Object Detection
Transformers
Safetensors
English
d_fine
vision
vladislavbro commited on
Commit
3e79c95
·
verified ·
1 Parent(s): 5073ce6

Add config from convert_d_fine_original_pytorch_checkpoint_to_hf.py

Browse files
Files changed (2) hide show
  1. README.md +199 -0
  2. config.json +919 -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 +1,919 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "silu",
5
+ "anchor_image_size": null,
6
+ "attention_dropout": 0.0,
7
+ "auxiliary_loss": true,
8
+ "backbone": null,
9
+ "backbone_config": {
10
+ "depths": [
11
+ 3,
12
+ 4,
13
+ 6,
14
+ 3
15
+ ],
16
+ "downsample_in_bottleneck": false,
17
+ "downsample_in_first_stage": false,
18
+ "embedding_size": 32,
19
+ "hidden_act": "relu",
20
+ "hidden_sizes": [
21
+ 192,
22
+ 384,
23
+ 768,
24
+ 1536
25
+ ],
26
+ "initializer_range": 0.02,
27
+ "layer_type": "basic",
28
+ "model_type": "hgnet_v2",
29
+ "num_channels": 3,
30
+ "out_features": [
31
+ "stage2",
32
+ "stage3",
33
+ "stage4"
34
+ ],
35
+ "out_indices": [
36
+ 2,
37
+ 3,
38
+ 4
39
+ ],
40
+ "stage_downsample": [
41
+ false,
42
+ true,
43
+ true,
44
+ true
45
+ ],
46
+ "stage_in_channels": [
47
+ 32,
48
+ 96,
49
+ 384,
50
+ 768
51
+ ],
52
+ "stage_kernel_size": [
53
+ 3,
54
+ 3,
55
+ 5,
56
+ 5
57
+ ],
58
+ "stage_light_block": [
59
+ false,
60
+ false,
61
+ true,
62
+ true
63
+ ],
64
+ "stage_mid_channels": [
65
+ 32,
66
+ 64,
67
+ 128,
68
+ 256
69
+ ],
70
+ "stage_names": [
71
+ "stem",
72
+ "stage1",
73
+ "stage2",
74
+ "stage3",
75
+ "stage4"
76
+ ],
77
+ "stage_num_blocks": [
78
+ 1,
79
+ 1,
80
+ 3,
81
+ 1
82
+ ],
83
+ "stage_numb_of_layers": [
84
+ 4,
85
+ 4,
86
+ 4,
87
+ 4
88
+ ],
89
+ "stage_out_channels": [
90
+ 96,
91
+ 384,
92
+ 768,
93
+ 1536
94
+ ],
95
+ "stem_channels": [
96
+ 3,
97
+ 24,
98
+ 32
99
+ ],
100
+ "use_learnable_affine_block": true
101
+ },
102
+ "backbone_kwargs": null,
103
+ "batch_norm_eps": 1e-05,
104
+ "box_noise_scale": 1.0,
105
+ "d_model": 256,
106
+ "decoder_activation_function": "relu",
107
+ "decoder_attention_heads": 8,
108
+ "decoder_ffn_dim": 1024,
109
+ "decoder_in_channels": [
110
+ 256,
111
+ 256,
112
+ 256
113
+ ],
114
+ "decoder_layers": 4,
115
+ "decoder_method": "default",
116
+ "decoder_n_points": [
117
+ 3,
118
+ 6,
119
+ 3
120
+ ],
121
+ "decoder_offset_scale": 0.5,
122
+ "depth_mult": 0.67,
123
+ "dropout": 0.0,
124
+ "encode_proj_layers": [
125
+ 2
126
+ ],
127
+ "encoder_activation_function": "gelu",
128
+ "encoder_attention_heads": 8,
129
+ "encoder_ffn_dim": 1024,
130
+ "encoder_hidden_dim": 256,
131
+ "encoder_in_channels": [
132
+ 384,
133
+ 768,
134
+ 1536
135
+ ],
136
+ "encoder_layers": 1,
137
+ "eos_coefficient": 0.0001,
138
+ "eval_idx": -1,
139
+ "eval_size": null,
140
+ "feat_strides": [
141
+ 8,
142
+ 16,
143
+ 32
144
+ ],
145
+ "focal_loss_alpha": 0.75,
146
+ "focal_loss_gamma": 2.0,
147
+ "freeze_backbone_batch_norms": true,
148
+ "hidden_expansion": 1.0,
149
+ "id2label": {
150
+ "0": "None",
151
+ "1": "Person",
152
+ "2": "Sneakers",
153
+ "3": "Chair",
154
+ "4": "Other Shoes",
155
+ "5": "Hat",
156
+ "6": "Car",
157
+ "7": "Lamp",
158
+ "8": "Glasses",
159
+ "9": "Bottle",
160
+ "10": "Desk",
161
+ "11": "Cup",
162
+ "12": "Street Lights",
163
+ "13": "Cabinet/shelf",
164
+ "14": "Handbag/Satchel",
165
+ "15": "Bracelet",
166
+ "16": "Plate",
167
+ "17": "Picture/Frame",
168
+ "18": "Helmet",
169
+ "19": "Book",
170
+ "20": "Gloves",
171
+ "21": "Storage box",
172
+ "22": "Boat",
173
+ "23": "Leather Shoes",
174
+ "24": "Flower",
175
+ "25": "Bench",
176
+ "26": "Potted Plant",
177
+ "27": "Bowl/Basin",
178
+ "28": "Flag",
179
+ "29": "Pillow",
180
+ "30": "Boots",
181
+ "31": "Vase",
182
+ "32": "Microphone",
183
+ "33": "Necklace",
184
+ "34": "Ring",
185
+ "35": "SUV",
186
+ "36": "Wine Glass",
187
+ "37": "Belt",
188
+ "38": "Monitor/TV",
189
+ "39": "Backpack",
190
+ "40": "Umbrella",
191
+ "41": "Traffic Light",
192
+ "42": "Speaker",
193
+ "43": "Watch",
194
+ "44": "Tie",
195
+ "45": "Trash bin Can",
196
+ "46": "Slippers",
197
+ "47": "Bicycle",
198
+ "48": "Stool",
199
+ "49": "Barrel/bucket",
200
+ "50": "Van",
201
+ "51": "Couch",
202
+ "52": "Sandals",
203
+ "53": "Basket",
204
+ "54": "Drum",
205
+ "55": "Pen/Pencil",
206
+ "56": "Bus",
207
+ "57": "Wild Bird",
208
+ "58": "High Heels",
209
+ "59": "Motorcycle",
210
+ "60": "Guitar",
211
+ "61": "Carpet",
212
+ "62": "Cell Phone",
213
+ "63": "Bread",
214
+ "64": "Camera",
215
+ "65": "Canned",
216
+ "66": "Truck",
217
+ "67": "Traffic cone",
218
+ "68": "Cymbal",
219
+ "69": "Lifesaver",
220
+ "70": "Towel",
221
+ "71": "Stuffed Toy",
222
+ "72": "Candle",
223
+ "73": "Sailboat",
224
+ "74": "Laptop",
225
+ "75": "Awning",
226
+ "76": "Bed",
227
+ "77": "Faucet",
228
+ "78": "Tent",
229
+ "79": "Horse",
230
+ "80": "Mirror",
231
+ "81": "Power outlet",
232
+ "82": "Sink",
233
+ "83": "Apple",
234
+ "84": "Air Conditioner",
235
+ "85": "Knife",
236
+ "86": "Hockey Stick",
237
+ "87": "Paddle",
238
+ "88": "Pickup Truck",
239
+ "89": "Fork",
240
+ "90": "Traffic Sign",
241
+ "91": "Balloon",
242
+ "92": "Tripod",
243
+ "93": "Dog",
244
+ "94": "Spoon",
245
+ "95": "Clock",
246
+ "96": "Pot",
247
+ "97": "Cow",
248
+ "98": "Cake",
249
+ "99": "Dinning Table",
250
+ "100": "Sheep",
251
+ "101": "Hanger",
252
+ "102": "Blackboard/Whiteboard",
253
+ "103": "Napkin",
254
+ "104": "Other Fish",
255
+ "105": "Orange/Tangerine",
256
+ "106": "Toiletry",
257
+ "107": "Keyboard",
258
+ "108": "Tomato",
259
+ "109": "Lantern",
260
+ "110": "Machinery Vehicle",
261
+ "111": "Fan",
262
+ "112": "Green Vegetables",
263
+ "113": "Banana",
264
+ "114": "Baseball Glove",
265
+ "115": "Airplane",
266
+ "116": "Mouse",
267
+ "117": "Train",
268
+ "118": "Pumpkin",
269
+ "119": "Soccer",
270
+ "120": "Skiboard",
271
+ "121": "Luggage",
272
+ "122": "Nightstand",
273
+ "123": "Tea pot",
274
+ "124": "Telephone",
275
+ "125": "Trolley",
276
+ "126": "Head Phone",
277
+ "127": "Sports Car",
278
+ "128": "Stop Sign",
279
+ "129": "Dessert",
280
+ "130": "Scooter",
281
+ "131": "Stroller",
282
+ "132": "Crane",
283
+ "133": "Remote",
284
+ "134": "Refrigerator",
285
+ "135": "Oven",
286
+ "136": "Lemon",
287
+ "137": "Duck",
288
+ "138": "Baseball Bat",
289
+ "139": "Surveillance Camera",
290
+ "140": "Cat",
291
+ "141": "Jug",
292
+ "142": "Broccoli",
293
+ "143": "Piano",
294
+ "144": "Pizza",
295
+ "145": "Elephant",
296
+ "146": "Skateboard",
297
+ "147": "Surfboard",
298
+ "148": "Gun",
299
+ "149": "Skating and Skiing shoes",
300
+ "150": "Gas stove",
301
+ "151": "Donut",
302
+ "152": "Bow Tie",
303
+ "153": "Carrot",
304
+ "154": "Toilet",
305
+ "155": "Kite",
306
+ "156": "Strawberry",
307
+ "157": "Other Balls",
308
+ "158": "Shovel",
309
+ "159": "Pepper",
310
+ "160": "Computer Box",
311
+ "161": "Toilet Paper",
312
+ "162": "Cleaning Products",
313
+ "163": "Chopsticks",
314
+ "164": "Microwave",
315
+ "165": "Pigeon",
316
+ "166": "Baseball",
317
+ "167": "Cutting/chopping Board",
318
+ "168": "Coffee Table",
319
+ "169": "Side Table",
320
+ "170": "Scissors",
321
+ "171": "Marker",
322
+ "172": "Pie",
323
+ "173": "Ladder",
324
+ "174": "Snowboard",
325
+ "175": "Cookies",
326
+ "176": "Radiator",
327
+ "177": "Fire Hydrant",
328
+ "178": "Basketball",
329
+ "179": "Zebra",
330
+ "180": "Grape",
331
+ "181": "Giraffe",
332
+ "182": "Potato",
333
+ "183": "Sausage",
334
+ "184": "Tricycle",
335
+ "185": "Violin",
336
+ "186": "Egg",
337
+ "187": "Fire Extinguisher",
338
+ "188": "Candy",
339
+ "189": "Fire Truck",
340
+ "190": "Billiards",
341
+ "191": "Converter",
342
+ "192": "Bathtub",
343
+ "193": "Wheelchair",
344
+ "194": "Golf Club",
345
+ "195": "Briefcase",
346
+ "196": "Cucumber",
347
+ "197": "Cigar/Cigarette",
348
+ "198": "Paint Brush",
349
+ "199": "Pear",
350
+ "200": "Heavy Truck",
351
+ "201": "Hamburger",
352
+ "202": "Extractor",
353
+ "203": "Extension Cord",
354
+ "204": "Tong",
355
+ "205": "Tennis Racket",
356
+ "206": "Folder",
357
+ "207": "American Football",
358
+ "208": "earphone",
359
+ "209": "Mask",
360
+ "210": "Kettle",
361
+ "211": "Tennis",
362
+ "212": "Ship",
363
+ "213": "Swing",
364
+ "214": "Coffee Machine",
365
+ "215": "Slide",
366
+ "216": "Carriage",
367
+ "217": "Onion",
368
+ "218": "Green beans",
369
+ "219": "Projector",
370
+ "220": "Frisbee",
371
+ "221": "Washing Machine/Drying Machine",
372
+ "222": "Chicken",
373
+ "223": "Printer",
374
+ "224": "Watermelon",
375
+ "225": "Saxophone",
376
+ "226": "Tissue",
377
+ "227": "Toothbrush",
378
+ "228": "Ice cream",
379
+ "229": "Hot-air balloon",
380
+ "230": "Cello",
381
+ "231": "French Fries",
382
+ "232": "Scale",
383
+ "233": "Trophy",
384
+ "234": "Cabbage",
385
+ "235": "Hot dog",
386
+ "236": "Blender",
387
+ "237": "Peach",
388
+ "238": "Rice",
389
+ "239": "Wallet/Purse",
390
+ "240": "Volleyball",
391
+ "241": "Deer",
392
+ "242": "Goose",
393
+ "243": "Tape",
394
+ "244": "Tablet",
395
+ "245": "Cosmetics",
396
+ "246": "Trumpet",
397
+ "247": "Pineapple",
398
+ "248": "Golf Ball",
399
+ "249": "Ambulance",
400
+ "250": "Parking meter",
401
+ "251": "Mango",
402
+ "252": "Key",
403
+ "253": "Hurdle",
404
+ "254": "Fishing Rod",
405
+ "255": "Medal",
406
+ "256": "Flute",
407
+ "257": "Brush",
408
+ "258": "Penguin",
409
+ "259": "Megaphone",
410
+ "260": "Corn",
411
+ "261": "Lettuce",
412
+ "262": "Garlic",
413
+ "263": "Swan",
414
+ "264": "Helicopter",
415
+ "265": "Green Onion",
416
+ "266": "Sandwich",
417
+ "267": "Nuts",
418
+ "268": "Speed Limit Sign",
419
+ "269": "Induction Cooker",
420
+ "270": "Broom",
421
+ "271": "Trombone",
422
+ "272": "Plum",
423
+ "273": "Rickshaw",
424
+ "274": "Goldfish",
425
+ "275": "Kiwi fruit",
426
+ "276": "Router/modem",
427
+ "277": "Poker Card",
428
+ "278": "Toaster",
429
+ "279": "Shrimp",
430
+ "280": "Sushi",
431
+ "281": "Cheese",
432
+ "282": "Notepaper",
433
+ "283": "Cherry",
434
+ "284": "Pliers",
435
+ "285": "CD",
436
+ "286": "Pasta",
437
+ "287": "Hammer",
438
+ "288": "Cue",
439
+ "289": "Avocado",
440
+ "290": "Hamimelon",
441
+ "291": "Flask",
442
+ "292": "Mushroom",
443
+ "293": "Screwdriver",
444
+ "294": "Soap",
445
+ "295": "Recorder",
446
+ "296": "Bear",
447
+ "297": "Eggplant",
448
+ "298": "Board Eraser",
449
+ "299": "Coconut",
450
+ "300": "Tape Measure/Ruler",
451
+ "301": "Pig",
452
+ "302": "Showerhead",
453
+ "303": "Globe",
454
+ "304": "Chips",
455
+ "305": "Steak",
456
+ "306": "Crosswalk Sign",
457
+ "307": "Stapler",
458
+ "308": "Camel",
459
+ "309": "Formula 1",
460
+ "310": "Pomegranate",
461
+ "311": "Dishwasher",
462
+ "312": "Crab",
463
+ "313": "Hoverboard",
464
+ "314": "Meat ball",
465
+ "315": "Rice Cooker",
466
+ "316": "Tuba",
467
+ "317": "Calculator",
468
+ "318": "Papaya",
469
+ "319": "Antelope",
470
+ "320": "Parrot",
471
+ "321": "Seal",
472
+ "322": "Butterfly",
473
+ "323": "Dumbbell",
474
+ "324": "Donkey",
475
+ "325": "Lion",
476
+ "326": "Urinal",
477
+ "327": "Dolphin",
478
+ "328": "Electric Drill",
479
+ "329": "Hair Dryer",
480
+ "330": "Egg tart",
481
+ "331": "Jellyfish",
482
+ "332": "Treadmill",
483
+ "333": "Lighter",
484
+ "334": "Grapefruit",
485
+ "335": "Game board",
486
+ "336": "Mop",
487
+ "337": "Radish",
488
+ "338": "Baozi",
489
+ "339": "Target",
490
+ "340": "French",
491
+ "341": "Spring Rolls",
492
+ "342": "Monkey",
493
+ "343": "Rabbit",
494
+ "344": "Pencil Case",
495
+ "345": "Yak",
496
+ "346": "Red Cabbage",
497
+ "347": "Binoculars",
498
+ "348": "Asparagus",
499
+ "349": "Barbell",
500
+ "350": "Scallop",
501
+ "351": "Noddles",
502
+ "352": "Comb",
503
+ "353": "Dumpling",
504
+ "354": "Oyster",
505
+ "355": "Table Tennis paddle",
506
+ "356": "Cosmetics Brush/Eyeliner Pencil",
507
+ "357": "Chainsaw",
508
+ "358": "Eraser",
509
+ "359": "Lobster",
510
+ "360": "Durian",
511
+ "361": "Okra",
512
+ "362": "Lipstick",
513
+ "363": "Cosmetics Mirror",
514
+ "364": "Curling",
515
+ "365": "Table Tennis"
516
+ },
517
+ "initializer_bias_prior_prob": null,
518
+ "initializer_range": 0.01,
519
+ "is_encoder_decoder": true,
520
+ "label2id": {
521
+ "Air Conditioner": 84,
522
+ "Airplane": 115,
523
+ "Ambulance": 249,
524
+ "American Football": 207,
525
+ "Antelope": 319,
526
+ "Apple": 83,
527
+ "Asparagus": 348,
528
+ "Avocado": 289,
529
+ "Awning": 75,
530
+ "Backpack": 39,
531
+ "Balloon": 91,
532
+ "Banana": 113,
533
+ "Baozi": 338,
534
+ "Barbell": 349,
535
+ "Barrel/bucket": 49,
536
+ "Baseball": 166,
537
+ "Baseball Bat": 138,
538
+ "Baseball Glove": 114,
539
+ "Basket": 53,
540
+ "Basketball": 178,
541
+ "Bathtub": 192,
542
+ "Bear": 296,
543
+ "Bed": 76,
544
+ "Belt": 37,
545
+ "Bench": 25,
546
+ "Bicycle": 47,
547
+ "Billiards": 190,
548
+ "Binoculars": 347,
549
+ "Blackboard/Whiteboard": 102,
550
+ "Blender": 236,
551
+ "Board Eraser": 298,
552
+ "Boat": 22,
553
+ "Book": 19,
554
+ "Boots": 30,
555
+ "Bottle": 9,
556
+ "Bow Tie": 152,
557
+ "Bowl/Basin": 27,
558
+ "Bracelet": 15,
559
+ "Bread": 63,
560
+ "Briefcase": 195,
561
+ "Broccoli": 142,
562
+ "Broom": 270,
563
+ "Brush": 257,
564
+ "Bus": 56,
565
+ "Butterfly": 322,
566
+ "CD": 285,
567
+ "Cabbage": 234,
568
+ "Cabinet/shelf": 13,
569
+ "Cake": 98,
570
+ "Calculator": 317,
571
+ "Camel": 308,
572
+ "Camera": 64,
573
+ "Candle": 72,
574
+ "Candy": 188,
575
+ "Canned": 65,
576
+ "Car": 6,
577
+ "Carpet": 61,
578
+ "Carriage": 216,
579
+ "Carrot": 153,
580
+ "Cat": 140,
581
+ "Cell Phone": 62,
582
+ "Cello": 230,
583
+ "Chainsaw": 357,
584
+ "Chair": 3,
585
+ "Cheese": 281,
586
+ "Cherry": 283,
587
+ "Chicken": 222,
588
+ "Chips": 304,
589
+ "Chopsticks": 163,
590
+ "Cigar/Cigarette": 197,
591
+ "Cleaning Products": 162,
592
+ "Clock": 95,
593
+ "Coconut": 299,
594
+ "Coffee Machine": 214,
595
+ "Coffee Table": 168,
596
+ "Comb": 352,
597
+ "Computer Box": 160,
598
+ "Converter": 191,
599
+ "Cookies": 175,
600
+ "Corn": 260,
601
+ "Cosmetics": 245,
602
+ "Cosmetics Brush/Eyeliner Pencil": 356,
603
+ "Cosmetics Mirror": 363,
604
+ "Couch": 51,
605
+ "Cow": 97,
606
+ "Crab": 312,
607
+ "Crane": 132,
608
+ "Crosswalk Sign": 306,
609
+ "Cucumber": 196,
610
+ "Cue": 288,
611
+ "Cup": 11,
612
+ "Curling": 364,
613
+ "Cutting/chopping Board": 167,
614
+ "Cymbal": 68,
615
+ "Deer": 241,
616
+ "Desk": 10,
617
+ "Dessert": 129,
618
+ "Dinning Table": 99,
619
+ "Dishwasher": 311,
620
+ "Dog": 93,
621
+ "Dolphin": 327,
622
+ "Donkey": 324,
623
+ "Donut": 151,
624
+ "Drum": 54,
625
+ "Duck": 137,
626
+ "Dumbbell": 323,
627
+ "Dumpling": 353,
628
+ "Durian": 360,
629
+ "Egg": 186,
630
+ "Egg tart": 330,
631
+ "Eggplant": 297,
632
+ "Electric Drill": 328,
633
+ "Elephant": 145,
634
+ "Eraser": 358,
635
+ "Extension Cord": 203,
636
+ "Extractor": 202,
637
+ "Fan": 111,
638
+ "Faucet": 77,
639
+ "Fire Extinguisher": 187,
640
+ "Fire Hydrant": 177,
641
+ "Fire Truck": 189,
642
+ "Fishing Rod": 254,
643
+ "Flag": 28,
644
+ "Flask": 291,
645
+ "Flower": 24,
646
+ "Flute": 256,
647
+ "Folder": 206,
648
+ "Fork": 89,
649
+ "Formula 1": 309,
650
+ "French": 340,
651
+ "French Fries": 231,
652
+ "Frisbee": 220,
653
+ "Game board": 335,
654
+ "Garlic": 262,
655
+ "Gas stove": 150,
656
+ "Giraffe": 181,
657
+ "Glasses": 8,
658
+ "Globe": 303,
659
+ "Gloves": 20,
660
+ "Goldfish": 274,
661
+ "Golf Ball": 248,
662
+ "Golf Club": 194,
663
+ "Goose": 242,
664
+ "Grape": 180,
665
+ "Grapefruit": 334,
666
+ "Green Onion": 265,
667
+ "Green Vegetables": 112,
668
+ "Green beans": 218,
669
+ "Guitar": 60,
670
+ "Gun": 148,
671
+ "Hair Dryer": 329,
672
+ "Hamburger": 201,
673
+ "Hamimelon": 290,
674
+ "Hammer": 287,
675
+ "Handbag/Satchel": 14,
676
+ "Hanger": 101,
677
+ "Hat": 5,
678
+ "Head Phone": 126,
679
+ "Heavy Truck": 200,
680
+ "Helicopter": 264,
681
+ "Helmet": 18,
682
+ "High Heels": 58,
683
+ "Hockey Stick": 86,
684
+ "Horse": 79,
685
+ "Hot dog": 235,
686
+ "Hot-air balloon": 229,
687
+ "Hoverboard": 313,
688
+ "Hurdle": 253,
689
+ "Ice cream": 228,
690
+ "Induction Cooker": 269,
691
+ "Jellyfish": 331,
692
+ "Jug": 141,
693
+ "Kettle": 210,
694
+ "Key": 252,
695
+ "Keyboard": 107,
696
+ "Kite": 155,
697
+ "Kiwi fruit": 275,
698
+ "Knife": 85,
699
+ "Ladder": 173,
700
+ "Lamp": 7,
701
+ "Lantern": 109,
702
+ "Laptop": 74,
703
+ "Leather Shoes": 23,
704
+ "Lemon": 136,
705
+ "Lettuce": 261,
706
+ "Lifesaver": 69,
707
+ "Lighter": 333,
708
+ "Lion": 325,
709
+ "Lipstick": 362,
710
+ "Lobster": 359,
711
+ "Luggage": 121,
712
+ "Machinery Vehicle": 110,
713
+ "Mango": 251,
714
+ "Marker": 171,
715
+ "Mask": 209,
716
+ "Meat ball": 314,
717
+ "Medal": 255,
718
+ "Megaphone": 259,
719
+ "Microphone": 32,
720
+ "Microwave": 164,
721
+ "Mirror": 80,
722
+ "Monitor/TV": 38,
723
+ "Monkey": 342,
724
+ "Mop": 336,
725
+ "Motorcycle": 59,
726
+ "Mouse": 116,
727
+ "Mushroom": 292,
728
+ "Napkin": 103,
729
+ "Necklace": 33,
730
+ "Nightstand": 122,
731
+ "Noddles": 351,
732
+ "None": 0,
733
+ "Notepaper": 282,
734
+ "Nuts": 267,
735
+ "Okra": 361,
736
+ "Onion": 217,
737
+ "Orange/Tangerine": 105,
738
+ "Other Balls": 157,
739
+ "Other Fish": 104,
740
+ "Other Shoes": 4,
741
+ "Oven": 135,
742
+ "Oyster": 354,
743
+ "Paddle": 87,
744
+ "Paint Brush": 198,
745
+ "Papaya": 318,
746
+ "Parking meter": 250,
747
+ "Parrot": 320,
748
+ "Pasta": 286,
749
+ "Peach": 237,
750
+ "Pear": 199,
751
+ "Pen/Pencil": 55,
752
+ "Pencil Case": 344,
753
+ "Penguin": 258,
754
+ "Pepper": 159,
755
+ "Person": 1,
756
+ "Piano": 143,
757
+ "Pickup Truck": 88,
758
+ "Picture/Frame": 17,
759
+ "Pie": 172,
760
+ "Pig": 301,
761
+ "Pigeon": 165,
762
+ "Pillow": 29,
763
+ "Pineapple": 247,
764
+ "Pizza": 144,
765
+ "Plate": 16,
766
+ "Pliers": 284,
767
+ "Plum": 272,
768
+ "Poker Card": 277,
769
+ "Pomegranate": 310,
770
+ "Pot": 96,
771
+ "Potato": 182,
772
+ "Potted Plant": 26,
773
+ "Power outlet": 81,
774
+ "Printer": 223,
775
+ "Projector": 219,
776
+ "Pumpkin": 118,
777
+ "Rabbit": 343,
778
+ "Radiator": 176,
779
+ "Radish": 337,
780
+ "Recorder": 295,
781
+ "Red Cabbage": 346,
782
+ "Refrigerator": 134,
783
+ "Remote": 133,
784
+ "Rice": 238,
785
+ "Rice Cooker": 315,
786
+ "Rickshaw": 273,
787
+ "Ring": 34,
788
+ "Router/modem": 276,
789
+ "SUV": 35,
790
+ "Sailboat": 73,
791
+ "Sandals": 52,
792
+ "Sandwich": 266,
793
+ "Sausage": 183,
794
+ "Saxophone": 225,
795
+ "Scale": 232,
796
+ "Scallop": 350,
797
+ "Scissors": 170,
798
+ "Scooter": 130,
799
+ "Screwdriver": 293,
800
+ "Seal": 321,
801
+ "Sheep": 100,
802
+ "Ship": 212,
803
+ "Shovel": 158,
804
+ "Showerhead": 302,
805
+ "Shrimp": 279,
806
+ "Side Table": 169,
807
+ "Sink": 82,
808
+ "Skateboard": 146,
809
+ "Skating and Skiing shoes": 149,
810
+ "Skiboard": 120,
811
+ "Slide": 215,
812
+ "Slippers": 46,
813
+ "Sneakers": 2,
814
+ "Snowboard": 174,
815
+ "Soap": 294,
816
+ "Soccer": 119,
817
+ "Speaker": 42,
818
+ "Speed Limit Sign": 268,
819
+ "Spoon": 94,
820
+ "Sports Car": 127,
821
+ "Spring Rolls": 341,
822
+ "Stapler": 307,
823
+ "Steak": 305,
824
+ "Stool": 48,
825
+ "Stop Sign": 128,
826
+ "Storage box": 21,
827
+ "Strawberry": 156,
828
+ "Street Lights": 12,
829
+ "Stroller": 131,
830
+ "Stuffed Toy": 71,
831
+ "Surfboard": 147,
832
+ "Surveillance Camera": 139,
833
+ "Sushi": 280,
834
+ "Swan": 263,
835
+ "Swing": 213,
836
+ "Table Tennis": 365,
837
+ "Table Tennis paddle": 355,
838
+ "Tablet": 244,
839
+ "Tape": 243,
840
+ "Tape Measure/Ruler": 300,
841
+ "Target": 339,
842
+ "Tea pot": 123,
843
+ "Telephone": 124,
844
+ "Tennis": 211,
845
+ "Tennis Racket": 205,
846
+ "Tent": 78,
847
+ "Tie": 44,
848
+ "Tissue": 226,
849
+ "Toaster": 278,
850
+ "Toilet": 154,
851
+ "Toilet Paper": 161,
852
+ "Toiletry": 106,
853
+ "Tomato": 108,
854
+ "Tong": 204,
855
+ "Toothbrush": 227,
856
+ "Towel": 70,
857
+ "Traffic Light": 41,
858
+ "Traffic Sign": 90,
859
+ "Traffic cone": 67,
860
+ "Train": 117,
861
+ "Trash bin Can": 45,
862
+ "Treadmill": 332,
863
+ "Tricycle": 184,
864
+ "Tripod": 92,
865
+ "Trolley": 125,
866
+ "Trombone": 271,
867
+ "Trophy": 233,
868
+ "Truck": 66,
869
+ "Trumpet": 246,
870
+ "Tuba": 316,
871
+ "Umbrella": 40,
872
+ "Urinal": 326,
873
+ "Van": 50,
874
+ "Vase": 31,
875
+ "Violin": 185,
876
+ "Volleyball": 240,
877
+ "Wallet/Purse": 239,
878
+ "Washing Machine/Drying Machine": 221,
879
+ "Watch": 43,
880
+ "Watermelon": 224,
881
+ "Wheelchair": 193,
882
+ "Wild Bird": 57,
883
+ "Wine Glass": 36,
884
+ "Yak": 345,
885
+ "Zebra": 179,
886
+ "earphone": 208
887
+ },
888
+ "label_noise_ratio": 0.5,
889
+ "layer_norm_eps": 1e-05,
890
+ "layer_scale": 1,
891
+ "learn_initial_query": false,
892
+ "lqe_hidden_dim": 64,
893
+ "lqe_layers": 2,
894
+ "matcher_alpha": 0.25,
895
+ "matcher_bbox_cost": 5.0,
896
+ "matcher_class_cost": 2.0,
897
+ "matcher_gamma": 2.0,
898
+ "matcher_giou_cost": 2.0,
899
+ "max_num_bins": 32,
900
+ "model_type": "d_fine",
901
+ "normalize_before": false,
902
+ "num_denoising": 100,
903
+ "num_feature_levels": 3,
904
+ "num_queries": 300,
905
+ "positional_encoding_temperature": 10000,
906
+ "reg_scale": 4.0,
907
+ "top_prob_values": 4,
908
+ "transformers_version": "4.51.0.dev0",
909
+ "up": 0.5,
910
+ "use_focal_loss": true,
911
+ "use_pretrained_backbone": false,
912
+ "use_timm_backbone": false,
913
+ "weight_loss_bbox": 5.0,
914
+ "weight_loss_ddf": 1.5,
915
+ "weight_loss_fgl": 0.15,
916
+ "weight_loss_giou": 2.0,
917
+ "weight_loss_vfl": 1.0,
918
+ "with_box_refine": true
919
+ }