Upload DPTForDepthEstimation
Browse files- config.json +159 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,159 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_commit_hash": null,
|
3 |
+
"add_projection": true,
|
4 |
+
"architectures": [
|
5 |
+
"DPTForDepthEstimation"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": null,
|
8 |
+
"auxiliary_loss_weight": 0.4,
|
9 |
+
"backbone_config": {
|
10 |
+
"_name_or_path": "",
|
11 |
+
"add_cross_attention": false,
|
12 |
+
"apply_layernorm": false,
|
13 |
+
"architectures": [
|
14 |
+
"Dinov2Model"
|
15 |
+
],
|
16 |
+
"attention_probs_dropout_prob": 0.0,
|
17 |
+
"bad_words_ids": null,
|
18 |
+
"begin_suppress_tokens": null,
|
19 |
+
"bos_token_id": null,
|
20 |
+
"chunk_size_feed_forward": 0,
|
21 |
+
"cross_attention_hidden_size": null,
|
22 |
+
"decoder_start_token_id": null,
|
23 |
+
"diversity_penalty": 0.0,
|
24 |
+
"do_sample": false,
|
25 |
+
"drop_path_rate": 0.0,
|
26 |
+
"early_stopping": false,
|
27 |
+
"encoder_no_repeat_ngram_size": 0,
|
28 |
+
"eos_token_id": null,
|
29 |
+
"exponential_decay_length_penalty": null,
|
30 |
+
"finetuning_task": null,
|
31 |
+
"forced_bos_token_id": null,
|
32 |
+
"forced_eos_token_id": null,
|
33 |
+
"hidden_act": "gelu",
|
34 |
+
"hidden_dropout_prob": 0.0,
|
35 |
+
"hidden_size": 384,
|
36 |
+
"id2label": {
|
37 |
+
"0": "LABEL_0",
|
38 |
+
"1": "LABEL_1"
|
39 |
+
},
|
40 |
+
"image_size": 518,
|
41 |
+
"initializer_range": 0.02,
|
42 |
+
"is_decoder": false,
|
43 |
+
"is_encoder_decoder": false,
|
44 |
+
"label2id": {
|
45 |
+
"LABEL_0": 0,
|
46 |
+
"LABEL_1": 1
|
47 |
+
},
|
48 |
+
"layer_norm_eps": 1e-06,
|
49 |
+
"layerscale_value": 1.0,
|
50 |
+
"length_penalty": 1.0,
|
51 |
+
"max_length": 20,
|
52 |
+
"min_length": 0,
|
53 |
+
"mlp_ratio": 4,
|
54 |
+
"model_type": "dinov2",
|
55 |
+
"no_repeat_ngram_size": 0,
|
56 |
+
"num_attention_heads": 6,
|
57 |
+
"num_beam_groups": 1,
|
58 |
+
"num_beams": 1,
|
59 |
+
"num_channels": 3,
|
60 |
+
"num_hidden_layers": 12,
|
61 |
+
"num_return_sequences": 1,
|
62 |
+
"out_features": [
|
63 |
+
"stage3",
|
64 |
+
"stage6",
|
65 |
+
"stage9",
|
66 |
+
"stage12"
|
67 |
+
],
|
68 |
+
"out_indices": [
|
69 |
+
3,
|
70 |
+
6,
|
71 |
+
9,
|
72 |
+
12
|
73 |
+
],
|
74 |
+
"output_attentions": false,
|
75 |
+
"output_hidden_states": false,
|
76 |
+
"output_scores": false,
|
77 |
+
"pad_token_id": null,
|
78 |
+
"patch_size": 14,
|
79 |
+
"prefix": null,
|
80 |
+
"problem_type": null,
|
81 |
+
"pruned_heads": {},
|
82 |
+
"qkv_bias": true,
|
83 |
+
"remove_invalid_values": false,
|
84 |
+
"repetition_penalty": 1.0,
|
85 |
+
"reshape_hidden_states": false,
|
86 |
+
"return_dict": true,
|
87 |
+
"return_dict_in_generate": false,
|
88 |
+
"sep_token_id": null,
|
89 |
+
"stage_names": [
|
90 |
+
"stem",
|
91 |
+
"stage1",
|
92 |
+
"stage2",
|
93 |
+
"stage3",
|
94 |
+
"stage4",
|
95 |
+
"stage5",
|
96 |
+
"stage6",
|
97 |
+
"stage7",
|
98 |
+
"stage8",
|
99 |
+
"stage9",
|
100 |
+
"stage10",
|
101 |
+
"stage11",
|
102 |
+
"stage12"
|
103 |
+
],
|
104 |
+
"suppress_tokens": null,
|
105 |
+
"task_specific_params": null,
|
106 |
+
"temperature": 1.0,
|
107 |
+
"tf_legacy_loss": false,
|
108 |
+
"tie_encoder_decoder": false,
|
109 |
+
"tie_word_embeddings": true,
|
110 |
+
"tokenizer_class": null,
|
111 |
+
"top_k": 50,
|
112 |
+
"top_p": 1.0,
|
113 |
+
"torch_dtype": "float32",
|
114 |
+
"torchscript": false,
|
115 |
+
"transformers_version": "4.35.0.dev0",
|
116 |
+
"typical_p": 1.0,
|
117 |
+
"use_bfloat16": false,
|
118 |
+
"use_swiglu_ffn": false
|
119 |
+
},
|
120 |
+
"backbone_featmap_shape": null,
|
121 |
+
"backbone_out_indices": null,
|
122 |
+
"fusion_hidden_size": 256,
|
123 |
+
"head_in_index": -1,
|
124 |
+
"hidden_act": "gelu",
|
125 |
+
"hidden_dropout_prob": null,
|
126 |
+
"hidden_size": 768,
|
127 |
+
"image_size": null,
|
128 |
+
"initializer_range": 0.02,
|
129 |
+
"intermediate_size": null,
|
130 |
+
"is_hybrid": false,
|
131 |
+
"layer_norm_eps": null,
|
132 |
+
"model_type": "dpt",
|
133 |
+
"neck_hidden_sizes": [
|
134 |
+
48,
|
135 |
+
96,
|
136 |
+
192,
|
137 |
+
384
|
138 |
+
],
|
139 |
+
"neck_ignore_stages": [],
|
140 |
+
"num_attention_heads": null,
|
141 |
+
"num_channels": null,
|
142 |
+
"num_hidden_layers": null,
|
143 |
+
"patch_size": null,
|
144 |
+
"qkv_bias": null,
|
145 |
+
"readout_type": "project",
|
146 |
+
"reassemble_factors": [
|
147 |
+
4,
|
148 |
+
2,
|
149 |
+
1,
|
150 |
+
0.5
|
151 |
+
],
|
152 |
+
"semantic_classifier_dropout": 0.1,
|
153 |
+
"semantic_loss_ignore_index": 255,
|
154 |
+
"torch_dtype": "float32",
|
155 |
+
"transformers_version": null,
|
156 |
+
"use_auxiliary_head": true,
|
157 |
+
"use_batch_norm_in_fusion_residual": false,
|
158 |
+
"use_bias_in_fusion_residual": false
|
159 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d75e96bdb1355fb9075aa3ecd727daa78fbd2887f6c02dbf410aa4b0237a6ba8
|
3 |
+
size 148882609
|