Depth Estimation
Transformers
Safetensors
tipsv2_dpt
feature-extraction
vision
surface-normals
semantic-segmentation
dense-prediction
custom_code
Instructions to use google/tipsv2-so400m14-dpt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/tipsv2-so400m14-dpt with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("depth-estimation", model="google/tipsv2-so400m14-dpt", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("google/tipsv2-so400m14-dpt", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Upload config.json with huggingface_hub
Browse files- config.json +30 -0
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "tipsv2_dpt",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"TIPSv2DPTModel"
|
| 5 |
+
],
|
| 6 |
+
"auto_map": {
|
| 7 |
+
"AutoConfig": "configuration_dpt.TIPSv2DPTConfig",
|
| 8 |
+
"AutoModel": "modeling_dpt.TIPSv2DPTModel"
|
| 9 |
+
},
|
| 10 |
+
"channels": 256,
|
| 11 |
+
"readout_type": "project",
|
| 12 |
+
"num_depth_bins": 256,
|
| 13 |
+
"min_depth": 0.001,
|
| 14 |
+
"max_depth": 10.0,
|
| 15 |
+
"num_seg_classes": 150,
|
| 16 |
+
"backbone_repo": "google/tipsv2-so400m14",
|
| 17 |
+
"embed_dim": 1152,
|
| 18 |
+
"block_indices": [
|
| 19 |
+
6,
|
| 20 |
+
13,
|
| 21 |
+
20,
|
| 22 |
+
26
|
| 23 |
+
],
|
| 24 |
+
"post_process_channels": [
|
| 25 |
+
144,
|
| 26 |
+
288,
|
| 27 |
+
576,
|
| 28 |
+
1152
|
| 29 |
+
]
|
| 30 |
+
}
|