videomae-small-finetuned-kinetics-finetuned-SoccerNetChunks-InferenceCamT-Replay-5c

SushantGautam/videomae-small-finetuned-kinetics-finetuned-SoccerNetChunks-InferenceCamT-Replay-5c

videomae-small-finetuned-kinetics-finetuned-SoccerNetChunks-InferenceCamT-Replay-5c is a machine learning model from SushantGautam. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as cc-by-nc-4.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

20% of all-time downloads

All-time downloads

Public

Repo size

1.9 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin87.6 MB · 99%

At a glance

Library: transformers
License: cc-by-nc-4.0
Model type: videomae
Access: Public
Created: Jul 18, 2023
Updated: Jul 20, 2023
SHA: ce25f577

Model card

From the Hugging Face model README

videomae-small-finetuned-kinetics-finetuned-SoccerNetChunks-InferenceCamT-Replay-5c

This model is a fine-tuned version of MCG-NJU/videomae-small-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.9690
Accuracy: 0.6194
Balanced Accuracy: 0.6194
Matthews Correlation: 0.5491
Confusion Matrix: [[ 995 77 83 101 23 93] [ 249 876 76 39 29 102] [ 94 28 1010 148 71 19] [ 249 34 301 627 118 41] [ 171 34 341 466 320 39] [ 71 15 12 2 4 1266]]
0 Ball out of play: {'precision': 0.544013121924549, 'recall': 0.7252186588921283, 'f1-score': 0.6216807247735083, 'support': 1372.0}
Precision 0: 0.5440
Recall 0: 0.7252
F1-score 0: 0.6217
Support 0: 1372.0
1 Foul: {'precision': 0.8233082706766918, 'recall': 0.6389496717724289, 'f1-score': 0.7195071868583162, 'support': 1371.0}
Precision 1: 0.8233
Recall 1: 0.6389
F1-score 1: 0.7195
Support 1: 1371.0
2 Goal: {'precision': 0.5540318156884256, 'recall': 0.7372262773722628, 'f1-score': 0.6326338866269965, 'support': 1370.0}
Precision 2: 0.5540
Recall 2: 0.7372
F1-score 2: 0.6326
Support 2: 1370.0
3 Shots off target: {'precision': 0.45336225596529284, 'recall': 0.4576642335766423, 'f1-score': 0.4555030875408645, 'support': 1370.0}
Precision 3: 0.4534
Recall 3: 0.4577
F1-score 3: 0.4555
Support 3: 1370.0
4 Shots on target: {'precision': 0.5663716814159292, 'recall': 0.23340627279358134, 'f1-score': 0.3305785123966943, 'support': 1371.0}
Precision 4: 0.5664
Recall 4: 0.2334
F1-score 4: 0.3306
Support 4: 1371.0
5 Throw-in: {'precision': 0.8115384615384615, 'recall': 0.9240875912408759, 'f1-score': 0.8641638225255973, 'support': 1370.0}
Precision 5: 0.8115
Recall 5: 0.9241
F1-score 5: 0.8642
Support 5: 1370.0
Precision Macro avg: 0.6254
Recall Macro avg: 0.6194
F1-score Macro avg: 0.6040
Support Macro avg: 8224.0
Precision Weighted avg: 0.6254
Recall Weighted avg: 0.6194
F1-score Weighted avg: 0.6040
Support Weighted avg: 8224.0

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
distributed_type: multi-GPU
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
training_steps: 10310

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Balanced Accuracy	Matthews Correlation	Confusion Matrix	0 Ball out of play	Precision 0	Recall 0	F1-score 0	Support 0	1 Foul	Precision 1	Recall 1	F1-score 1	Support 1	2 Goal	Precision 2	Recall 2	F1-score 2	Support 2	3 Shots off target	Precision 3	Recall 3	F1-score 3	Support 3	4 Shots on target	Precision 4	Recall 4	F1-score 4	Support 4	5 Throw-in	Precision 5	Recall 5	F1-score 5	Support 5	Precision Macro avg
1.3568	0.1	1031	1.2032	0.5098	0.5099	0.4200	[[ 430 181 121 253 74 313]
[ 90 788 83 89 46 275]
[ 45 41 942 219 71 52]
[ 87 38 470 507 169 99]
[ 47 27 432 494 253 118]
[ 12 27 27 11 20 1273]]	{'precision': 0.6047819971870605, 'recall': 0.31341107871720114, 'f1-score': 0.4128660585693711, 'support': 1372.0}	0.6048	0.3134	0.4129	1372.0	{'precision': 0.7150635208711433, 'recall': 0.574762946754194, 'f1-score': 0.637282652648605, 'support': 1371.0}	0.7151	0.5748	0.6373	1371.0	{'precision': 0.45397590361445783, 'recall': 0.6875912408759124, 'f1-score': 0.5468795355587809, 'support': 1370.0}	0.4540	0.6876	0.5469	1370.0	{'precision': 0.32231404958677684, 'recall': 0.3700729927007299, 'f1-score': 0.34454638124362896, 'support': 1370.0}	0.3223	0.3701	0.3445	1370.0	{'precision': 0.39968404423380727, 'recall': 0.18453683442742524, 'f1-score': 0.25249500998003993, 'support': 1371.0}	0.3997	0.1845	0.2525	1371.0	{'precision': 0.5976525821596245, 'recall': 0.9291970802919708, 'f1-score': 0.7274285714285714, 'support': 1370.0}	0.5977	0.9292	0.7274	1370.0	0.5156	0.5099	0.4869	8224.0	0.5156	0.5098	0.4869	8224.0
0.8604	0.2	2062	1.1708	0.5125	0.5125	0.4247	[[982 89 101 142 24 34]
[459 679 79 71 39 44]
[137 36 812 287 91 7]
[286 47 248 677 94 18]
[235 43 256 674 130 33]
[262 58 75 37 3 935]]	{'precision': 0.41592545531554426, 'recall': 0.7157434402332361, 'f1-score': 0.5261184034288775, 'support': 1372.0}	0.4159	0.7157	0.5261	1372.0	{'precision': 0.7132352941176471, 'recall': 0.49525893508388036, 'f1-score': 0.5845888936719759, 'support': 1371.0}	0.7132	0.4953	0.5846	1371.0	{'precision': 0.5168682367918523, 'recall': 0.5927007299270073, 'f1-score': 0.5521931315878954, 'support': 1370.0}	0.5169	0.5927	0.5522	1370.0	{'precision': 0.3585805084745763, 'recall': 0.49416058394160584, 'f1-score': 0.41559238796807857, 'support': 1370.0}	0.3586	0.4942	0.4156	1370.0	{'precision': 0.34120734908136485, 'recall': 0.09482129832239242, 'f1-score': 0.14840182648401828, 'support': 1371.0}	0.3412	0.0948	0.1484	1371.0	{'precision': 0.873015873015873, 'recall': 0.6824817518248175, 'f1-score': 0.7660794756247439, 'support': 1370.0}	0.8730	0.6825	0.7661	1370.0	0.5365	0.5125	0.4988	8224.0	0.5364	0.5125	0.4988	8224.0
1.6791	0.3	3093	1.0393	0.5744	0.5744	0.4948	[[ 820 156 112 166 21 97]
[ 217 911 91 52 28 72]
[ 102 61 974 160 52 21]
[ 178 61 385 616 102 28]
[ 118 47 400 536 252 18]
[ 77 71 29 19 23 1151]]	{'precision': 0.5423280423280423, 'recall': 0.597667638483965, 'f1-score': 0.5686546463245492, 'support': 1372.0}	0.5423	0.5977	0.5687	1372.0	{'precision': 0.6970160673297628, 'recall': 0.6644784828592268, 'f1-score': 0.6803584764749814, 'support': 1371.0}	0.6970	0.6645	0.6804	1371.0	{'precision': 0.48920140632847814, 'recall': 0.710948905109489, 'f1-score': 0.5795894079143111, 'support': 1370.0}	0.4892	0.7109	0.5796	1370.0	{'precision': 0.3976759199483538, 'recall': 0.44963503649635034, 'f1-score': 0.42206235011990406, 'support': 1370.0}	0.3977	0.4496	0.4221	1370.0	{'precision': 0.5271966527196653, 'recall': 0.1838074398249453, 'f1-score': 0.2725797728501893, 'support': 1371.0}	0.5272	0.1838	0.2726	1371.0	{'precision': 0.8298485940879596, 'recall': 0.8401459854014599, 'f1-score': 0.8349655422560754, 'support': 1370.0}	0.8298	0.8401	0.8350	1370.0	0.5805	0.5744	0.5597	8224.0	0.5805	0.5744	0.5597	8224.0
1.1391	1.0	4124	0.9952	0.6049	0.6050	0.5291	[[ 715 306 85 107 90 69]
[ 96 1076 56 20 47 76]
[ 64 54 968 94 176 14]
[ 115 117 314 375 416 33]
[ 67 92 318 211 655 28]
[ 57 77 27 2 21 1186]]	{'precision': 0.6418312387791741, 'recall': 0.5211370262390671, 'f1-score': 0.5752212389380531, 'support': 1372.0}	0.6418	0.5211	0.5752	1372.0	{'precision': 0.6248548199767712, 'recall': 0.7848285922684172, 'f1-score': 0.6957646298092466, 'support': 1371.0}	0.6249	0.7848	0.6958	1371.0	{'precision': 0.5475113122171946, 'recall': 0.7065693430656934, 'f1-score': 0.6169534735500319, 'support': 1370.0}	0.5475	0.7066	0.6170	1370.0	{'precision': 0.4635352286773795, 'recall': 0.2737226277372263, 'f1-score': 0.3441945846718678, 'support': 1370.0}	0.4635	0.2737	0.3442	1370.0	{'precision': 0.46619217081850534, 'recall': 0.4777534646243618, 'f1-score': 0.4719020172910663, 'support': 1371.0}	0.4662	0.4778	0.4719	1371.0	{'precision': 0.8435277382645804, 'recall': 0.8656934306569343, 'f1-score': 0.8544668587896254, 'support': 1370.0}	0.8435	0.8657	0.8545	1370.0	0.5979	0.6050	0.5931	8224.0	0.5979	0.6049	0.5931	8224.0
1.3699	1.1	5155	1.0480	0.5764	0.5764	0.5012	[[1036 67 90 137 24 18]
[ 347 787 82 73 54 28]
[ 111 19 956 230 50 4]
[ 289 26 291 680 75 9]
[ 226 38 326 538 227 16]
[ 249 26 24 12 5 1054]]	{'precision': 0.4588131089459699, 'recall': 0.7551020408163265, 'f1-score': 0.5707988980716253, 'support': 1372.0}	0.4588	0.7551	0.5708	1372.0	{'precision': 0.8172377985462098, 'recall': 0.574033552151714, 'f1-score': 0.6743787489288775, 'support': 1371.0}	0.8172	0.5740	0.6744	1371.0	{'precision': 0.5404183154324477, 'recall': 0.6978102189781021, 'f1-score': 0.6091111819050652, 'support': 1370.0}	0.5404	0.6978	0.6091	1370.0	{'precision': 0.40718562874251496, 'recall': 0.49635036496350365, 'f1-score': 0.44736842105263164, 'support': 1370.0}	0.4072	0.4964	0.4474	1370.0	{'precision': 0.5218390804597701, 'recall': 0.16557257476294676, 'f1-score': 0.2513842746400886, 'support': 1371.0}	0.5218	0.1656	0.2514	1371.0	{'precision': 0.933569530558016, 'recall': 0.7693430656934307, 'f1-score': 0.8435374149659864, 'support': 1370.0}	0.9336	0.7693	0.8435	1370.0	0.6132	0.5764	0.5661	8224.0	0.6132	0.5764	0.5661	8224.0
0.7439	1.2	6186	0.9830	0.5990	0.5990	0.5290	[[ 874 104 60 207 12 115]
[ 195 881 74 85 30 106]
[ 79 25 860 357 33 16]
[ 148 32 230 865 55 40]
[ 96 28 255 784 170 38]
[ 51 20 10 8 5 1276]]	{'precision': 0.6056826056826057, 'recall': 0.6370262390670554, 'f1-score': 0.6209591474245115, 'support': 1372.0}	0.6057	0.6370	0.6210	1372.0	{'precision': 0.808256880733945, 'recall': 0.6425966447848286, 'f1-score': 0.715969118244616, 'support': 1371.0}	0.8083	0.6426	0.7160	1371.0	{'precision': 0.577568838146407, 'recall': 0.6277372262773723, 'f1-score': 0.6016089541797831, 'support': 1370.0}	0.5776	0.6277	0.6016	1370.0	{'precision': 0.3751084128360798, 'recall': 0.6313868613138686, 'f1-score': 0.47062023939064196, 'support': 1370.0}	0.3751	0.6314	0.4706	1370.0	{'precision': 0.5573770491803278, 'recall': 0.12399708242159008, 'f1-score': 0.20286396181384245, 'support': 1371.0}	0.5574	0.1240	0.2029	1371.0	{'precision': 0.8020113136392206, 'recall': 0.9313868613138686, 'f1-score': 0.8618709895305641, 'support': 1370.0}	0.8020	0.9314	0.8619	1370.0	0.6210	0.5990	0.5790	8224.0	0.6210	0.5990	0.5790	8224.0
0.8838	1.3	7217	0.9624	0.6175	0.6175	0.5448	[[ 957 91 52 150 25 97]
[ 265 888 48 41 23 106]
[ 102 34 897 222 101 14]
[ 211 54 252 671 140 42]
[ 136 64 257 500 374 40]
[ 57 15 2 1 4 1291]]	{'precision': 0.5538194444444444, 'recall': 0.6975218658892128, 'f1-score': 0.6174193548387097, 'support': 1372.0}	0.5538	0.6975	0.6174	1372.0	{'precision': 0.774869109947644, 'recall': 0.6477024070021882, 'f1-score': 0.7056019070321811, 'support': 1371.0}	0.7749	0.6477	0.7056	1371.0	{'precision': 0.5948275862068966, 'recall': 0.6547445255474452, 'f1-score': 0.6233495482974287, 'support': 1370.0}	0.5948	0.6547	0.6233	1370.0	{'precision': 0.42334384858044166, 'recall': 0.4897810218978102, 'f1-score': 0.4541455160744501, 'support': 1370.0}	0.4233	0.4898	0.4541	1370.0	{'precision': 0.56071964017991, 'recall': 0.2727935813274982, 'f1-score': 0.36702649656526004, 'support': 1371.0}	0.5607	0.2728	0.3670	1371.0	{'precision': 0.8119496855345912, 'recall': 0.9423357664233577, 'f1-score': 0.8722972972972974, 'support': 1370.0}	0.8119	0.9423	0.8723	1370.0	0.6199	0.6175	0.6066	8224.0	0.6199	0.6175	0.6066	8224.0
1.1552	2.0	8248	0.9936	0.6136	0.6136	0.5425	[[ 991 93 87 97 24 80]
[ 231 896 85 42 35 82]
[ 118 26 1028 131 55 12]
[ 239 59 324 597 112 39]
[ 156 76 388 415 298 38]
[ 74 27 25 3 5 1236]]	{'precision': 0.5478164731896075, 'recall': 0.7223032069970845, 'f1-score': 0.6230745048726815, 'support': 1372.0}	0.5478	0.7223	0.6231	1372.0	{'precision': 0.7612574341546304, 'recall': 0.6535375638220278, 'f1-score': 0.7032967032967034, 'support': 1371.0}	0.7613	0.6535	0.7033	1371.0	{'precision': 0.5307176045431079, 'recall': 0.7503649635036497, 'f1-score': 0.6217115210160266, 'support': 1370.0}	0.5307	0.7504	0.6217	1370.0	{'precision': 0.46459143968871597, 'recall': 0.43576642335766425, 'f1-score': 0.44971751412429384, 'support': 1370.0}	0.4646	0.4358	0.4497	1370.0	{'precision': 0.5633270321361059, 'recall': 0.21735959153902262, 'f1-score': 0.31368421052631584, 'support': 1371.0}	0.5633	0.2174	0.3137	1371.0	{'precision': 0.8312037659717552, 'recall': 0.9021897810218978, 'f1-score': 0.8652432621631081, 'support': 1370.0}	0.8312	0.9022	0.8652	1370.0	0.6165	0.6136	0.5961	8224.0	0.6165	0.6136	0.5961	8224.0
1.0153	2.1	9279	1.0328	0.5963	0.5963	0.5251	[[1062 66 60 99 17 68]
[ 321 824 68 47 27 84]
[ 159 26 931 201 42 11]
[ 341 33 243 658 72 23]
[ 275 37 299 528 201 31]
[ 100 17 19 3 3 1228]]	{'precision': 0.47032772364924713, 'recall': 0.7740524781341108, 'f1-score': 0.5851239669421487, 'support': 1372.0}	0.4703	0.7741	0.5851	1372.0	{'precision': 0.8215353938185443, 'recall': 0.6010211524434719, 'f1-score': 0.6941870261162594, 'support': 1371.0}	0.8215	0.6010	0.6942	1371.0	{'precision': 0.5746913580246914, 'recall': 0.6795620437956205, 'f1-score': 0.6227424749163879, 'support': 1370.0}	0.5747	0.6796	0.6227	1370.0	{'precision': 0.4283854166666667, 'recall': 0.4802919708029197, 'f1-score': 0.452856159669649, 'support': 1370.0}	0.4284	0.4803	0.4529	1370.0	{'precision': 0.5552486187845304, 'recall': 0.14660831509846828, 'f1-score': 0.2319676860934795, 'support': 1371.0}	0.5552	0.1466	0.2320	1371.0	{'precision': 0.8498269896193772, 'recall': 0.8963503649635036, 'f1-score': 0.8724689165186502, 'support': 1370.0}	0.8498	0.8964	0.8725	1370.0	0.6167	0.5963	0.5766	8224.0	0.6167	0.5963	0.5765	8224.0
0.6315	2.2	10310	0.9690	0.6194	0.6194	0.5491	[[ 995 77 83 101 23 93]
[ 249 876 76 39 29 102]
[ 94 28 1010 148 71 19]
[ 249 34 301 627 118 41]
[ 171 34 341 466 320 39]
[ 71 15 12 2 4 1266]]	{'precision': 0.544013121924549, 'recall': 0.7252186588921283, 'f1-score': 0.6216807247735083, 'support': 1372.0}	0.5440	0.7252	0.6217	1372.0	{'precision': 0.8233082706766918, 'recall': 0.6389496717724289, 'f1-score': 0.7195071868583162, 'support': 1371.0}	0.8233	0.6389	0.7195	1371.0	{'precision': 0.5540318156884256, 'recall': 0.7372262773722628, 'f1-score': 0.6326338866269965, 'support': 1370.0}	0.5540	0.7372	0.6326	1370.0	{'precision': 0.45336225596529284, 'recall': 0.4576642335766423, 'f1-score': 0.4555030875408645, 'support': 1370.0}	0.4534	0.4577	0.4555	1370.0	{'precision': 0.5663716814159292, 'recall': 0.23340627279358134, 'f1-score': 0.3305785123966943, 'support': 1371.0}	0.5664	0.2334	0.3306	1371.0	{'precision': 0.8115384615384615, 'recall': 0.9240875912408759, 'f1-score': 0.8641638225255973, 'support': 1370.0}	0.8115	0.9241	0.8642	1370.0	0.6254	0.6194	0.6040	8224.0	0.6254	0.6194	0.6040	8224.0

Framework versions

Transformers 4.30.2
Pytorch 2.0.1+cu117
Datasets 2.13.1
Tokenizers 0.13.3

Library: transformers
Type: videomae
License: cc-by-nc-4.0
Created: Jul 18, 2023
Updated: Jul 20, 2023