promptda_vitl_hf / config.json
haotongl
update
8ca53ce
{
"_commit_hash": null,
"architectures": [
"PromptDepthAnythingForDepthEstimation"
],
"backbone": null,
"backbone_config": {
"architectures": [
"Dinov2Model"
],
"hidden_size": 1024,
"image_size": 518,
"model_type": "dinov2",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"out_features": [
"stage5",
"stage12",
"stage18",
"stage24"
],
"out_indices": [
5,
12,
18,
24
],
"reshape_hidden_states": false,
"stage_names": [
"stem",
"stage1",
"stage2",
"stage3",
"stage4",
"stage5",
"stage6",
"stage7",
"stage8",
"stage9",
"stage10",
"stage11",
"stage12",
"stage13",
"stage14",
"stage15",
"stage16",
"stage17",
"stage18",
"stage19",
"stage20",
"stage21",
"stage22",
"stage23",
"stage24"
],
"torch_dtype": "float32"
},
"backbone_kwargs": null,
"depth_estimation_type": "metric",
"fusion_hidden_size": 256,
"head_hidden_size": 32,
"head_in_index": -1,
"initializer_range": 0.02,
"max_depth": 1,
"model_type": "prompt_depth_anything",
"neck_hidden_sizes": [
256,
512,
1024,
1024
],
"patch_size": 14,
"reassemble_factors": [
4,
2,
1,
0.5
],
"reassemble_hidden_size": 1024,
"torch_dtype": "float32",
"transformers_version": null,
"use_pretrained_backbone": false,
"use_timm_backbone": false
}