xiuqhou commited on
Commit
a284cba
·
verified ·
1 Parent(s): d276149

Upload RelationDetrForObjectDetection

Browse files
Files changed (3) hide show
  1. README.md +199 -0
  2. config.json +241 -0
  3. model.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,199 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags: []
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+ This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
config.json ADDED
@@ -0,0 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "relu",
4
+ "architectures": [
5
+ "RelationDetrForObjectDetection"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "backbone": "swin_large_patch4_window7_224",
9
+ "backbone_config": null,
10
+ "backbone_kwargs": {
11
+ "dynamic_img_pad": true,
12
+ "img_size": null,
13
+ "out_indices": [
14
+ 1,
15
+ 2,
16
+ 3
17
+ ],
18
+ "strict_img_size": false
19
+ },
20
+ "bbox_cost": 5,
21
+ "bbox_loss_coefficient": 5,
22
+ "box_noise_scale": 1.0,
23
+ "class_cost": 2,
24
+ "class_loss_coefficient": 1,
25
+ "d_model": 256,
26
+ "d_relation": 16,
27
+ "decoder_attention_heads": 8,
28
+ "decoder_ffn_dim": 2048,
29
+ "decoder_layers": 6,
30
+ "decoder_n_points": 4,
31
+ "dilation": false,
32
+ "disable_custom_kernels": false,
33
+ "dropout": 0.0,
34
+ "encoder_attention_heads": 8,
35
+ "encoder_ffn_dim": 2048,
36
+ "encoder_layers": 6,
37
+ "encoder_n_points": 4,
38
+ "focal_alpha": 0.25,
39
+ "focal_gamma": 2.0,
40
+ "giou_cost": 2,
41
+ "giou_loss_coefficient": 2,
42
+ "hybrid_assign": 6,
43
+ "hybrid_queries": 1500,
44
+ "id2label": {
45
+ "0": "none",
46
+ "1": "person",
47
+ "2": "bicycle",
48
+ "3": "car",
49
+ "4": "motorcycle",
50
+ "5": "airplane",
51
+ "6": "bus",
52
+ "7": "train",
53
+ "8": "truck",
54
+ "9": "boat",
55
+ "10": "traffic light",
56
+ "11": "fire hydrant",
57
+ "12": "none",
58
+ "13": "stop sign",
59
+ "14": "parking meter",
60
+ "15": "bench",
61
+ "16": "bird",
62
+ "17": "cat",
63
+ "18": "dog",
64
+ "19": "horse",
65
+ "20": "sheep",
66
+ "21": "cow",
67
+ "22": "elephant",
68
+ "23": "bear",
69
+ "24": "zebra",
70
+ "25": "giraffe",
71
+ "26": "none",
72
+ "27": "backpack",
73
+ "28": "umbrella",
74
+ "29": "none",
75
+ "30": "none",
76
+ "31": "handbag",
77
+ "32": "tie",
78
+ "33": "suitcase",
79
+ "34": "frisbee",
80
+ "35": "skis",
81
+ "36": "snowboard",
82
+ "37": "sports ball",
83
+ "38": "kite",
84
+ "39": "baseball bat",
85
+ "40": "baseball glove",
86
+ "41": "skateboard",
87
+ "42": "surfboard",
88
+ "43": "tennis racket",
89
+ "44": "bottle",
90
+ "45": "none",
91
+ "46": "wine glass",
92
+ "47": "cup",
93
+ "48": "fork",
94
+ "49": "knife",
95
+ "50": "spoon",
96
+ "51": "bowl",
97
+ "52": "banana",
98
+ "53": "apple",
99
+ "54": "sandwich",
100
+ "55": "orange",
101
+ "56": "broccoli",
102
+ "57": "carrot",
103
+ "58": "hot dog",
104
+ "59": "pizza",
105
+ "60": "donut",
106
+ "61": "cake",
107
+ "62": "chair",
108
+ "63": "couch",
109
+ "64": "potted plant",
110
+ "65": "bed",
111
+ "66": "none",
112
+ "67": "dining table",
113
+ "68": "none",
114
+ "69": "none",
115
+ "70": "toilet",
116
+ "71": "none",
117
+ "72": "tv",
118
+ "73": "laptop",
119
+ "74": "mouse",
120
+ "75": "remote",
121
+ "76": "keyboard",
122
+ "77": "cell phone",
123
+ "78": "microwave",
124
+ "79": "oven",
125
+ "80": "toaster",
126
+ "81": "sink",
127
+ "82": "refrigerator",
128
+ "83": "none",
129
+ "84": "book",
130
+ "85": "clock",
131
+ "86": "vase",
132
+ "87": "scissors",
133
+ "88": "teddy bear",
134
+ "89": "hair drier",
135
+ "90": "toothbrush"
136
+ },
137
+ "init_std": 0.02,
138
+ "init_xavier_std": 1.0,
139
+ "is_encoder_decoder": true,
140
+ "label2id": {
141
+ "airplane": 5,
142
+ "apple": 53,
143
+ "backpack": 27,
144
+ "banana": 52,
145
+ "baseball bat": 39,
146
+ "baseball glove": 40,
147
+ "bear": 23,
148
+ "bed": 65,
149
+ "bench": 15,
150
+ "bicycle": 2,
151
+ "bird": 16,
152
+ "boat": 9,
153
+ "book": 84,
154
+ "bottle": 44,
155
+ "bowl": 51,
156
+ "broccoli": 56,
157
+ "bus": 6,
158
+ "cake": 61,
159
+ "car": 3,
160
+ "carrot": 57,
161
+ "cat": 17,
162
+ "cell phone": 77,
163
+ "chair": 62,
164
+ "clock": 85,
165
+ "couch": 63,
166
+ "cow": 21,
167
+ "cup": 47,
168
+ "dining table": 67,
169
+ "dog": 18,
170
+ "donut": 60,
171
+ "elephant": 22,
172
+ "fire hydrant": 11,
173
+ "fork": 48,
174
+ "frisbee": 34,
175
+ "giraffe": 25,
176
+ "hair drier": 89,
177
+ "handbag": 31,
178
+ "horse": 19,
179
+ "hot dog": 58,
180
+ "keyboard": 76,
181
+ "kite": 38,
182
+ "knife": 49,
183
+ "laptop": 73,
184
+ "microwave": 78,
185
+ "motorcycle": 4,
186
+ "mouse": 74,
187
+ "none": 83,
188
+ "orange": 55,
189
+ "oven": 79,
190
+ "parking meter": 14,
191
+ "person": 1,
192
+ "pizza": 59,
193
+ "potted plant": 64,
194
+ "refrigerator": 82,
195
+ "remote": 75,
196
+ "sandwich": 54,
197
+ "scissors": 87,
198
+ "sheep": 20,
199
+ "sink": 81,
200
+ "skateboard": 41,
201
+ "skis": 35,
202
+ "snowboard": 36,
203
+ "spoon": 50,
204
+ "sports ball": 37,
205
+ "stop sign": 13,
206
+ "suitcase": 33,
207
+ "surfboard": 42,
208
+ "teddy bear": 88,
209
+ "tennis racket": 43,
210
+ "tie": 32,
211
+ "toaster": 80,
212
+ "toilet": 70,
213
+ "toothbrush": 90,
214
+ "traffic light": 10,
215
+ "train": 7,
216
+ "truck": 8,
217
+ "tv": 72,
218
+ "umbrella": 28,
219
+ "vase": 86,
220
+ "wine glass": 46,
221
+ "zebra": 24
222
+ },
223
+ "label_noise_ratio": 0.5,
224
+ "model_type": "relation_detr",
225
+ "num_channels": 3,
226
+ "num_denoising": 100,
227
+ "num_feature_levels": 4,
228
+ "num_queries": 900,
229
+ "position_embedding_type": "sine",
230
+ "rel_scale": 100,
231
+ "rel_temperature": 10000,
232
+ "sin_cos_normalize": true,
233
+ "sin_cos_offset": -0.5,
234
+ "sin_cos_scale": 6.283185307179586,
235
+ "sin_cos_temperature": 10000,
236
+ "torch_dtype": "float32",
237
+ "transformers_version": "4.47.0.dev0",
238
+ "two_stage_binary_cls": false,
239
+ "use_pretrained_backbone": false,
240
+ "use_timm_backbone": true
241
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fc5aed7893aefed8efdd2f388bd8cb24354cd63645e7465e5cbcf4284946900
3
+ size 876072424