Hugging Face's logo

omermazig
/
videomae-finetuned-nba-5-class-4-batch-8000-vid-multilabel

Video Classification
Transformers
TensorBoard
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
omermazig commited on
Commit
7b27a25
•
1 Parent(s): aaf0209

Model save

Browse files
Files changed (7) hide show
  1. README.md +88 -0
  2. config.json +47 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +27 -0
  5. runs/Nov04_14-42-29_4ce8c3d43516/events.out.tfevents.1699108955.4ce8c3d43516.1418.0 +3 -0
  6. runs/Nov04_14-42-29_4ce8c3d43516/events.out.tfevents.1699172654.4ce8c3d43516.1418.1 +3 -0
  7. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ base_model: MCG-NJU/videomae-base-finetuned-kinetics
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - f1
8
+ - accuracy
9
+ model-index:
10
+ - name: videomae-finetuned-nba-5-class-4-batch-8000-vid-multilabel-4
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # videomae-finetuned-nba-5-class-4-batch-8000-vid-multilabel-4
18
+
19
+ This model is a fine-tuned version of [MCG-NJU/videomae-base-finetuned-kinetics](https://huggingface.co/MCG-NJU/videomae-base-finetuned-kinetics) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.4886
22
+ - F1: 0.8863
23
+ - Roc Auc: 0.9209
24
+ - Accuracy: 0.7962
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 1.5e-05
44
+ - train_batch_size: 4
45
+ - eval_batch_size: 4
46
+ - seed: 42
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - training_steps: 50000
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
55
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|:--------:|
56
+ | 0.771 | 0.04 | 2000 | 0.7660 | 0.6227 | 0.7324 | 0.2937 |
57
+ | 0.6225 | 1.04 | 4000 | 0.6446 | 0.7401 | 0.8162 | 0.4653 |
58
+ | 0.6093 | 2.04 | 6000 | 0.6517 | 0.7441 | 0.8223 | 0.5253 |
59
+ | 0.603 | 3.04 | 8000 | 0.5630 | 0.8151 | 0.8722 | 0.6558 |
60
+ | 0.6547 | 4.04 | 10000 | 0.5009 | 0.8425 | 0.8911 | 0.6695 |
61
+ | 0.6426 | 5.04 | 12000 | 0.5179 | 0.8422 | 0.9012 | 0.6642 |
62
+ | 0.4447 | 6.04 | 14000 | 0.5052 | 0.8537 | 0.8973 | 0.7147 |
63
+ | 0.6949 | 7.04 | 16000 | 0.5045 | 0.8548 | 0.8974 | 0.7337 |
64
+ | 0.509 | 8.04 | 18000 | 0.5262 | 0.8705 | 0.9089 | 0.7768 |
65
+ | 0.4341 | 9.04 | 20000 | 0.4731 | 0.8831 | 0.9163 | 0.7863 |
66
+ | 0.5037 | 10.04 | 22000 | 0.5040 | 0.8781 | 0.9154 | 0.7747 |
67
+ | 0.3592 | 11.04 | 24000 | 0.5091 | 0.8746 | 0.9101 | 0.7821 |
68
+ | 0.2829 | 12.04 | 26000 | 0.4709 | 0.8867 | 0.9230 | 0.7905 |
69
+ | 0.3599 | 13.04 | 28000 | 0.4722 | 0.8888 | 0.9230 | 0.7947 |
70
+ | 0.4152 | 14.04 | 30000 | 0.4744 | 0.8911 | 0.9247 | 0.8074 |
71
+ | 0.1167 | 15.04 | 32000 | 0.4817 | 0.8949 | 0.9241 | 0.8179 |
72
+ | 0.2721 | 16.04 | 34000 | 0.4627 | 0.9064 | 0.9337 | 0.8274 |
73
+ | 0.42 | 17.04 | 36000 | 0.4849 | 0.8992 | 0.9282 | 0.8295 |
74
+ | 0.5841 | 18.04 | 38000 | 0.4747 | 0.9026 | 0.9304 | 0.8379 |
75
+ | 0.509 | 19.04 | 40000 | 0.4779 | 0.8991 | 0.9273 | 0.8316 |
76
+ | 0.1599 | 20.04 | 42000 | 0.4945 | 0.9056 | 0.9319 | 0.8411 |
77
+ | 0.3645 | 21.04 | 44000 | 0.4875 | 0.8984 | 0.9277 | 0.8242 |
78
+ | 0.4402 | 22.04 | 46000 | 0.5156 | 0.9004 | 0.9283 | 0.8368 |
79
+ | 0.2769 | 23.04 | 48000 | 0.5063 | 0.9028 | 0.9296 | 0.8389 |
80
+ | 0.3009 | 24.04 | 50000 | 0.5122 | 0.8975 | 0.9257 | 0.8326 |
81
+
82
+
83
+ ### Framework versions
84
+
85
+ - Transformers 4.35.0
86
+ - Pytorch 2.1.0+cu118
87
+ - Datasets 2.14.6
88
+ - Tokenizers 0.14.1
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "MCG-NJU/videomae-base-finetuned-kinetics",
3
+ "architectures": [
4
+ "VideoMAEForVideoClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "decoder_hidden_size": 384,
8
+ "decoder_intermediate_size": 1536,
9
+ "decoder_num_attention_heads": 6,
10
+ "decoder_num_hidden_layers": 4,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.0,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "DUNK",
16
+ "1": "FLOATING",
17
+ "2": "JUMP",
18
+ "3": "REVERSE_LAYUP",
19
+ "4": "SHOT",
20
+ "5": "TURNAROUND_HOOK"
21
+ },
22
+ "image_size": 224,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "DUNK": 0,
27
+ "FLOATING": 1,
28
+ "JUMP": 2,
29
+ "REVERSE_LAYUP": 3,
30
+ "SHOT": 4,
31
+ "TURNAROUND_HOOK": 5
32
+ },
33
+ "layer_norm_eps": 1e-12,
34
+ "model_type": "videomae",
35
+ "norm_pix_loss": false,
36
+ "num_attention_heads": 12,
37
+ "num_channels": 3,
38
+ "num_frames": 16,
39
+ "num_hidden_layers": 12,
40
+ "patch_size": 16,
41
+ "problem_type": "multi_label_classification",
42
+ "qkv_bias": true,
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.35.0",
45
+ "tubelet_size": 2,
46
+ "use_mean_pooling": true
47
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8909a18f29f4a8868e69aebe1660abd1bfbd95f3933a731f00d3b23d392ecc5b
3
+ size 344949640
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_normalize": true,
8
+ "do_rescale": true,
9
+ "do_resize": true,
10
+ "feature_extractor_type": "VideoMAEFeatureExtractor",
11
+ "image_mean": [
12
+ 0.485,
13
+ 0.456,
14
+ 0.406
15
+ ],
16
+ "image_processor_type": "VideoMAEImageProcessor",
17
+ "image_std": [
18
+ 0.229,
19
+ 0.224,
20
+ 0.225
21
+ ],
22
+ "resample": 2,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "shortest_edge": 224
26
+ }
27
+ }
runs/Nov04_14-42-29_4ce8c3d43516/events.out.tfevents.1699108955.4ce8c3d43516.1418.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78387af1b7ae2c97306267744b0b3a660dbc77e8fc0775c626e831a67b2414ef
3
+ size 810863
runs/Nov04_14-42-29_4ce8c3d43516/events.out.tfevents.1699172654.4ce8c3d43516.1418.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41a7d4edb4a7809c8e11cc14823e9eb788486715f720dca7fb218e26862d422d
3
+ size 944
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9873b050e72872b0be6e307e83a54f78c2f2bc19be3cf22fb8f24536f5022e4
3
+ size 4664