danelcsb commited on
Commit
041288b
1 Parent(s): 0062ca7

Model save

Browse files
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: IDEA-Research/grounding-dino-tiny
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: grounding-dino-tiny-finetuned-cppe-5-10k-steps
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # grounding-dino-tiny-finetuned-cppe-5-10k-steps
15
+
16
+ This model is a fine-tuned version of [IDEA-Research/grounding-dino-tiny](https://huggingface.co/IDEA-Research/grounding-dino-tiny) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 5.5317
19
+ - Map: 0.0151
20
+ - Map 50: 0.0275
21
+ - Map 75: 0.0157
22
+ - Map Small: 0.0125
23
+ - Map Medium: 0.0149
24
+ - Map Large: 0.0236
25
+ - Mar 1: 0.0202
26
+ - Mar 10: 0.0902
27
+ - Mar 100: 0.1127
28
+ - Mar Small: 0.0815
29
+ - Mar Medium: 0.0975
30
+ - Mar Large: 0.1461
31
+ - Map Coverall: 0.0755
32
+ - Mar 100 Coverall: 0.5636
33
+ - Map Face Shield: 0.0
34
+ - Mar 100 Face Shield: 0.0
35
+ - Map Gloves: 0.0
36
+ - Mar 100 Gloves: 0.0
37
+ - Map Goggles: 0.0
38
+ - Mar 100 Goggles: 0.0
39
+ - Map Mask: 0.0
40
+ - Mar 100 Mask: 0.0
41
+
42
+ ## Model description
43
+
44
+ More information needed
45
+
46
+ ## Intended uses & limitations
47
+
48
+ More information needed
49
+
50
+ ## Training and evaluation data
51
+
52
+ More information needed
53
+
54
+ ## Training procedure
55
+
56
+ ### Training hyperparameters
57
+
58
+ The following hyperparameters were used during training:
59
+ - learning_rate: 5e-05
60
+ - train_batch_size: 1
61
+ - eval_batch_size: 1
62
+ - seed: 1337
63
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
+ - lr_scheduler_type: linear
65
+ - num_epochs: 10.0
66
+
67
+ ### Training results
68
+
69
+ | Training Loss | Epoch | Step | Validation Loss | Map | Map 50 | Map 75 | Map Small | Map Medium | Map Large | Mar 1 | Mar 10 | Mar 100 | Mar Small | Mar Medium | Mar Large | Map Coverall | Mar 100 Coverall | Map Face Shield | Mar 100 Face Shield | Map Gloves | Mar 100 Gloves | Map Goggles | Mar 100 Goggles | Map Mask | Mar 100 Mask |
70
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:------------:|:----------------:|:---------------:|:-------------------:|:----------:|:--------------:|:-----------:|:---------------:|:--------:|:------------:|
71
+ | 8355.9482 | 1.0 | 850 | 6.6137 | 0.014 | 0.0272 | 0.0134 | 0.0048 | 0.0111 | 0.0243 | 0.0149 | 0.0893 | 0.1073 | 0.0523 | 0.0889 | 0.1328 | 0.0702 | 0.5366 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
72
+ | 6.7523 | 2.0 | 1700 | 6.2357 | 0.0162 | 0.0302 | 0.0148 | 0.0106 | 0.0189 | 0.0192 | 0.0247 | 0.0894 | 0.107 | 0.0643 | 0.0968 | 0.1258 | 0.0809 | 0.535 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
73
+ | 6.5566 | 3.0 | 2550 | 6.0890 | 0.0158 | 0.0294 | 0.0134 | 0.01 | 0.0199 | 0.0215 | 0.0222 | 0.0876 | 0.1065 | 0.0671 | 0.0846 | 0.1324 | 0.0791 | 0.5323 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
74
+ | 6.2217 | 4.0 | 3400 | 5.9028 | 0.0144 | 0.0271 | 0.0134 | 0.0066 | 0.0096 | 0.0225 | 0.0232 | 0.0857 | 0.107 | 0.06 | 0.0823 | 0.1397 | 0.0721 | 0.5348 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
75
+ | 6.0963 | 5.0 | 4250 | 5.8411 | 0.0126 | 0.0215 | 0.014 | 0.0055 | 0.0138 | 0.0178 | 0.0201 | 0.0811 | 0.1052 | 0.044 | 0.0942 | 0.1377 | 0.0631 | 0.5258 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
76
+ | 5.996 | 6.0 | 5100 | 5.7244 | 0.0162 | 0.0311 | 0.0166 | 0.0059 | 0.0145 | 0.0221 | 0.0223 | 0.0869 | 0.1088 | 0.0667 | 0.0919 | 0.1328 | 0.0812 | 0.5437 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
77
+ | 5.8971 | 7.0 | 5950 | 5.5473 | 0.0154 | 0.027 | 0.016 | 0.01 | 0.014 | 0.0208 | 0.0244 | 0.0946 | 0.1154 | 0.084 | 0.106 | 0.1311 | 0.0769 | 0.5772 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
78
+ | 5.7451 | 8.0 | 6800 | 5.5231 | 0.0146 | 0.0267 | 0.0148 | 0.0021 | 0.0161 | 0.0183 | 0.0256 | 0.0905 | 0.1125 | 0.0325 | 0.1062 | 0.128 | 0.0731 | 0.5624 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
79
+ | 5.7931 | 9.0 | 7650 | 5.5190 | 0.0182 | 0.032 | 0.0195 | 0.0175 | 0.0147 | 0.0249 | 0.0299 | 0.1048 | 0.1138 | 0.08 | 0.0945 | 0.1309 | 0.091 | 0.5688 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
80
+ | 5.7435 | 10.0 | 8500 | 5.5317 | 0.0151 | 0.0275 | 0.0157 | 0.0125 | 0.0149 | 0.0236 | 0.0202 | 0.0902 | 0.1127 | 0.0815 | 0.0975 | 0.1461 | 0.0755 | 0.5636 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
81
+
82
+
83
+ ### Framework versions
84
+
85
+ - Transformers 4.45.0.dev0
86
+ - Pytorch 2.2.2
87
+ - Datasets 2.20.0
88
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "IDEA-Research/grounding-dino-tiny",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "GroundingDinoForObjectDetection"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "auxiliary_loss": false,
10
+ "backbone": null,
11
+ "backbone_config": {
12
+ "model_type": "swin",
13
+ "out_features": [
14
+ "stage2",
15
+ "stage3",
16
+ "stage4"
17
+ ],
18
+ "out_indices": [
19
+ 2,
20
+ 3,
21
+ 4
22
+ ]
23
+ },
24
+ "backbone_kwargs": null,
25
+ "bbox_cost": 5.0,
26
+ "bbox_loss_coefficient": 5.0,
27
+ "class_cost": 1.0,
28
+ "class_loss_coefficient": 2.0,
29
+ "class_loss_reduction": "sum",
30
+ "d_model": 256,
31
+ "decoder_attention_heads": 8,
32
+ "decoder_bbox_embed_share": true,
33
+ "decoder_ffn_dim": 2048,
34
+ "decoder_layers": 6,
35
+ "decoder_n_points": 4,
36
+ "disable_custom_kernels": false,
37
+ "dropout": 0.1,
38
+ "embedding_init_target": true,
39
+ "encoder_attention_heads": 8,
40
+ "encoder_ffn_dim": 2048,
41
+ "encoder_layers": 6,
42
+ "encoder_n_points": 4,
43
+ "focal_alpha": 0.25,
44
+ "fusion_dropout": 0.0,
45
+ "fusion_droppath": 0.1,
46
+ "giou_cost": 2.0,
47
+ "giou_loss_coefficient": 2.0,
48
+ "id2label": {
49
+ "0": "Coverall",
50
+ "1": "Face_Shield",
51
+ "2": "Gloves",
52
+ "3": "Goggles",
53
+ "4": "Mask"
54
+ },
55
+ "init_std": 0.02,
56
+ "is_encoder_decoder": true,
57
+ "label2id": {
58
+ "Coverall": 0,
59
+ "Face_Shield": 1,
60
+ "Gloves": 2,
61
+ "Goggles": 3,
62
+ "Mask": 4
63
+ },
64
+ "layer_norm_eps": 1e-05,
65
+ "max_text_len": 256,
66
+ "model_type": "grounding-dino",
67
+ "num_feature_levels": 4,
68
+ "num_queries": 900,
69
+ "position_embedding_type": "sine",
70
+ "positional_embedding_temperature": 20,
71
+ "query_dim": 4,
72
+ "text_config": {
73
+ "model_type": "bert"
74
+ },
75
+ "text_enhancer_dropout": 0.0,
76
+ "torch_dtype": "float32",
77
+ "transformers_version": "4.45.0.dev0",
78
+ "two_stage": true,
79
+ "two_stage_bbox_embed_share": false,
80
+ "use_pretrained_backbone": false,
81
+ "use_timm_backbone": false
82
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:787fe7c9de7d70cb3a0bbe8b1cab074f3668e0061211104b814c83a49edbc33d
3
+ size 689359096
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_annotations": true,
3
+ "do_normalize": true,
4
+ "do_pad": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "format": "coco_detection",
8
+ "image_mean": [
9
+ 0.485,
10
+ 0.456,
11
+ 0.406
12
+ ],
13
+ "image_processor_type": "GroundingDinoImageProcessor",
14
+ "image_std": [
15
+ 0.229,
16
+ 0.224,
17
+ 0.225
18
+ ],
19
+ "pad_size": null,
20
+ "processor_class": "GroundingDinoProcessor",
21
+ "resample": 2,
22
+ "rescale_factor": 0.00392156862745098,
23
+ "size": {
24
+ "longest_edge": 1333,
25
+ "shortest_edge": 800
26
+ }
27
+ }
runs/Aug08_23-59-04_4553f658f331/events.out.tfevents.1723161558.4553f658f331.26688.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31b381e3ce13c2917d292f572f013f1bb10666510221575adb6fb5e68b33f42e
3
+ size 6527
runs/Aug09_00-00-24_4553f658f331/events.out.tfevents.1723161638.4553f658f331.28126.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:657745056f24983870e85a41908110fe6440c7332488c11ad04d218aaae4b3ab
3
+ size 6527
runs/Aug09_00-04-29_4553f658f331/events.out.tfevents.1723161885.4553f658f331.29564.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50e204141f07b59e9604b535cbc3176368575864e926b8403fd93769e3fb3b02
3
+ size 6527
runs/Aug09_00-06-15_4553f658f331/events.out.tfevents.1723161989.4553f658f331.31003.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:defdcd94d7c40a160d336a66e9d94125f7a0d278d2252cecf725346130d81bf1
3
+ size 6527
runs/Aug09_00-08-23_4553f658f331/events.out.tfevents.1723162117.4553f658f331.32441.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec4459f47197437c727f28d50eb4296ddb122fd6da4055172a0ef649e6c0c64b
3
+ size 9807
runs/Aug09_00-09-54_4553f658f331/events.out.tfevents.1723162210.4553f658f331.35864.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bba9dfbf5143dc0bc2fbb5c78f6c9694332394c4d937e798d1ac107c7a95c6e3
3
+ size 7961
runs/Aug09_00-11-01_4553f658f331/events.out.tfevents.1723162276.4553f658f331.37956.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eebdbae3f46203b8dc71eea34601b4e6bc2dad2d56cea90b438134b889cd58bb
3
+ size 12880
runs/Aug09_04-33-55_a44b5742ff80/events.out.tfevents.1723178053.a44b5742ff80.5133.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79a8eeb2dd6c9a3e511465feaca41cae7a19445c7f12439c4a1a64e6363cd986
3
+ size 7991
runs/Aug09_04-42-08_a44b5742ff80/events.out.tfevents.1723178546.a44b5742ff80.6692.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f489a2cae806af50c8456ce8eb6393f344e72c6f19c33ab029e0d3f2d275d92e
3
+ size 23385
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "processor_class": "GroundingDinoProcessor",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25039c49df114f4fad99be56baee1461adb2a82290ece3a9f9f27957a49cacfe
3
+ size 5368
vocab.txt ADDED
The diff for this file is too large to render. See raw diff