Duplicate from LiheYoung/depth-anything-large-hf

Co-authored-by: Niels Rogge <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,98 @@
+---
+license: apache-2.0
+tags:
+- vision
+pipeline_tag: depth-estimation
+widget:
+- inference: false
+---
+
+# Depth Anything (large-sized model, Transformers version) 
+
+Depth Anything model. It was introduced in the paper [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://arxiv.org/abs/2401.10891) by Lihe Yang et al. and first released in [this repository](https://github.com/LiheYoung/Depth-Anything).
+
+[Online demo](https://huggingface.co/spaces/LiheYoung/Depth-Anything) is also provided.
+
+Disclaimer: The team releasing Depth Anything did not write a model card for this model so this model card has been written by the Hugging Face team.
+
+## Model description
+
+Depth Anything leverages the [DPT](https://huggingface.co/docs/transformers/model_doc/dpt) architecture with a [DINOv2](https://huggingface.co/docs/transformers/model_doc/dinov2) backbone.
+
+The model is trained on ~62 million images, obtaining state-of-the-art results for both relative and absolute depth estimation.
+
+<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/depth_anything_overview.jpg"
+alt="drawing" width="600"/>
+
+<small> Depth Anything overview. Taken from the <a href="https://arxiv.org/abs/2401.10891">original paper</a>.</small>
+
+## Intended uses & limitations
+
+You can use the raw model for tasks like zero-shot depth estimation. See the [model hub](https://huggingface.co/models?search=depth-anything) to look for
+other versions on a task that interests you.
+
+### How to use
+
+Here is how to use this model to perform zero-shot depth estimation:
+
+```python
+from transformers import pipeline
+from PIL import Image
+import requests
+
+# load pipe
+pipe = pipeline(task="depth-estimation", model="LiheYoung/depth-anything-large-hf")
+
+# load image
+url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
+image = Image.open(requests.get(url, stream=True).raw)
+
+# inference
+depth = pipe(image)["depth"]
+```
+
+Alternatively, one can use the classes themselves:
+
+```python
+from transformers import AutoImageProcessor, AutoModelForDepthEstimation
+import torch
+import numpy as np
+from PIL import Image
+import requests
+
+url = "http://images.cocodataset.org/val2017/000000039769.jpg"
+image = Image.open(requests.get(url, stream=True).raw)
+
+image_processor = AutoImageProcessor.from_pretrained("LiheYoung/depth-anything-large-hf")
+model = AutoModelForDepthEstimation.from_pretrained("LiheYoung/depth-anything-large-hf")
+
+# prepare image for the model
+inputs = image_processor(images=image, return_tensors="pt")
+
+with torch.no_grad():
+    outputs = model(**inputs)
+    predicted_depth = outputs.predicted_depth
+
+# interpolate to original size
+prediction = torch.nn.functional.interpolate(
+    predicted_depth.unsqueeze(1),
+    size=image.size[::-1],
+    mode="bicubic",
+    align_corners=False,
+)
+```
+For more code examples, we refer to the [documentation](https://huggingface.co/transformers/main/model_doc/depth_anything.html#).
+
+
+### BibTeX entry and citation info
+
+```bibtex
+@misc{yang2024depth,
+      title={Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data}, 
+      author={Lihe Yang and Bingyi Kang and Zilong Huang and Xiaogang Xu and Jiashi Feng and Hengshuang Zhao},
+      year={2024},
+      eprint={2401.10891},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}
+```

config.json

@@ -0,0 +1,81 @@
+{
+  "_commit_hash": null,
+  "architectures": [
+    "DepthAnythingForDepthEstimation"
+  ],
+  "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": [
+      "stage21",
+      "stage22",
+      "stage23",
+      "stage24"
+    ],
+    "out_indices": [
+      21,
+      22,
+      23,
+      24
+    ],
+    "patch_size": 14,
+    "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"
+  },
+  "fusion_hidden_size": 256,
+  "head_hidden_size": 32,
+  "head_in_index": -1,
+  "initializer_range": 0.02,
+  "model_type": "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
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc27360a3e6906e5ddd8f618e2dcde11362327361918b8f76793e42e25de31b3
+size 1341322868

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "do_normalize": true,
+  "do_pad": false,
+  "do_rescale": true,
+  "do_resize": true,
+  "ensure_multiple_of": 14,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "DPTImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "keep_aspect_ratio": true,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 518,
+    "width": 518
+  },
+  "size_divisor": null
+}