End of training
Browse files
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: google/vivit-b-16x2
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- f1
|
9 |
+
- recall
|
10 |
+
- precision
|
11 |
+
model-index:
|
12 |
+
- name: vivit-b-16x2-finetuned-cctv-surveillance
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# vivit-b-16x2-finetuned-cctv-surveillance
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [google/vivit-b-16x2](https://huggingface.co/google/vivit-b-16x2) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.1478
|
24 |
+
- Accuracy: 0.9460
|
25 |
+
- F1: 0.9430
|
26 |
+
- Recall: 0.9460
|
27 |
+
- Precision: 0.9454
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 5e-06
|
47 |
+
- train_batch_size: 2
|
48 |
+
- eval_batch_size: 2
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- lr_scheduler_warmup_ratio: 0.1
|
53 |
+
- training_steps: 4176
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Precision |
|
58 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:|
|
59 |
+
| 0.9564 | 0.12 | 522 | 0.4417 | 0.8685 | 0.8096 | 0.8685 | 0.7990 |
|
60 |
+
| 0.4574 | 1.12 | 1044 | 0.2633 | 0.9131 | 0.9042 | 0.9131 | 0.9269 |
|
61 |
+
| 0.421 | 2.12 | 1566 | 0.1875 | 0.9272 | 0.9100 | 0.9272 | 0.9353 |
|
62 |
+
| 0.4785 | 3.12 | 2088 | 0.1854 | 0.9249 | 0.9082 | 0.9249 | 0.9140 |
|
63 |
+
| 0.3213 | 4.12 | 2610 | 0.1805 | 0.9272 | 0.9125 | 0.9272 | 0.9216 |
|
64 |
+
| 0.1465 | 5.12 | 3132 | 0.1733 | 0.9413 | 0.9362 | 0.9413 | 0.9398 |
|
65 |
+
| 0.0784 | 6.12 | 3654 | 0.1616 | 0.9437 | 0.9391 | 0.9437 | 0.9434 |
|
66 |
+
| 0.2017 | 7.12 | 4176 | 0.1478 | 0.9460 | 0.9430 | 0.9460 | 0.9454 |
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- Transformers 4.39.3
|
72 |
+
- Pytorch 2.1.2
|
73 |
+
- Datasets 2.18.0
|
74 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/vivit-b-16x2",
|
3 |
+
"architectures": [
|
4 |
+
"VivitForVideoClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"hidden_act": "gelu_fast",
|
8 |
+
"hidden_dropout_prob": 0.0,
|
9 |
+
"hidden_size": 768,
|
10 |
+
"id2label": {
|
11 |
+
"0": "burglary",
|
12 |
+
"1": "normal",
|
13 |
+
"2": "roadaccidents",
|
14 |
+
"3": "robbery",
|
15 |
+
"4": "stealing"
|
16 |
+
},
|
17 |
+
"image_size": 224,
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"label2id": {
|
21 |
+
"burglary": 0,
|
22 |
+
"normal": 1,
|
23 |
+
"roadaccidents": 2,
|
24 |
+
"robbery": 3,
|
25 |
+
"stealing": 4
|
26 |
+
},
|
27 |
+
"layer_norm_eps": 1e-06,
|
28 |
+
"model_type": "vivit",
|
29 |
+
"num_attention_heads": 12,
|
30 |
+
"num_channels": 3,
|
31 |
+
"num_frames": 32,
|
32 |
+
"num_hidden_layers": 12,
|
33 |
+
"qkv_bias": true,
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.39.3",
|
36 |
+
"tubelet_size": [
|
37 |
+
2,
|
38 |
+
16,
|
39 |
+
16
|
40 |
+
]
|
41 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bae592f59e4941c46b91796d07b68aee3c830ad7b69c29d3840905d900c5039
|
3 |
+
size 354624604
|
preprocessor_config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_valid_processor_keys": [
|
3 |
+
"videos",
|
4 |
+
"do_resize",
|
5 |
+
"size",
|
6 |
+
"resample",
|
7 |
+
"do_center_crop",
|
8 |
+
"crop_size",
|
9 |
+
"do_rescale",
|
10 |
+
"rescale_factor",
|
11 |
+
"offset",
|
12 |
+
"do_normalize",
|
13 |
+
"image_mean",
|
14 |
+
"image_std",
|
15 |
+
"return_tensors",
|
16 |
+
"data_format",
|
17 |
+
"input_data_format"
|
18 |
+
],
|
19 |
+
"crop_size": {
|
20 |
+
"height": 224,
|
21 |
+
"width": 224
|
22 |
+
},
|
23 |
+
"do_center_crop": true,
|
24 |
+
"do_normalize": false,
|
25 |
+
"do_rescale": true,
|
26 |
+
"do_resize": true,
|
27 |
+
"do_zero_centering": true,
|
28 |
+
"image_mean": [
|
29 |
+
0.5,
|
30 |
+
0.5,
|
31 |
+
0.5
|
32 |
+
],
|
33 |
+
"image_processor_type": "VivitImageProcessor",
|
34 |
+
"image_std": [
|
35 |
+
0.5,
|
36 |
+
0.5,
|
37 |
+
0.5
|
38 |
+
],
|
39 |
+
"offset": true,
|
40 |
+
"resample": 2,
|
41 |
+
"rescale_factor": 0.00784313725490196,
|
42 |
+
"size": {
|
43 |
+
"shortest_edge": 256
|
44 |
+
}
|
45 |
+
}
|
runs/May25_09-57-28_a97e9f363930/events.out.tfevents.1716631053.a97e9f363930.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a42b40bd25cda86ae37d200cdd9ef1e248d0a6c82504da0318fe0fd5731c8c33
|
3 |
+
size 96940
|
runs/May25_09-57-28_a97e9f363930/events.out.tfevents.1716655678.a97e9f363930.34.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3dc37cbc59532259ced92f66890b768d810ba91ff42851516ea5ef2370d5a41e
|
3 |
+
size 560
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74e13b1ddc7f922e0cb7c79c0ae42de2ef87cdc489731b9b9553703e7b404848
|
3 |
+
size 4984
|