Hugging Face's logo

srikrishnateja
/
vit-hybrid-base-bit-384-finetuned-cctv

Image Classification
Transformers
TensorBoard
Safetensors
vit-hybrid
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
srikrishnateja commited on
Commit
efaaf22
·
verified ·
1 Parent(s): 17b3f59

End of training

Browse files
Files changed (9) hide show
  1. README.md +53 -0
  2. config.json +63 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +27 -0
  5. runs/Mar03_16-27-17_6974a0189950/events.out.tfevents.1709483301.6974a0189950.34.0 +3 -0
  6. runs/Mar03_16-27-17_6974a0189950/events.out.tfevents.1709483714.6974a0189950.34.1 +3 -0
  7. runs/Mar03_16-27-17_6974a0189950/events.out.tfevents.1709483752.6974a0189950.34.2 +3 -0
  8. runs/Mar03_16-27-17_6974a0189950/events.out.tfevents.1709483760.6974a0189950.34.3 +3 -0
  9. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/vit-hybrid-base-bit-384
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - image_folder
8
+ model-index:
9
+ - name: vit-hybrid-base-bit-384-finetuned-cctv
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # vit-hybrid-base-bit-384-finetuned-cctv
17
+
18
+ This model is a fine-tuned version of [google/vit-hybrid-base-bit-384](https://huggingface.co/google/vit-hybrid-base-bit-384) on the image_folder dataset.
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
+ - train_batch_size: 32
39
+ - eval_batch_size: 32
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 4
42
+ - total_train_batch_size: 128
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_ratio: 0.1
46
+ - num_epochs: 3
47
+
48
+ ### Framework versions
49
+
50
+ - Transformers 4.38.1
51
+ - Pytorch 2.1.2
52
+ - Datasets 2.1.0
53
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-hybrid-base-bit-384",
3
+ "architectures": [
4
+ "ViTHybridForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "backbone": null,
8
+ "backbone_config": {
9
+ "depths": [
10
+ 3,
11
+ 4,
12
+ 9
13
+ ],
14
+ "embedding_dynamic_padding": true,
15
+ "global_padding": "SAME",
16
+ "layer_type": "bottleneck",
17
+ "model_type": "bit",
18
+ "out_features": [
19
+ "stage3"
20
+ ],
21
+ "out_indices": [
22
+ 3
23
+ ],
24
+ "stage_names": [
25
+ "stem",
26
+ "stage1",
27
+ "stage2",
28
+ "stage3"
29
+ ]
30
+ },
31
+ "backbone_featmap_shape": [
32
+ 1,
33
+ 1024,
34
+ 24,
35
+ 24
36
+ ],
37
+ "backbone_kwargs": null,
38
+ "hidden_act": "gelu",
39
+ "hidden_dropout_prob": 0.0,
40
+ "hidden_size": 768,
41
+ "id2label": {
42
+ "0": "Accident",
43
+ "1": "Non Accident"
44
+ },
45
+ "image_size": 384,
46
+ "initializer_range": 0.02,
47
+ "intermediate_size": 3072,
48
+ "label2id": {
49
+ "Accident": 0,
50
+ "Non Accident": 1
51
+ },
52
+ "layer_norm_eps": 1e-12,
53
+ "model_type": "vit-hybrid",
54
+ "num_attention_heads": 12,
55
+ "num_channels": 3,
56
+ "num_hidden_layers": 12,
57
+ "patch_size": 1,
58
+ "qkv_bias": true,
59
+ "torch_dtype": "float32",
60
+ "transformers_version": "4.38.1",
61
+ "use_pretrained_backbone": false,
62
+ "use_timm_backbone": false
63
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80ed8cf7d046a077fae3e7a58ba7e06d54392fe936da62e1c99ac2cbb304f00a
3
+ size 392780920
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 384,
4
+ "width": 384
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.5,
13
+ 0.5,
14
+ 0.5
15
+ ],
16
+ "image_processor_type": "ViTHybridImageProcessor",
17
+ "image_std": [
18
+ 0.5,
19
+ 0.5,
20
+ 0.5
21
+ ],
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "shortest_edge": 384
26
+ }
27
+ }
runs/Mar03_16-27-17_6974a0189950/events.out.tfevents.1709483301.6974a0189950.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be5ca10939303ec6dc2c95d6ceef6322fd2c969270644355460c1183121a35c4
3
+ size 14472
runs/Mar03_16-27-17_6974a0189950/events.out.tfevents.1709483714.6974a0189950.34.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5844114a72566d24118d4f2098aee84d56f1f76630e968c9dce438860aa1df8
3
+ size 8280
runs/Mar03_16-27-17_6974a0189950/events.out.tfevents.1709483752.6974a0189950.34.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:011bc5ee899bfd9b426896ab75a7872d15dad8bc0aecc5ef6f2fa61ba11b3206
3
+ size 4184
runs/Mar03_16-27-17_6974a0189950/events.out.tfevents.1709483760.6974a0189950.34.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b97e6625cc006354425f37550ef9cbb40842f2287ee5bbaa1625581e3a685111
3
+ size 4184
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:795591c2f7a8bdc118f03e84574990e201bf4fe84cd7aa95e51b53a713a243aa
3
+ size 4984