Duplicate from nielsr/dpt-depth-estimation

Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Dpt Depth Estimation
+emoji: ⚡
+colorFrom: blue
+colorTo: red
+sdk: gradio
+sdk_version: 2.8.13
+app_file: app.py
+pinned: false
+duplicated_from: nielsr/dpt-depth-estimation
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference

app.py

@@ -0,0 +1,46 @@
+import gradio as gr
+from transformers import DPTFeatureExtractor, DPTForDepthEstimation
+import torch
+import numpy as np
+from PIL import Image
+
+torch.hub.download_url_to_file('http://images.cocodataset.org/val2017/000000039769.jpg', 'cats.jpg')
+
+feature_extractor = DPTFeatureExtractor.from_pretrained("Intel/dpt-large")
+model = DPTForDepthEstimation.from_pretrained("Intel/dpt-large")
+
+def process_image(image):
+    # prepare image for the model
+    encoding = feature_extractor(image, return_tensors="pt")
+    
+    # forward pass
+    with torch.no_grad():
+       outputs = model(**encoding)
+       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,
+                 ).squeeze()
+    output = prediction.cpu().numpy()
+    formatted = (output * 255 / np.max(output)).astype('uint8')
+    img = Image.fromarray(formatted)
+    return img
+    
+    return result
+    
+title = "Demo: zero-shot depth estimation with DPT"
+description = "Demo for Intel's DPT, a Dense Prediction Transformer for state-of-the-art dense prediction tasks such as semantic segmentation and depth estimation."
+examples =[['cats.jpg']]
+
+iface = gr.Interface(fn=process_image, 
+                     inputs=gr.inputs.Image(type="pil"), 
+                     outputs=gr.outputs.Image(type="pil", label="predicted depth"),
+                     title=title,
+                     description=description,
+                     examples=examples,
+                     enable_queue=True)
+iface.launch(debug=True)

requirements.txt

@@ -0,0 +1,4 @@
+torch
+git+https://github.com/nielsrogge/transformers.git@add_dpt_redesign#egg=transformers
+numpy
+Pillow