Hugging Face's logo

NRPU
/
detr-finetuned-balloon-v4

Object Detection
Transformers
PyTorch
Safetensors
detr
Inference Endpoints
Model card Files Community
NRPU commited on
Commit
aa54856
•
1 Parent(s): 4865f5f

Upload DetrForObjectDetection

Browse files
Files changed (2) hide show
  1. config.json +172 -174
  2. pytorch_model.bin +3 -0
config.json CHANGED
@@ -1,174 +1,172 @@
1
- {
2
- "_name_or_path": "facebook/detr-resnet-50",
3
- "activation_dropout": 0.0,
4
- "activation_function": "relu",
5
- "architectures": [
6
- "DetrForObjectDetection"
7
- ],
8
- "attention_dropout": 0.0,
9
- "auxiliary_loss": false,
10
- "backbone": null,
11
- "backbone_config": {
12
- "_name_or_path": "",
13
- "add_cross_attention": false,
14
- "architectures": null,
15
- "bad_words_ids": null,
16
- "begin_suppress_tokens": null,
17
- "bos_token_id": null,
18
- "chunk_size_feed_forward": 0,
19
- "cross_attention_hidden_size": null,
20
- "decoder_start_token_id": null,
21
- "depths": [
22
- 3,
23
- 4,
24
- 6,
25
- 3
26
- ],
27
- "diversity_penalty": 0.0,
28
- "do_sample": false,
29
- "downsample_in_bottleneck": false,
30
- "downsample_in_first_stage": false,
31
- "early_stopping": false,
32
- "embedding_size": 64,
33
- "encoder_no_repeat_ngram_size": 0,
34
- "eos_token_id": null,
35
- "exponential_decay_length_penalty": null,
36
- "finetuning_task": null,
37
- "forced_bos_token_id": null,
38
- "forced_eos_token_id": null,
39
- "hidden_act": "relu",
40
- "hidden_sizes": [
41
- 256,
42
- 512,
43
- 1024,
44
- 2048
45
- ],
46
- "id2label": {
47
- "0": "LABEL_0",
48
- "1": "LABEL_1"
49
- },
50
- "is_decoder": false,
51
- "is_encoder_decoder": false,
52
- "label2id": {
53
- "LABEL_0": 0,
54
- "LABEL_1": 1
55
- },
56
- "layer_type": "bottleneck",
57
- "length_penalty": 1.0,
58
- "max_length": 20,
59
- "min_length": 0,
60
- "model_type": "resnet",
61
- "no_repeat_ngram_size": 0,
62
- "num_beam_groups": 1,
63
- "num_beams": 1,
64
- "num_channels": 3,
65
- "num_return_sequences": 1,
66
- "out_features": [
67
- "stage4"
68
- ],
69
- "out_indices": [
70
- 4
71
- ],
72
- "output_attentions": false,
73
- "output_hidden_states": false,
74
- "output_scores": false,
75
- "pad_token_id": null,
76
- "prefix": null,
77
- "problem_type": null,
78
- "pruned_heads": {},
79
- "remove_invalid_values": false,
80
- "repetition_penalty": 1.0,
81
- "return_dict": true,
82
- "return_dict_in_generate": false,
83
- "sep_token_id": null,
84
- "stage_names": [
85
- "stem",
86
- "stage1",
87
- "stage2",
88
- "stage3",
89
- "stage4"
90
- ],
91
- "suppress_tokens": null,
92
- "task_specific_params": null,
93
- "temperature": 1.0,
94
- "tf_legacy_loss": false,
95
- "tie_encoder_decoder": false,
96
- "tie_word_embeddings": true,
97
- "tokenizer_class": null,
98
- "top_k": 50,
99
- "top_p": 1.0,
100
- "torch_dtype": null,
101
- "torchscript": false,
102
- "typical_p": 1.0,
103
- "use_bfloat16": false
104
- },
105
- "backbone_kwargs": null,
106
- "bbox_cost": 5,
107
- "bbox_loss_coefficient": 5,
108
- "class_cost": 1,
109
- "d_model": 256,
110
- "decoder_attention_heads": 8,
111
- "decoder_ffn_dim": 2048,
112
- "decoder_layerdrop": 0.0,
113
- "decoder_layers": 6,
114
- "dice_loss_coefficient": 1,
115
- "dilation": null,
116
- "dropout": 0.1,
117
- "encoder_attention_heads": 8,
118
- "encoder_ffn_dim": 2048,
119
- "encoder_layerdrop": 0.0,
120
- "encoder_layers": 6,
121
- "eos_coefficient": 0.1,
122
- "giou_cost": 2,
123
- "giou_loss_coefficient": 2,
124
- "id2label": {
125
- "0": "LABEL_0",
126
- "1": "LABEL_1",
127
- "2": "LABEL_2",
128
- "3": "LABEL_3",
129
- "4": "LABEL_4",
130
- "5": "LABEL_5",
131
- "6": "LABEL_6",
132
- "7": "LABEL_7",
133
- "8": "LABEL_8",
134
- "9": "LABEL_9",
135
- "10": "LABEL_10",
136
- "11": "LABEL_11",
137
- "12": "LABEL_12",
138
- "13": "LABEL_13",
139
- "14": "LABEL_14",
140
- "15": "LABEL_15"
141
- },
142
- "init_std": 0.02,
143
- "init_xavier_std": 1.0,
144
- "is_encoder_decoder": true,
145
- "label2id": {
146
- "LABEL_0": 0,
147
- "LABEL_1": 1,
148
- "LABEL_10": 10,
149
- "LABEL_11": 11,
150
- "LABEL_12": 12,
151
- "LABEL_13": 13,
152
- "LABEL_14": 14,
153
- "LABEL_15": 15,
154
- "LABEL_2": 2,
155
- "LABEL_3": 3,
156
- "LABEL_4": 4,
157
- "LABEL_5": 5,
158
- "LABEL_6": 6,
159
- "LABEL_7": 7,
160
- "LABEL_8": 8,
161
- "LABEL_9": 9
162
- },
163
- "mask_loss_coefficient": 1,
164
- "model_type": "detr",
165
- "num_channels": 3,
166
- "num_hidden_layers": 6,
167
- "num_queries": 100,
168
- "position_embedding_type": "sine",
169
- "scale_embedding": false,
170
- "torch_dtype": "float32",
171
- "transformers_version": "4.41.1",
172
- "use_pretrained_backbone": null,
173
- "use_timm_backbone": false
174
- }
 
1
+ {
2
+ "_name_or_path": "facebook/detr-resnet-50",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "DetrForObjectDetection"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "auxiliary_loss": false,
10
+ "backbone": null,
11
+ "backbone_config": {
12
+ "_name_or_path": "",
13
+ "add_cross_attention": false,
14
+ "architectures": null,
15
+ "bad_words_ids": null,
16
+ "begin_suppress_tokens": null,
17
+ "bos_token_id": null,
18
+ "chunk_size_feed_forward": 0,
19
+ "cross_attention_hidden_size": null,
20
+ "decoder_start_token_id": null,
21
+ "depths": [
22
+ 3,
23
+ 4,
24
+ 6,
25
+ 3
26
+ ],
27
+ "diversity_penalty": 0.0,
28
+ "do_sample": false,
29
+ "downsample_in_first_stage": false,
30
+ "early_stopping": false,
31
+ "embedding_size": 64,
32
+ "encoder_no_repeat_ngram_size": 0,
33
+ "eos_token_id": null,
34
+ "exponential_decay_length_penalty": null,
35
+ "finetuning_task": null,
36
+ "forced_bos_token_id": null,
37
+ "forced_eos_token_id": null,
38
+ "hidden_act": "relu",
39
+ "hidden_sizes": [
40
+ 256,
41
+ 512,
42
+ 1024,
43
+ 2048
44
+ ],
45
+ "id2label": {
46
+ "0": "LABEL_0",
47
+ "1": "LABEL_1"
48
+ },
49
+ "is_decoder": false,
50
+ "is_encoder_decoder": false,
51
+ "label2id": {
52
+ "LABEL_0": 0,
53
+ "LABEL_1": 1
54
+ },
55
+ "layer_type": "bottleneck",
56
+ "length_penalty": 1.0,
57
+ "max_length": 20,
58
+ "min_length": 0,
59
+ "model_type": "resnet",
60
+ "no_repeat_ngram_size": 0,
61
+ "num_beam_groups": 1,
62
+ "num_beams": 1,
63
+ "num_channels": 3,
64
+ "num_return_sequences": 1,
65
+ "out_features": [
66
+ "stage4"
67
+ ],
68
+ "out_indices": [
69
+ 4
70
+ ],
71
+ "output_attentions": false,
72
+ "output_hidden_states": false,
73
+ "output_scores": false,
74
+ "pad_token_id": null,
75
+ "prefix": null,
76
+ "problem_type": null,
77
+ "pruned_heads": {},
78
+ "remove_invalid_values": false,
79
+ "repetition_penalty": 1.0,
80
+ "return_dict": true,
81
+ "return_dict_in_generate": false,
82
+ "sep_token_id": null,
83
+ "stage_names": [
84
+ "stem",
85
+ "stage1",
86
+ "stage2",
87
+ "stage3",
88
+ "stage4"
89
+ ],
90
+ "suppress_tokens": null,
91
+ "task_specific_params": null,
92
+ "temperature": 1.0,
93
+ "tf_legacy_loss": false,
94
+ "tie_encoder_decoder": false,
95
+ "tie_word_embeddings": true,
96
+ "tokenizer_class": null,
97
+ "top_k": 50,
98
+ "top_p": 1.0,
99
+ "torch_dtype": null,
100
+ "torchscript": false,
101
+ "typical_p": 1.0,
102
+ "use_bfloat16": false
103
+ },
104
+ "bbox_cost": 5,
105
+ "bbox_loss_coefficient": 5,
106
+ "class_cost": 1,
107
+ "d_model": 256,
108
+ "decoder_attention_heads": 8,
109
+ "decoder_ffn_dim": 2048,
110
+ "decoder_layerdrop": 0.0,
111
+ "decoder_layers": 6,
112
+ "dice_loss_coefficient": 1,
113
+ "dilation": null,
114
+ "dropout": 0.1,
115
+ "encoder_attention_heads": 8,
116
+ "encoder_ffn_dim": 2048,
117
+ "encoder_layerdrop": 0.0,
118
+ "encoder_layers": 6,
119
+ "eos_coefficient": 0.1,
120
+ "giou_cost": 2,
121
+ "giou_loss_coefficient": 2,
122
+ "id2label": {
123
+ "0": "LABEL_0",
124
+ "1": "LABEL_1",
125
+ "2": "LABEL_2",
126
+ "3": "LABEL_3",
127
+ "4": "LABEL_4",
128
+ "5": "LABEL_5",
129
+ "6": "LABEL_6",
130
+ "7": "LABEL_7",
131
+ "8": "LABEL_8",
132
+ "9": "LABEL_9",
133
+ "10": "LABEL_10",
134
+ "11": "LABEL_11",
135
+ "12": "LABEL_12",
136
+ "13": "LABEL_13",
137
+ "14": "LABEL_14",
138
+ "15": "LABEL_15"
139
+ },
140
+ "init_std": 0.02,
141
+ "init_xavier_std": 1.0,
142
+ "is_encoder_decoder": true,
143
+ "label2id": {
144
+ "LABEL_0": 0,
145
+ "LABEL_1": 1,
146
+ "LABEL_10": 10,
147
+ "LABEL_11": 11,
148
+ "LABEL_12": 12,
149
+ "LABEL_13": 13,
150
+ "LABEL_14": 14,
151
+ "LABEL_15": 15,
152
+ "LABEL_2": 2,
153
+ "LABEL_3": 3,
154
+ "LABEL_4": 4,
155
+ "LABEL_5": 5,
156
+ "LABEL_6": 6,
157
+ "LABEL_7": 7,
158
+ "LABEL_8": 8,
159
+ "LABEL_9": 9
160
+ },
161
+ "mask_loss_coefficient": 1,
162
+ "model_type": "detr",
163
+ "num_channels": 3,
164
+ "num_hidden_layers": 6,
165
+ "num_queries": 100,
166
+ "position_embedding_type": "sine",
167
+ "scale_embedding": false,
168
+ "torch_dtype": "float32",
169
+ "transformers_version": "4.32.1",
170
+ "use_pretrained_backbone": null,
171
+ "use_timm_backbone": false
172
+ }
 
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c32d3cba6547867add96a9cd347fbde199cb224ce383d6b643fa957898f779a6
3
+ size 166632018