peter881122
commited on
Commit
•
734f80b
1
Parent(s):
17811cb
Upload YolosForObjectDetection
Browse files- config.json +41 -142
- pytorch_model.bin +2 -2
config.json
CHANGED
@@ -1,148 +1,47 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"_name_or_path": "facebook/detr-resnet-50",
|
4 |
-
"activation_dropout": 0.0,
|
5 |
-
"activation_function": "relu",
|
6 |
"architectures": [
|
7 |
-
"
|
8 |
],
|
9 |
-
"
|
10 |
"auxiliary_loss": false,
|
11 |
-
"backbone": null,
|
12 |
-
"backbone_config": {
|
13 |
-
"_name_or_path": "",
|
14 |
-
"add_cross_attention": false,
|
15 |
-
"architectures": null,
|
16 |
-
"bad_words_ids": null,
|
17 |
-
"begin_suppress_tokens": null,
|
18 |
-
"bos_token_id": null,
|
19 |
-
"chunk_size_feed_forward": 0,
|
20 |
-
"cross_attention_hidden_size": null,
|
21 |
-
"decoder_start_token_id": null,
|
22 |
-
"depths": [
|
23 |
-
3,
|
24 |
-
4,
|
25 |
-
6,
|
26 |
-
3
|
27 |
-
],
|
28 |
-
"diversity_penalty": 0.0,
|
29 |
-
"do_sample": 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 |
-
"output_attentions": false,
|
70 |
-
"output_hidden_states": false,
|
71 |
-
"output_scores": false,
|
72 |
-
"pad_token_id": null,
|
73 |
-
"prefix": null,
|
74 |
-
"problem_type": null,
|
75 |
-
"pruned_heads": {},
|
76 |
-
"remove_invalid_values": false,
|
77 |
-
"repetition_penalty": 1.0,
|
78 |
-
"return_dict": true,
|
79 |
-
"return_dict_in_generate": false,
|
80 |
-
"sep_token_id": null,
|
81 |
-
"stage_names": [
|
82 |
-
"stem",
|
83 |
-
"stage1",
|
84 |
-
"stage2",
|
85 |
-
"stage3",
|
86 |
-
"stage4"
|
87 |
-
],
|
88 |
-
"suppress_tokens": null,
|
89 |
-
"task_specific_params": null,
|
90 |
-
"temperature": 1.0,
|
91 |
-
"tf_legacy_loss": false,
|
92 |
-
"tie_encoder_decoder": false,
|
93 |
-
"tie_word_embeddings": true,
|
94 |
-
"tokenizer_class": null,
|
95 |
-
"top_k": 50,
|
96 |
-
"top_p": 1.0,
|
97 |
-
"torch_dtype": null,
|
98 |
-
"torchscript": false,
|
99 |
-
"transformers_version": "4.27.0.dev0",
|
100 |
-
"typical_p": 1.0,
|
101 |
-
"use_bfloat16": false
|
102 |
-
},
|
103 |
"bbox_cost": 5,
|
104 |
"bbox_loss_coefficient": 5,
|
105 |
"class_cost": 1,
|
106 |
-
"d_model": 256,
|
107 |
-
"decoder_attention_heads": 8,
|
108 |
-
"decoder_ffn_dim": 2048,
|
109 |
-
"decoder_layerdrop": 0.0,
|
110 |
-
"decoder_layers": 6,
|
111 |
-
"dice_loss_coefficient": 1,
|
112 |
-
"dilation": null,
|
113 |
-
"dropout": 0.1,
|
114 |
-
"encoder_attention_heads": 8,
|
115 |
-
"encoder_ffn_dim": 2048,
|
116 |
-
"encoder_layerdrop": 0.0,
|
117 |
-
"encoder_layers": 6,
|
118 |
"eos_coefficient": 0.1,
|
119 |
"giou_cost": 2,
|
120 |
"giou_loss_coefficient": 2,
|
|
|
|
|
|
|
121 |
"id2label": {
|
122 |
-
"
|
123 |
-
"
|
124 |
-
"
|
125 |
-
"
|
126 |
-
"
|
127 |
-
"
|
128 |
-
"
|
129 |
-
"
|
130 |
-
"
|
131 |
-
"
|
132 |
-
"
|
133 |
-
"
|
134 |
-
"
|
135 |
-
"
|
136 |
-
"
|
137 |
-
"
|
138 |
-
"
|
139 |
-
"
|
140 |
-
"
|
141 |
-
"
|
142 |
},
|
143 |
-
"
|
144 |
-
|
145 |
-
|
|
|
|
|
|
|
146 |
"label2id": {
|
147 |
"LABEL_0": 0,
|
148 |
"LABEL_1": 1,
|
@@ -165,15 +64,15 @@
|
|
165 |
"LABEL_8": 8,
|
166 |
"LABEL_9": 9
|
167 |
},
|
168 |
-
"
|
169 |
-
"model_type": "
|
|
|
170 |
"num_channels": 3,
|
171 |
-
"
|
172 |
-
"
|
173 |
-
"
|
174 |
-
"
|
175 |
"torch_dtype": "float32",
|
176 |
-
"transformers_version":
|
177 |
-
"
|
178 |
-
"use_timm_backbone": false
|
179 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "hustvl/yolos-tiny",
|
|
|
|
|
|
|
3 |
"architectures": [
|
4 |
+
"YolosForObjectDetection"
|
5 |
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
"auxiliary_loss": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
"bbox_cost": 5,
|
9 |
"bbox_loss_coefficient": 5,
|
10 |
"class_cost": 1,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
"eos_coefficient": 0.1,
|
12 |
"giou_cost": 2,
|
13 |
"giou_loss_coefficient": 2,
|
14 |
+
"hidden_act": "gelu",
|
15 |
+
"hidden_dropout_prob": 0.0,
|
16 |
+
"hidden_size": 192,
|
17 |
"id2label": {
|
18 |
+
"0": "LABEL_0",
|
19 |
+
"1": "LABEL_1",
|
20 |
+
"2": "LABEL_2",
|
21 |
+
"3": "LABEL_3",
|
22 |
+
"4": "LABEL_4",
|
23 |
+
"5": "LABEL_5",
|
24 |
+
"6": "LABEL_6",
|
25 |
+
"7": "LABEL_7",
|
26 |
+
"8": "LABEL_8",
|
27 |
+
"9": "LABEL_9",
|
28 |
+
"10": "LABEL_10",
|
29 |
+
"11": "LABEL_11",
|
30 |
+
"12": "LABEL_12",
|
31 |
+
"13": "LABEL_13",
|
32 |
+
"14": "LABEL_14",
|
33 |
+
"15": "LABEL_15",
|
34 |
+
"16": "LABEL_16",
|
35 |
+
"17": "LABEL_17",
|
36 |
+
"18": "LABEL_18",
|
37 |
+
"19": "LABEL_19"
|
38 |
},
|
39 |
+
"image_size": [
|
40 |
+
800,
|
41 |
+
1333
|
42 |
+
],
|
43 |
+
"initializer_range": 0.02,
|
44 |
+
"intermediate_size": 768,
|
45 |
"label2id": {
|
46 |
"LABEL_0": 0,
|
47 |
"LABEL_1": 1,
|
|
|
64 |
"LABEL_8": 8,
|
65 |
"LABEL_9": 9
|
66 |
},
|
67 |
+
"layer_norm_eps": 1e-12,
|
68 |
+
"model_type": "yolos",
|
69 |
+
"num_attention_heads": 3,
|
70 |
"num_channels": 3,
|
71 |
+
"num_detection_tokens": 100,
|
72 |
+
"num_hidden_layers": 12,
|
73 |
+
"patch_size": 16,
|
74 |
+
"qkv_bias": true,
|
75 |
"torch_dtype": "float32",
|
76 |
+
"transformers_version": "4.27.0.dev0",
|
77 |
+
"use_mid_position_embeddings": false
|
|
|
78 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:346370ead26f656c20a5cc21f97885cfce868fbf7acca55ff1aa323ef394ff53
|
3 |
+
size 25968281
|