a

README.md

@@ -0,0 +1,94 @@
+---
+license: apache-2.0
+tags:
+- vision
+- depth-estimation
+widget:
+- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
+  example_title: Tiger
+- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
+  example_title: Teapot
+- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
+  example_title: Palace
+---
+
+# GLPN fine-tuned on NYUv2
+
+Global-Local Path Networks (GLPN) model trained on NYUv2 for monocular depth estimation. It was introduced in the paper [Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth](https://arxiv.org/abs/2201.07436) by Kim et al. and first released in [this repository](https://github.com/vinvino02/GLPDepth). 
+
+Disclaimer: The team releasing GLPN did not write a model card for this model so this model card has been written by the Hugging Face team.
+
+## Model description
+
+GLPN uses SegFormer as backbone and adds a lightweight head on top for depth estimation.
+
+![model image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/glpn_architecture.jpg)
+
+## Intended uses & limitations
+
+You can use the raw model for monocular depth estimation. See the [model hub](https://huggingface.co/models?search=glpn) to look for
+fine-tuned versions on a task that interests you.
+
+### How to use
+
+Here is how to use this model:
+
+```python
+from transformers import GLPNFeatureExtractor, GLPNForDepthEstimation
+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)
+
+feature_extractor = GLPNFeatureExtractor.from_pretrained("vinvino02/glpn-nyu")
+model = GLPNForDepthEstimation.from_pretrained("vinvino02/glpn-nyu")
+
+# prepare image for the model
+inputs = feature_extractor(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)
+```
+
+For more code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/master/en/model_doc/glpn).
+
+### BibTeX entry and citation info
+
+```bibtex
+@article{DBLP:journals/corr/abs-2201-07436,
+  author    = {Doyeon Kim and
+               Woonghyun Ga and
+               Pyunghwan Ahn and
+               Donggyu Joo and
+               Sehwan Chun and
+               Junmo Kim},
+  title     = {Global-Local Path Networks for Monocular Depth Estimation with Vertical
+               CutDepth},
+  journal   = {CoRR},
+  volume    = {abs/2201.07436},
+  year      = {2022},
+  url       = {https://arxiv.org/abs/2201.07436},
+  eprinttype = {arXiv},
+  eprint    = {2201.07436},
+  timestamp = {Fri, 21 Jan 2022 13:57:15 +0100},
+  biburl    = {https://dblp.org/rec/journals/corr/abs-2201-07436.bib},
+  bibsource = {dblp computer science bibliography, https://dblp.org}
+}
+```

config.json

@@ -0,0 +1,69 @@
+{
+  "architectures": [
+    "GLPNForDepthEstimation"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.1,
+  "decoder_hidden_size": 64,
+  "depths": [
+    3,
+    8,
+    27,
+    3
+  ],
+  "downsampling_rates": [
+    1,
+    4,
+    8,
+    16
+  ],
+  "drop_path_rate": 0.1,
+  "head_in_index": -1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_sizes": [
+    64,
+    128,
+    320,
+    512
+  ],
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-06,
+  "max_depth": 10,
+  "mlp_ratios": [
+    4,
+    4,
+    4,
+    4
+  ],
+  "model_type": "glpn",
+  "num_attention_heads": [
+    1,
+    2,
+    5,
+    8
+  ],
+  "num_channels": 3,
+  "num_encoder_blocks": 4,
+  "patch_sizes": [
+    7,
+    3,
+    3,
+    3
+  ],
+  "sr_ratios": [
+    8,
+    4,
+    2,
+    1
+  ],
+  "strides": [
+    4,
+    2,
+    2,
+    2
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0.dev0"
+}

preprocessor_config.json

@@ -0,0 +1,7 @@
+{
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "GLPNFeatureExtractor",
+  "resample": 2,
+  "size_divisor": 32
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c353b12e5f4e5fafd0053d1c19bf60dfb1562b74db4728c6920a2cf44782b603
+size 245258793