upload app

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* 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
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.jpeg filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,17 @@
+import os
+import gradio as gr
+from model import predict
+
+examples_dir = "assets/examples/"
+examples = [[os.path.join(examples_dir, filename)] for filename in os.listdir(examples_dir)]
+
+interface = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(type="pil"),
+    outputs=gr.Image(type="pil"),
+    title="DepthPro: Monocular Depth Estimation",
+    examples=examples,
+)
+
+if __name__ == "__main__":
+    interface.launch()

model.py

@@ -0,0 +1,37 @@
+from PIL import Image
+import torch
+
+# custom installation from this PR: https://github.com/huggingface/transformers/pull/34583
+# !pip install git+https://github.com/geetu040/transformers.git@depth-pro-projects#egg=transformers
+from transformers import DepthProImageProcessorFast, DepthProForDepthEstimation
+
+# initialize processor and model
+checkpoint = "geetu040/DepthPro"
+revision = "project"
+image_processor = DepthProImageProcessorFast.from_pretrained(checkpoint, revision=revision)
+model = DepthProForDepthEstimation.from_pretrained(checkpoint, revision=revision)
+model = model.to('cuda')
+
+def predict(image):
+	# inference
+
+	# prepare image for the model
+	inputs = image_processor(images=image, return_tensors="pt")
+	inputs = {k: v.to('cuda') for k, v in inputs.items()}
+
+	with torch.no_grad():
+		outputs = model(**inputs)
+
+	# interpolate to original size
+	post_processed_output = image_processor.post_process_depth_estimation(
+		outputs, target_sizes=[(image.height, image.width)],
+	)
+
+	# visualize the prediction
+	depth = post_processed_output[0]["predicted_depth"]
+	depth = (depth - depth.min()) / depth.max()
+	depth = depth * 255.
+	depth = depth.detach().cpu().numpy()
+	depth = Image.fromarray(depth.astype("uint8"))
+
+	return depth

requirements.txt

@@ -0,0 +1,6 @@
+gradio
+numpy
+pillow
+torch
+torchvision
+git+https://github.com/geetu040/transformers.git@depth-pro-projects#egg=transformers