Upload 4 files

README.md

@@ -0,0 +1,80 @@
+---
+license: apache-2.0
+tags:
+- vision
+- depth-estimation
+- dinov2
+inference: false
+---
+
+# Model Card: DPT model with DINOv2 backbone
+
+## Model Details
+
+DPT (Dense Prediction Transformer) model with DINOv2 backbone as proposed in [DINOv2: Learning Robust Visual Features without Supervision](https://arxiv.org/abs/2304.07193) by Oquab et al.
+
+<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/dpt_architecture.jpg"
+alt="drawing" width="600"/>
+
+<small> DPT architecture. Taken from the <a href="https://arxiv.org/abs/2103.13413" target="_blank">original paper</a>. </small>
+
+### Resources
+
+- [DINOv2 Paper](https://arxiv.org/abs/2304.07193)
+- [DPT Paper](https://arxiv.org/abs/2103.13413)
+
+
+### Use with Transformers
+
+```python
+from transformers import AutoImageProcessor, DPTForDepthEstimation
+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("facebook/dpt-dinov2-base-nyu")
+model = DPTForDepthEstimation.from_pretrained("facebook/dpt-dinov2-base-nyu")
+
+# 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,
+)
+
+# visualize the prediction
+output = prediction.squeeze().cpu().numpy()
+formatted = (output * 255 / np.max(output)).astype("uint8")
+depth = Image.fromarray(formatted)
+```
+
+## Model Use
+
+### Intended Use
+
+The model is intended to showcase that using the DPT framework with DINOv2 as backbone yields a powerful depth estimator.
+
+### BibTeX entry and citation info
+
+```bibtex
+@misc{oquab2023dinov2,
+      title={DINOv2: Learning Robust Visual Features without Supervision}, 
+      author={Maxime Oquab and Timothée Darcet and Théo Moutakanni and Huy Vo and Marc Szafraniec and Vasil Khalidov and Pierre Fernandez and Daniel Haziza and Francisco Massa and Alaaeldin El-Nouby and Mahmoud Assran and Nicolas Ballas and Wojciech Galuba and Russell Howes and Po-Yao Huang and Shang-Wen Li and Ishan Misra and Michael Rabbat and Vasu Sharma and Gabriel Synnaeve and Hu Xu and Hervé Jegou and Julien Mairal and Patrick Labatut and Armand Joulin and Piotr Bojanowski},
+      year={2023},
+      eprint={2304.07193},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}
+```

config.json

@@ -0,0 +1,159 @@
+{
+  "_commit_hash": null,
+  "add_projection": true,
+  "architectures": [
+    "DPTForDepthEstimation"
+  ],
+  "attention_probs_dropout_prob": null,
+  "auxiliary_loss_weight": 0.4,
+  "backbone_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "apply_layernorm": false,
+    "architectures": [
+      "Dinov2Model"
+    ],
+    "attention_probs_dropout_prob": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 518,
+    "initializer_range": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-06,
+    "layerscale_value": 1.0,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "mlp_ratio": 4,
+    "model_type": "dinov2",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "out_features": [
+      "stage3",
+      "stage6",
+      "stage9",
+      "stage12"
+    ],
+    "out_indices": [
+      3,
+      6,
+      9,
+      12
+    ],
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "reshape_hidden_states": false,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4",
+      "stage5",
+      "stage6",
+      "stage7",
+      "stage8",
+      "stage9",
+      "stage10",
+      "stage11",
+      "stage12"
+    ],
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "transformers_version": "4.35.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_swiglu_ffn": false
+  },
+  "backbone_featmap_shape": null,
+  "backbone_out_indices": null,
+  "fusion_hidden_size": 256,
+  "head_in_index": -1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": null,
+  "hidden_size": 768,
+  "image_size": null,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "is_hybrid": false,
+  "layer_norm_eps": null,
+  "model_type": "dpt",
+  "neck_hidden_sizes": [
+    96,
+    192,
+    384,
+    768
+  ],
+  "neck_ignore_stages": [],
+  "num_attention_heads": null,
+  "num_channels": null,
+  "num_hidden_layers": null,
+  "patch_size": null,
+  "qkv_bias": null,
+  "readout_type": "project",
+  "reassemble_factors": [
+    4,
+    2,
+    1,
+    0.5
+  ],
+  "semantic_classifier_dropout": 0.1,
+  "semantic_loss_ignore_index": 255,
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "use_auxiliary_head": true,
+  "use_batch_norm_in_fusion_residual": false,
+  "use_bias_in_fusion_residual": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60460ae14c3abc07875faf44f6769811e0a410c7dfb3d9d5b82df909d3f5ad4a
+size 447849116

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": false,
+  "do_resize": false,
+  "ensure_multiple_of": 1,
+  "image_mean": [
+    123.675,
+    116.28,
+    103.53
+  ],
+  "image_processor_type": "DPTImageProcessor",
+  "image_std": [
+    58.395,
+    57.12,
+    57.375
+  ],
+  "keep_aspect_ratio": false,
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 384,
+    "width": 384
+  },
+  "size_divisor": 14
+}