Duplicate from akhaliq/DPT-Large

Co-authored-by: Ahsen Khaliq <akhaliq@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 +1,38 @@
+---
+title: DPT Large
+emoji: 🐠
+colorFrom: red
+colorTo: blue
+sdk: gradio
+app_file: app.py
+pinned: false
+duplicated_from: akhaliq/DPT-Large
+---
+
+# Configuration
+
+`title`: _string_  
+Display title for the Space
+
+`emoji`: _string_  
+Space emoji (emoji-only character allowed)
+
+`colorFrom`: _string_  
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`colorTo`: _string_  
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`sdk`: _string_  
+Can be either `gradio` or `streamlit`
+
+`sdk_version` : _string_  
+Only applicable for `streamlit` SDK.  
+See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
+
+`app_file`: _string_  
+Path to your main application file (which contains either `gradio` or `streamlit` Python code).  
+Path is relative to the root of the repository.
+
+`pinned`: _boolean_  
+Whether the Space stays on top of your list.

app.py

@@ -0,0 +1,58 @@
+import cv2
+import torch
+import urllib.request
+import gradio as gr
+import matplotlib.pyplot as plt
+import numpy as np
+from PIL import Image
+
+url, filename = ("https://github.com/pytorch/hub/raw/master/images/dog.jpg", "dog.jpg")
+urllib.request.urlretrieve(url, filename)
+
+model_type = "DPT_Large"     # MiDaS v3 - Large     (highest accuracy, slowest inference speed)
+#model_type = "DPT_Hybrid"   # MiDaS v3 - Hybrid    (medium accuracy, medium inference speed)
+#model_type = "MiDaS_small"  # MiDaS v2.1 - Small   (lowest accuracy, highest inference speed)
+
+midas = torch.hub.load("intel-isl/MiDaS", model_type)
+
+device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
+midas.to(device)
+midas.eval()
+
+midas_transforms = torch.hub.load("intel-isl/MiDaS", "transforms")
+
+if model_type == "DPT_Large" or model_type == "DPT_Hybrid":
+    transform = midas_transforms.dpt_transform
+else:
+    transform = midas_transforms.small_transform
+
+def inference(img):
+    img = cv2.imread(img.name)
+    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+
+    input_batch = transform(img).to(device)
+
+    with torch.no_grad():
+        prediction = midas(input_batch)
+
+        prediction = torch.nn.functional.interpolate(
+            prediction.unsqueeze(1),
+            size=img.shape[:2],
+            mode="bicubic",
+            align_corners=False,
+        ).squeeze()
+
+    output = prediction.cpu().numpy()
+    formatted = (output * 255 / np.max(output)).astype('uint8')
+    img = Image.fromarray(formatted)
+    return img
+
+inputs =  gr.inputs.Image(type='file', label="Original Image")
+outputs = gr.outputs.Image(type="pil",label="Output Image")
+
+title = "DPT-Large"
+description = "Gradio demo for DPT-Large:Vision Transformers for Dense Prediction.To use it, simply upload your image, or click one of the examples to load them. Read more at the links below."
+article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2103.13413' target='_blank'>Vision Transformers for Dense Prediction</a> | <a href='https://github.com/intel-isl/MiDaS' target='_blank'>Github Repo</a></p>"
+
+examples=[['dog.jpg']]
+gr.Interface(inference, inputs, outputs, title=title, description=description, article=article, analytics_enabled=False,examples=examples,    enable_queue=True).launch(debug=True)

requirements.txt

@@ -0,0 +1,6 @@
+opencv-python-headless
+torch
+matplotlib
+numpy
+Pillow
+timm