEIGHT_DECAY: 0.0001 ```
Inference ``` cd CoModels/cv/classification/dla169 bash infer.sh ```
训练过程（1 epoch） * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/77448166/8286ebc2-29f2-41d9-af65-19fb05ef73cf)
推理结果 INFO * Acc@1 78.530 Acc@5 94.282 INFO Accuracy of the network on the 1563 test images: 78.5%
akeeei commented 9 months ago

Fluid simulation-ldc

cd CoModels/science/ldc
bash train.sh

Inference ``` cd CoModels/science/ldc bash infer.sh ```
训练过程 ``` num_epoch: 30000, loss: 1.00961 sub losses: 0.04032142 0.06947027 0.04393552 0.1423571 0.7135256 ```
推理结果 ``` Load checkpoint 100% [..............................................................................] 19311 / 19311 Start infer ``` 经过推断，将生成三个后缀为vtu的文件，分别表示LDC问题的水平流速、垂直流速和压力分布。可以使用Paraview等软件对结果进行可视化和后期处理。
akeeei commented 9 months ago

fan_hybrid_base_in22k_1k_384

cd CoModels/cv/classification/fan_hybrid_base_in22k_1k
bash train.sh
训练所用超参数 
DATA:
  BATCH_SIZE: 16
  DATASET: imagenet
  DATA_PATH: /data/dataset/ImageNet/extract
  IMG_SIZE: 384

MODEL:
  PRETRAINED: True
  LABEL_SMOOTHING: 0.11

TRAIN:
  START_EPOCH: 0
  EPOCHS: 90
  WARMUP_EPOCHS: 30
  WEIGHT_DECAY: 0.3
  BASE_LR: 1e-4
  WARMUP_LR: 5e-7

  LR_SCHEDULER:
    NAME: step

  OPTIMIZER:
    NAME: sgd
    MOMENTUM: 0.9

Inference ``` cd CoModels/cv/classification/fan_hybrid_base_in22k_1k bash infer.sh ```
训练过程 * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/98879022/d75fa592-ca97-4a88-80ad-034f6efa7dc4) * 训练结果 ： ``` INFO * Acc@1 85.876 Acc@5 97.701 INFO Accuracy of the network on the 1563 test images: 85.9% INFO Max accuracy: 85.88% INFO Training time 5:01:29 ```
推理结果 ``` INFO * Acc@1 83.982 Acc@5 97.006 INFO Accuracy of the network on the 1563 test images: 84.0% INFO throughput averaged with 30 times INFO batch_size 32 throughput 105.20254379907955 ```
akeeei commented 9 months ago

deit_base_patch16_LS_224

cd CoModels/cv/classification/deit_base_patch16_LS_224
bash train.sh
训练所用超参数 
DATA:
  BATCH_SIZE: 128
  DATASET: imagenet
  DATA_PATH: /data/dataset/ImageNet/extract
  IMG_SIZE: 224

MODEL:
  PRETRAINED: True
  LABEL_SMOOTHING: 0.11

TRAIN:
  START_EPOCH: 0
  EPOCHS: 90
  WARMUP_EPOCHS: 30
  WEIGHT_DECAY: 0.3
  BASE_LR: 1e-3
  WARMUP_LR: 5e-7

  LR_SCHEDULER:
    NAME: step

  OPTIMIZER:
    NAME: sgd
    MOMENTUM: 0.9

Inference ``` cd CoModels/cv/classification/deit_base_patch16_LS_224 bash infer.sh ```
训练过程 * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/98879022/7b296056-d335-47e7-a4f3-95267f525fab) * 训练结果 ： ``` INFO * Acc@1 83.054 Acc@5 96.147 INFO Accuracy of the network on the 98 test images: 83.1% INFO Max accuracy: 83.05% INFO Training time 0:57:07 ```
推理结果 ``` INFO * Acc@1 83.684 Acc@5 96.549 INFO Accuracy of the network on the 1563 test images: 83.7% INFO throughput averaged with 30 times INFO batch_size 32 throughput 266.17696222068827 ```
akeeei commented 9 months ago

fan_large_16_p4_hybrid_in22k_1k_384

cd CoModels/cv/classification/fan_large_16_p4_hybrid_in22k_1k_384
bash train.sh
训练所用超参数 
DATA:
  BATCH_SIZE: 8
  DATASET: imagenet
  DATA_PATH: /data/dataset/ImageNet/extract
  IMG_SIZE: 384

MODEL:
  PRETRAINED: True
  LABEL_SMOOTHING: 0.11

TRAIN:
  START_EPOCH: 0
  EPOCHS: 90
  WARMUP_EPOCHS: 30
  WEIGHT_DECAY: 0.3
  BASE_LR: 1e-4
  WARMUP_LR: 5e-7

  LR_SCHEDULER:
    NAME: step

  OPTIMIZER:
    NAME: sgd
    MOMENTUM: 0.9

Inference ``` cd CoModels/cv/classification/fan_large_16_p4_hybrid_in22k_1k_384 bash infer.sh ```
训练过程 * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/98879022/41db0dd0-e3a7-4be3-a5c6-a647a038e308) * 训练结果 ： ``` INFO * Acc@1 86.908 Acc@5 98.005 INFO Accuracy of the network on the 1563 test images: 86.9% INFO Max accuracy: 86.91% INFO Training time 3:50:51 ```
推理结果 ``` INFO * Acc@1 85.251 Acc@5 97.614 INFO Accuracy of the network on the 1563 test images: 85.3% INFO throughput averaged with 30 times INFO batch_size 32 throughput 242.6017645049282 ```
akeeei commented 9 months ago

fan_large_16_p4_hybrid_in22k_1k

cd CoModels/cv/classification/fan_large_16_p4_hybrid_in22k_1k
bash train.sh
训练所用超参数 
DATA:
  BATCH_SIZE: 32
  DATASET: imagenet
  DATA_PATH: /data/dataset/ImageNet/extract
  IMG_SIZE: 224

MODEL:
  PRETRAINED: True
  LABEL_SMOOTHING: 0.11

TRAIN:
  START_EPOCH: 0
  EPOCHS: 90
  WARMUP_EPOCHS: 30
  WEIGHT_DECAY: 0.3
  BASE_LR: 1e-4
  WARMUP_LR: 5e-7

  LR_SCHEDULER:
    NAME: step

  OPTIMIZER:
    NAME: sgd
    MOMENTUM: 0.9

Inference ``` cd CoModels/cv/classification/fan_large_16_p4_hybrid_in22k_1k bash infer.sh ```
训练过程 * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/98879022/dbb43628-6ece-4f52-a618-8843320d833c) * 训练结果 ： ``` INFO * Acc@1 86.171 Acc@5 97.823 INFO Accuracy of the network on the 391 test images: 86.2% INFO Max accuracy: 86.17% INFO Training time 1:16:32 ```
推理结果 ``` INFO * Acc@1 86.382 Acc@5 97.933 INFO Accuracy of the network on the 1563 test images: 86.4% INFO throughput averaged with 30 times INFO batch_size 32 throughput 111.53712566903394 ```
akeeei commented 9 months ago

Equation inversion-Lorenz system

cd CoModels/science/lorenz_system
bash train.sh

Inference ``` cd CoModels/science/lorenz_system bash infer.sh ```
训练过程 ``` num_epoch: 20000, loss: 0.02206432 sub losses: 0.005381995 0.005250522 0.01032578 1.64854e-05 0.001089531 variables: C1: 10.00202 C2: 14.99769 C3: 2.667474 ```
推理结果 ``` Load checkpoint 100% [..............................................................................] 64755 / 64755 Start infer Evaluate variables: C1: 10.00202 C2: 14.99769 C3: 2.667474 ```
akeeei commented 9 months ago

poolformer_s24

cd CoModels/cv/classification/poolformer_s24
bash train.sh
训练所用超参数 
DATA:
  BATCH_SIZE: 64
  DATASET: imagenet
  DATA_PATH: /data/dataset/ImageNet/extract
  IMG_SIZE: 224

MODEL:
  PRETRAINED: True
  LABEL_SMOOTHING: 0.11

TRAIN:
  START_EPOCH: 0
  EPOCHS: 90
  WARMUP_EPOCHS: 30
  WEIGHT_DECAY: 0.3
  BASE_LR: 1e-4
  WARMUP_LR: 5e-7

  LR_SCHEDULER:
    NAME: step

  OPTIMIZER:
    NAME: sgd
    MOMENTUM: 0.9

Inference ``` cd CoModels/cv/classification/poolformer_s24 bash infer.sh ```
训练过程 * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/98879022/c66efb64-d935-48fc-9650-03fd1013ae68) * 训练结果 ： ``` INFO * Acc@1 80.182 Acc@5 95.005 INFO Accuracy of the network on the 196 test images: 80.2% INFO Max accuracy: 80.18% INFO Training time 1:14:36 ```
推理结果 ``` INFO * Acc@1 80.301 Acc@5 95.140 INFO Accuracy of the network on the 1563 test images: 80.3% INFO throughput averaged with 30 times INFO batch_size 32 throughput 322.20938907454337 ```
akeeei commented 9 months ago

poolformer_s36

cd CoModels/cv/classification/poolformer_s36
bash train.sh
训练所用超参数 
DATA:
  BATCH_SIZE: 64
  DATASET: imagenet
  DATA_PATH: /data/dataset/ImageNet/extract
  IMG_SIZE: 224

MODEL:
  PRETRAINED: True
  LABEL_SMOOTHING: 0.11

TRAIN:
  START_EPOCH: 0
  EPOCHS: 90
  WARMUP_EPOCHS: 30
  WEIGHT_DECAY: 0.3
  BASE_LR: 1e-4
  WARMUP_LR: 5e-7

  LR_SCHEDULER:
    NAME: step

  OPTIMIZER:
    NAME: sgd
    MOMENTUM: 0.9

Inference ``` cd CoModels/cv/classification/poolformer_s36 bash infer.sh ```
训练过程 * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/98879022/f98dde57-db93-4a31-a6c7-aacebb314888) * 训练结果 ： ``` INFO * Acc@1 81.035 Acc@5 95.338 INFO Accuracy of the network on the 196 test images: 81.0% INFO Max accuracy: 81.04% INFO Training time 1:38:42 ```
推理结果 ``` INFO * Acc@1 81.276 Acc@5 95.457 INFO Accuracy of the network on the 1563 test images: 81.3% INFO throughput averaged with 30 times INFO batch_size 32 throughput 288.32020883483756 ```
akeeei commented 9 months ago

poolformer_m36

cd CoModels/cv/classification/poolformer_m36
bash train.sh
训练所用超参数 
DATA:
  BATCH_SIZE: 64
  DATASET: imagenet
  DATA_PATH: /data/dataset/ImageNet/extract
  IMG_SIZE: 224

MODEL:
  PRETRAINED: True
  LABEL_SMOOTHING: 0.11

TRAIN:
  START_EPOCH: 0
  EPOCHS: 90
  WARMUP_EPOCHS: 30
  WEIGHT_DECAY: 0.3
  BASE_LR: 1e-4
  WARMUP_LR: 5e-7

  LR_SCHEDULER:
    NAME: step

  OPTIMIZER:
    NAME: sgd
    MOMENTUM: 0.9

Inference ``` cd CoModels/cv/classification/poolformer_m36 bash infer.sh ```
训练过程 * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/98879022/5e89aeda-56f2-4ce1-a2cd-3cac7f669a7f) * 训练结果 ： ``` INFO * Acc@1 81.721 Acc@5 95.468 INFO Accuracy of the network on the 196 test images: 81.7% INFO Max accuracy: 81.72% INFO Training time 1:02:32 ```
推理结果 ``` INFO * Acc@1 82.090 Acc@5 95.710 INFO Accuracy of the network on the 1563 test images: 82.1% INFO throughput averaged with 30 times INFO batch_size 32 throughput 589.16099251004 ```
akeeei commented 9 months ago

poolformer_m48

cd CoModels/cv/classification/poolformer_m48
bash train.sh
训练所用超参数 
DATA:
  BATCH_SIZE: 64
  DATASET: imagenet
  DATA_PATH: /data/dataset/ImageNet/extract
  IMG_SIZE: 224

MODEL:
  PRETRAINED: True
  LABEL_SMOOTHING: 0.11

TRAIN:
  START_EPOCH: 0
  EPOCHS: 90
  WARMUP_EPOCHS: 30
  WEIGHT_DECAY: 0.3
  BASE_LR: 1e-4
  WARMUP_LR: 5e-7

  LR_SCHEDULER:
    NAME: step

  OPTIMIZER:
    NAME: sgd
    MOMENTUM: 0.9

Inference ``` cd CoModels/cv/classification/poolformer_m48 bash infer.sh ```
训练过程 * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/98879022/1a8673c8-2f0e-4cc6-acfa-a3ac3e11e1e9) * 训练结果 ： ``` INFO * Acc@1 82.165 Acc@5 95.722 INFO Accuracy of the network on the 391 test images: 82.2% INFO Max accuracy: 82.16% INFO Training time 1:13:00 ```
推理结果 ``` INFO * Acc@1 82.441 Acc@5 95.892 INFO Accuracy of the network on the 1563 test images: 82.4% INFO throughput averaged with 30 times INFO batch_size 32 throughput 445.26869289873656 ```
akeeei commented 9 months ago

pvt_medium

cd CoModels/cv/classification/pvt_medium
bash train.sh
训练所用超参数 
DATA:
  BATCH_SIZE: 32
  DATASET: imagenet
  DATA_PATH: /data/dataset/ImageNet/extract
  IMG_SIZE: 224

MODEL:
  PRETRAINED: True
  LABEL_SMOOTHING: 0.11

TRAIN:
  START_EPOCH: 0
  EPOCHS: 90
  WARMUP_EPOCHS: 30
  WEIGHT_DECAY: 0.3
  BASE_LR: 1e-4
  WARMUP_LR: 5e-7

  LR_SCHEDULER:
    NAME: step

  OPTIMIZER:
    NAME: sgd
    MOMENTUM: 0.9

Inference ``` cd CoModels/cv/classification/pvt_medium bash infer.sh ```
训练过程 * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/98879022/725c7128-1933-4000-b016-2582e026fb2c) * 训练结果 ： ``` INFO * Acc@1 81.364 Acc@5 95.580 INFO Accuracy of the network on the 391 test images: 81.4% INFO Max accuracy: 81.36% INFO Training time 1:48:35 ```
推理结果 ``` INFO * Acc@1 81.208 Acc@5 95.650 INFO Accuracy of the network on the 1563 test images: 81.2% INFO throughput averaged with 30 times INFO batch_size 32 throughput 236.46548065860975 ```
akeeei commented 9 months ago

pvt_tiny

cd CoModels/cv/classification/pvt_tiny
bash train.sh
训练所用超参数 
DATA:
  BATCH_SIZE: 64
  DATASET: imagenet
  DATA_PATH: /data/dataset/ImageNet/extract
  IMG_SIZE: 224

MODEL:
  PRETRAINED: True
  LABEL_SMOOTHING: 0.11

TRAIN:
  START_EPOCH: 0
  EPOCHS: 90
  WARMUP_EPOCHS: 30
  WEIGHT_DECAY: 0.3
  BASE_LR: 1e-4
  WARMUP_LR: 5e-7

  LR_SCHEDULER:
    NAME: step

  OPTIMIZER:
    NAME: sgd
    MOMENTUM: 0.9

Inference ``` cd CoModels/cv/classification/pvt_tiny bash infer.sh ```
训练过程 * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/98879022/56354201-8b2f-4a2b-a078-3cecd1021f91) * 训练结果 ： ``` INFO * Acc@1 81.704 Acc@5 95.849 INFO Accuracy of the network on the 391 test images: 81.7% INFO Max accuracy: 81.70% INFO Training time 1:23:07 ```
推理结果 ``` INFO * Acc@1 75.109 Acc@5 92.428 INFO Accuracy of the network on the 1563 test images: 75.1% INFO throughput averaged with 30 times INFO batch_size 32 throughput 655.271585262991 ```
akeeei commented 9 months ago

pvt_large

cd CoModels/cv/classification/pvt_large
bash train.sh
训练所用超参数 
DATA:
  BATCH_SIZE: 32
  DATASET: imagenet
  DATA_PATH: /data/dataset/ImageNet/extract
  IMG_SIZE: 224

MODEL:
  PRETRAINED: True
  LABEL_SMOOTHING: 0.11

TRAIN:
  START_EPOCH: 0
  EPOCHS: 90
  WARMUP_EPOCHS: 30
  WEIGHT_DECAY: 0.3
  BASE_LR: 1e-4
  WARMUP_LR: 5e-7

  LR_SCHEDULER:
    NAME: step

  OPTIMIZER:
    NAME: sgd
    MOMENTUM: 0.9

Inference ``` cd CoModels/cv/classification/pvt_large bash infer.sh ```
训练过程 * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/98879022/1f394d86-b20e-4a3c-aa7d-3c95c6d4a3f3) * 训练结果 ： ``` INFO * Acc@1 75.196 Acc@5 92.426 INFO Accuracy of the network on the 391 test images: 75.2% INFO Max accuracy: 75.20% INFO Training time 0:36:00 ```
推理结果 ``` INFO * Acc@1 81.689 Acc@5 95.841 INFO Accuracy of the network on the 1563 test images: 81.7% INFO throughput averaged with 30 times INFO batch_size 32 throughput 164.84514218123954 ```
akeeei commented 9 months ago

deit_base_patch16_LS_224_in21k

cd CoModels/cv/classification/deit_base_patch16_LS_224_in21k
bash train.sh
训练所用超参数 
DATA:
  BATCH_SIZE: 32
  DATASET: imagenet
  DATA_PATH: /data/dataset/ImageNet/extract
  IMG_SIZE: 224

MODEL:
  PRETRAINED: True
  LABEL_SMOOTHING: 0.11

TRAIN:
  START_EPOCH: 0
  EPOCHS: 90
  WARMUP_EPOCHS: 30
  WEIGHT_DECAY: 0.3
  BASE_LR: 5e-5
  WARMUP_LR: 5e-7

  LR_SCHEDULER:
    NAME: step

  OPTIMIZER:
    NAME: sgd
    MOMENTUM: 0.9

Inference ``` cd CoModels/cv/classification/deit_base_patch16_LS_224_in21k bash infer.sh ```
训练过程 * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/98879022/de452003-2319-4123-87c5-96a5e47d100e) * 训练结果 ： ``` INFO * Acc@1 85.158 Acc@5 97.409 INFO Accuracy of the network on the 391 test images: 85.2% INFO Max accuracy: 85.16% INFO Training time 0:57:07 ```
推理结果 ``` INFO * Acc@1 85.503 Acc@5 97.560 INFO Accuracy of the network on the 1563 test images: 85.5% INFO throughput averaged with 30 times INFO batch_size 32 throughput 570.4031648236078 ```
akeeei commented 9 months ago

vit_base_patch16_224_miil

cd CoModels/cv/classification/vit_base_patch16_224_miil
bash train.sh
训练所用超参数 
DATA:
  BATCH_SIZE: 32
  DATASET: imagenet
  DATA_PATH: /data/dataset/ImageNet/extract
  IMG_SIZE: 224

MODEL:
  PRETRAINED: True
  LABEL_SMOOTHING: 0.11

TRAIN:
  START_EPOCH: 0
  EPOCHS: 90
  WARMUP_EPOCHS: 30
  WEIGHT_DECAY: 0.3
  BASE_LR: 1e-4
  WARMUP_LR: 5e-7

  LR_SCHEDULER:
    NAME: step

  OPTIMIZER:
    NAME: sgd
    MOMENTUM: 0.9

Inference ``` cd CoModels/cv/classification/vit_base_patch16_224_miil bash infer.sh ```
训练过程 * 训练日志 ： ![image](https://github.com/Oneflow-Inc/CoModels/assets/98879022/a19dbffe-5803-4743-ae46-a812f0fa8d24) * 训练结果 ： ``` INFO * Acc@1 75.447 Acc@5 92.909 INFO Accuracy of the network on the 391 test images: 75.4% INFO Max accuracy: 75.45% INFO Training time 1:37:03 ```
推理结果 ``` INFO * Acc@1 33.865 Acc@5 53.165 INFO Accuracy of the network on the 1563 test images: 33.9% INFO throughput averaged with 30 times INFO batch_size 32 throughput 276.1159336251757 ```