aravindhank
commited on
Commit
•
983ff45
1
Parent(s):
a4edfd5
Upload DetrForObjectDetection
Browse files- config.json +7 -99
- model.safetensors +2 -2
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "relu",
|
5 |
"architectures": [
|
@@ -7,101 +7,8 @@
|
|
7 |
],
|
8 |
"attention_dropout": 0.0,
|
9 |
"auxiliary_loss": false,
|
10 |
-
"backbone":
|
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,
|
@@ -112,7 +19,7 @@
|
|
112 |
"decoder_layerdrop": 0.0,
|
113 |
"decoder_layers": 6,
|
114 |
"dice_loss_coefficient": 1,
|
115 |
-
"dilation":
|
116 |
"dropout": 0.1,
|
117 |
"encoder_attention_heads": 8,
|
118 |
"encoder_ffn_dim": 2048,
|
@@ -141,6 +48,7 @@
|
|
141 |
"LABEL_5": 5
|
142 |
},
|
143 |
"mask_loss_coefficient": 1,
|
|
|
144 |
"model_type": "detr",
|
145 |
"num_channels": 3,
|
146 |
"num_hidden_layers": 6,
|
@@ -149,6 +57,6 @@
|
|
149 |
"scale_embedding": false,
|
150 |
"torch_dtype": "float32",
|
151 |
"transformers_version": "4.38.2",
|
152 |
-
"use_pretrained_backbone":
|
153 |
-
"use_timm_backbone":
|
154 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "TahaDouaji/detr-doc-table-detection",
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "relu",
|
5 |
"architectures": [
|
|
|
7 |
],
|
8 |
"attention_dropout": 0.0,
|
9 |
"auxiliary_loss": false,
|
10 |
+
"backbone": "resnet50",
|
11 |
+
"backbone_config": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
"backbone_kwargs": null,
|
13 |
"bbox_cost": 5,
|
14 |
"bbox_loss_coefficient": 5,
|
|
|
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,
|
|
|
48 |
"LABEL_5": 5
|
49 |
},
|
50 |
"mask_loss_coefficient": 1,
|
51 |
+
"max_position_embeddings": 1024,
|
52 |
"model_type": "detr",
|
53 |
"num_channels": 3,
|
54 |
"num_hidden_layers": 6,
|
|
|
57 |
"scale_embedding": false,
|
58 |
"torch_dtype": "float32",
|
59 |
"transformers_version": "4.38.2",
|
60 |
+
"use_pretrained_backbone": true,
|
61 |
+
"use_timm_backbone": true
|
62 |
}
|
model.safetensors
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 sha256:327dbb96faf1e966c9f29e85b07f0634291ae62fe47716b00b9512352b41671e
|
3 |
+
size 166499964
|