Duplicate from gainforest/tree-crown-delineation

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt 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
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz 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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl 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
+*.safetensors 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
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+example4.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: Tree Crown Delineation
+emoji: 🌴📊💚
+colorFrom: gray
+colorTo: purple
+sdk: gradio
+sdk_version: 3.24.1
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: gainforest/tree-crown-delineation
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,62 @@
+import torch
+import numpy as np
+import torchvision.transforms as T
+from torchgeo.trainers import SemanticSegmentationTask
+import gradio as gr
+from PIL import Image
+import cv2
+
+def load_model(checkpoint_path):
+    model = SemanticSegmentationTask.load_from_checkpoint(checkpoint_path)
+    return model
+
+def preprocess_image(inp):
+    compose = T.Compose([T.Resize((2048, 2048)), T.ToTensor()])
+    inp = compose(inp).unsqueeze(0)
+    return inp
+
+def predict_segmentation(model, inp):
+    with torch.no_grad():
+        y_hat = torch.nn.Softmax2d()(model(inp))
+    return y_hat.squeeze()
+
+def overlay_prediction(input_image, prediction_tensor, alpha=0.5, threshold=0.25):
+    # Convert the prediction tensor to a PIL image and resize it to match the input image size
+    prediction_image = T.ToPILImage()(prediction_tensor[0])
+    prediction_image = prediction_image.resize(input_image.size, resample=Image.NEAREST)
+    
+    # Apply the cv2.COLORMAP_INFERNO colormap
+    prediction_image = cv2.applyColorMap(np.array(prediction_image), cv2.COLORMAP_INFERNO)
+    prediction_image = Image.fromarray(prediction_image).convert("RGBA")
+    
+    overlay = Image.new("RGBA", prediction_image.size, (0, 0, 0, 0))
+    
+    for x in range(prediction_image.width):
+        for y in range(prediction_image.height):
+            r, g, b, a = prediction_image.getpixel((x, y))
+            if a / 255 > threshold:
+                overlay.putpixel((x, y), (r, g, b, int(255 * alpha)))
+
+    combined_image = Image.alpha_composite(input_image.convert("RGBA"), overlay)
+    return combined_image.convert("RGB")
+
+def predict(inp):
+    model = load_model("./unet_resnet50.ckpt")
+    # Check if a GPU is available and move the model to the GPU if possible
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    model.to(device)
+    preprocessed_image = preprocess_image(inp)
+    # Move the input tensor to the GPU if available
+    preprocessed_image = preprocessed_image.to(device)
+    segmentation_result = predict_segmentation(model, preprocessed_image)
+    # Move the output tensor back to the CPU for post-processing
+    segmentation_result = segmentation_result.cpu()
+    output_image = overlay_prediction(inp, segmentation_result)
+    return output_image
+
+gr.Interface(
+    fn=predict,
+    inputs=gr.inputs.Image(type="pil"),
+    outputs="image",
+    examples=["./example1.jpg", "./example2.jpg", "./example3.jpg"]
+).launch()

packages.txt

@@ -0,0 +1 @@
+python3-opencv

requirements.txt

@@ -0,0 +1,13 @@
+# pip install -r requirements.txt
+
+# Requirements for are you wearing a mask
+# A YOLOv5 powered face mask decector Gradio application
+
+gradio
+torch
+torchvision
+numpy
+opencv-python
+pillow
+segmentation-models-pytorch
+torchgeo

unet_resnet50.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4245f09404a6f0070222eca9ad2b1e80e92635c3f7ac69eaf2ce6826a9159e7e
+size 390784569