Upload TableTransformerForObjectDetection
Browse files- config.json +13 -102
- pytorch_model.bin +2 -2
config.json
CHANGED
@@ -1,107 +1,17 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"_name_or_path": "facebook/detr-resnet-50",
|
4 |
"activation_dropout": 0.0,
|
5 |
"activation_function": "relu",
|
6 |
"architectures": [
|
7 |
-
"
|
8 |
],
|
9 |
"attention_dropout": 0.0,
|
10 |
"auxiliary_loss": false,
|
11 |
-
"backbone":
|
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,
|
@@ -109,13 +19,13 @@
|
|
109 |
"decoder_layerdrop": 0.0,
|
110 |
"decoder_layers": 6,
|
111 |
"dice_loss_coefficient": 1,
|
112 |
-
"dilation":
|
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.
|
119 |
"giou_cost": 2,
|
120 |
"giou_loss_coefficient": 2,
|
121 |
"id2label": {
|
@@ -128,14 +38,15 @@
|
|
128 |
"LABEL_0": 0
|
129 |
},
|
130 |
"mask_loss_coefficient": 1,
|
131 |
-
"
|
|
|
132 |
"num_channels": 3,
|
133 |
"num_hidden_layers": 6,
|
134 |
-
"num_queries":
|
135 |
"position_embedding_type": "sine",
|
136 |
"scale_embedding": false,
|
137 |
"torch_dtype": "float32",
|
138 |
-
"transformers_version":
|
139 |
-
"use_pretrained_backbone":
|
140 |
-
"use_timm_backbone":
|
141 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "microsoft/table-transformer-detection",
|
|
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "relu",
|
5 |
"architectures": [
|
6 |
+
"TableTransformerForObjectDetection"
|
7 |
],
|
8 |
"attention_dropout": 0.0,
|
9 |
"auxiliary_loss": false,
|
10 |
+
"backbone": "resnet18",
|
11 |
+
"backbone_config": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
"bbox_cost": 5,
|
13 |
"bbox_loss_coefficient": 5,
|
14 |
+
"ce_loss_coefficient": 1,
|
15 |
"class_cost": 1,
|
16 |
"d_model": 256,
|
17 |
"decoder_attention_heads": 8,
|
|
|
19 |
"decoder_layerdrop": 0.0,
|
20 |
"decoder_layers": 6,
|
21 |
"dice_loss_coefficient": 1,
|
22 |
+
"dilation": false,
|
23 |
"dropout": 0.1,
|
24 |
"encoder_attention_heads": 8,
|
25 |
"encoder_ffn_dim": 2048,
|
26 |
"encoder_layerdrop": 0.0,
|
27 |
"encoder_layers": 6,
|
28 |
+
"eos_coefficient": 0.4,
|
29 |
"giou_cost": 2,
|
30 |
"giou_loss_coefficient": 2,
|
31 |
"id2label": {
|
|
|
38 |
"LABEL_0": 0
|
39 |
},
|
40 |
"mask_loss_coefficient": 1,
|
41 |
+
"max_position_embeddings": 1024,
|
42 |
+
"model_type": "table-transformer",
|
43 |
"num_channels": 3,
|
44 |
"num_hidden_layers": 6,
|
45 |
+
"num_queries": 15,
|
46 |
"position_embedding_type": "sine",
|
47 |
"scale_embedding": false,
|
48 |
"torch_dtype": "float32",
|
49 |
+
"transformers_version": "4.27.0.dev0",
|
50 |
+
"use_pretrained_backbone": true,
|
51 |
+
"use_timm_backbone": true
|
52 |
}
|
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:d48b0446ff53db18631e4c121570dea58995aa5f7e166781bbb67dca945687f7
|
3 |
+
size 115395029
|