Upload 10 files

.gitattributes

@@ -1,35 +1,40 @@
-*.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
-*.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
+*.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
+*.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
+bicycle.jpg filter=lfs diff=lfs merge=lfs -text
+buildings.jpg filter=lfs diff=lfs merge=lfs -text
+chicago.jpg filter=lfs diff=lfs merge=lfs -text
+spain.jpg filter=lfs diff=lfs merge=lfs -text
+street.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,12 +1,12 @@
----
-title: GradioAssignmentTask3
-emoji: 🏃
-colorFrom: purple
-colorTo: pink
-sdk: gradio
-sdk_version: 5.49.1
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: GradioAssignmentTask3
+emoji: 🏃
+colorFrom: purple
+colorTo: pink
+sdk: gradio
+sdk_version: 5.49.1
+app_file: app.py
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,98 @@
+import gradio as gr
+from matplotlib import gridspec
+import matplotlib.pyplot as plt
+import numpy as np
+from PIL import Image
+import torch
+from transformers import AutoImageProcessor, AutoModelForSemanticSegmentation
+
+MODEL_ID = "nvidia/segformer-b4-finetuned-cityscapes-1024-1024"
+processor = AutoImageProcessor.from_pretrained(MODEL_ID)
+model = AutoModelForSemanticSegmentation.from_pretrained(MODEL_ID)
+
+def ade_palette():
+    """ADE20K palette that maps each class to RGB values."""
+    return [
+        [255, 0, 0], [0, 128, 0], [0, 0, 255], [255, 255, 0],
+        [255, 165, 0], [128, 0, 128], [0, 255, 255], [255, 0, 255],
+        [255, 192, 203], [165, 42, 42], [0, 128, 128], [50, 205, 50],
+        [0, 0, 128], [128, 128, 0], [128, 0, 0], [135, 206, 235],
+        [128, 128, 128], [245, 245, 220], [75, 0, 130]
+    ]
+
+labels_list = []
+with open("labels.txt", "r", encoding="utf-8") as fp:
+    for line in fp:
+        labels_list.append(line.rstrip("\n"))
+
+colormap = np.asarray(ade_palette(), dtype=np.uint8)
+
+def label_to_color_image(label):
+    if label.ndim != 2:
+        raise ValueError("Expect 2-D input label")
+    if np.max(label) >= len(colormap):
+        raise ValueError("label value too large.")
+    return colormap[label]
+
+def draw_plot(pred_img, seg_np):
+    fig = plt.figure(figsize=(20, 15))
+    grid_spec = gridspec.GridSpec(1, 2, width_ratios=[6, 1])
+
+    plt.subplot(grid_spec[0])
+    plt.imshow(pred_img)
+    plt.axis('off')
+
+    LABEL_NAMES = np.asarray(labels_list)
+    FULL_LABEL_MAP = np.arange(len(LABEL_NAMES)).reshape(len(LABEL_NAMES), 1)
+    FULL_COLOR_MAP = label_to_color_image(FULL_LABEL_MAP)
+
+    unique_labels = np.unique(seg_np.astype("uint8"))
+    ax = plt.subplot(grid_spec[1])
+    plt.imshow(FULL_COLOR_MAP[unique_labels].astype(np.uint8), interpolation="nearest")
+    ax.yaxis.tick_right()
+    plt.yticks(range(len(unique_labels)), LABEL_NAMES[unique_labels])
+    plt.xticks([], [])
+    ax.tick_params(width=0.0, labelsize=25)
+    return fig
+
+def run_inference(input_img):
+    # input: numpy array from gradio -> PIL
+    img = Image.fromarray(input_img.astype(np.uint8)) if isinstance(input_img, np.ndarray) else input_img
+    if img.mode != "RGB":
+        img = img.convert("RGB")
+
+    inputs = processor(images=img, return_tensors="pt")
+    with torch.no_grad():
+        outputs = model(**inputs)
+        logits = outputs.logits  # (1, C, h/4, w/4)
+
+    # resize to original
+    upsampled = torch.nn.functional.interpolate(
+        logits, size=img.size[::-1], mode="bilinear", align_corners=False
+    )
+    seg = upsampled.argmax(dim=1)[0].cpu().numpy().astype(np.uint8)  # (H,W)
+
+    # colorize & overlay
+    color_seg = colormap[seg]                                # (H,W,3)
+    pred_img = (np.array(img) * 0.5 + color_seg * 0.5).astype(np.uint8)
+
+    fig = draw_plot(pred_img, seg)
+    return fig
+
+demo = gr.Interface(
+    fn=run_inference,
+    inputs=gr.Image(type="numpy", label="Input Image"),
+    outputs=gr.Plot(label="Overlay + Legend"),
+    examples=[
+        "bicycle.jpg",
+        "buildings.jpg",
+        "chicago.jpg",
+        "spain.jpg",
+        "street.jpg"
+    ],
+    flagging_mode="never",
+    cache_examples=False,
+)
+
+if __name__ == "__main__":
+    demo.launch()

labels.txt

@@ -0,0 +1,19 @@
+road
+sidewalk
+building
+wall
+fence
+pole
+traffic light
+traffic sign
+vegetation
+terrain
+sky
+person
+rider
+car
+truck
+bus
+train
+motorcycle
+bicycle

requirements.txt

@@ -0,0 +1,6 @@
+torch
+transformers>=4.41.0
+gradio>=4.0.0
+Pillow
+numpy
+matplotlib