Create app.py

app.py

@@ -0,0 +1,107 @@
+import gradio as gr
+import torch
+import torch.nn.functional as F
+import numpy as np
+from transformers import SegformerImageProcessor, SegformerForSemanticSegmentation
+from PIL import Image
+import os 
+from functools import partial
+
+
+def resize_image(image, target_size=1024):
+    h_img, w_img = image.size
+    if h_img < w_img:
+        new_h, new_w = target_size, int(w_img * (target_size / h_img))
+    else:
+        new_h, new_w  = int(h_img * (target_size / w_img)), target_size
+    
+    resized_img = image.resize((new_h, new_w))
+    return resized_img
+
+def segment_image(image, preprocessor, model, crop_size = (1024, 1024), num_classes = 40):
+    print(type(image))
+    
+    h_crop, w_crop = crop_size
+    print(image.size)
+    
+    img = torch.Tensor(np.array(resize_image(image, target_size=1024)).transpose(2, 0, 1)).unsqueeze(0).to(device)
+    batch_size, _, h_img, w_img = img.size()
+    print(img.size())
+    
+    h_grids = int(np.round(3/2*h_img/h_crop)) if h_img > h_crop else 1
+    w_grids = int(np.round(3/2*w_img/w_crop)) if w_img > w_crop else 1
+    print(h_grids, w_grids)
+    
+    h_stride = int((h_img - h_crop + h_grids -1)/(h_grids -1)) if h_grids > 1 else h_crop
+    w_stride = int((w_img - w_crop + w_grids -1)/(w_grids -1)) if w_grids > 1 else w_crop
+    print(h_stride, w_stride)
+    
+    preds = img.new_zeros((batch_size, num_classes, h_img, w_img))
+    count_mat = img.new_zeros((batch_size, 1, h_img, w_img))
+    
+    for h_idx in range(h_grids):
+        for w_idx in range(w_grids):
+          y1 = h_idx * h_stride
+          x1 = w_idx * w_stride
+          y2 = min(y1 + h_crop, h_img)
+          x2 = min(x1 + w_crop, w_img)
+          y1 = max(y2 - h_crop, 0)
+          x1 = max(x2 - w_crop, 0)
+          crop_img = img[:, :, y1:y2, x1:x2]
+          print(x1, x2, y1, y2)
+          with torch.no_grad():
+            inputs = preprocessor(crop_img, return_tensors = "pt")
+            outputs = model(**inputs)
+        
+          resized_logits = F.interpolate(
+              outputs.logits[0].unsqueeze(dim=0), size=crop_img.shape[-2:], mode="bilinear", align_corners=False
+          )
+          preds += F.pad(resized_logits,
+                          (int(x1), int(preds.shape[3] - x2), int(y1),
+                          int(preds.shape[2] - y2)))
+          count_mat[:, :, y1:y2, x1:x2] += 1
+    
+    assert (count_mat == 0).sum() == 0
+    preds = preds / count_mat
+    
+    preds = preds.argmax(dim=1)
+    
+    preds = F.interpolate(preds.unsqueeze(0).type(torch.uint8), size=image.size[::-1], mode='nearest')
+    label_pred = preds.squeeze().cpu().numpy()
+
+
+    seg_info = [(label_pred == int(id), label) for id, label in id2label.items()]
+    return (image, seg_info)
+
+
+if __name__ == "__main__":
+    device = 'cuda' if torch.cuda.is_available() else 'cpu'
+    print(device)
+    
+    # Load model and processor
+    preprocessor = SegformerImageProcessor.from_pretrained("EPFL-ECEO/segformer-b2-finetuned-coralscapes-1024-1024")
+    model = SegformerForSemanticSegmentation.from_pretrained("EPFL-ECEO/segformer-b2-finetuned-coralscapes-1024-1024").to(device)
+    model.eval()
+ 
+    id2label = {"1": "seagrass", "2": "trash", "3": "other coral dead", "4": "other coral bleached", "5": "sand", "6": "other coral alive", "7": "human", "8": "transect tools", "9": "fish", "10": "algae covered substrate", "11": "other animal", "12": "unknown hard substrate", "13": "background", "14": "dark", "15": "transect line", "16": "massive/meandering bleached", "17": "massive/meandering alive", "18": "rubble", "19": "branching bleached", "20": "branching dead", "21": "millepora", "22": "branching alive", "23": "massive/meandering dead", "24": "clam", "25": "acropora alive", "26": "sea cucumber", "27": "turbinaria", "28": "table acropora alive", "29": "sponge", "30": "anemone", "31": "pocillopora alive", "32": "table acropora dead", "33": "meandering bleached", "34": "stylophora alive", "35": "sea urchin", "36": "meandering alive", "37": "meandering dead", "38": "crown of thorn", "39": "dead clam"}
+    label2color = {"human": [255, 0, 0], "background": [29, 162, 216], "fish": [255, 255, 0], "sand": [194, 178, 128], "rubble": [161, 153, 128], "unknown hard substrate": [125, 125, 125], "algae covered substrate": [125, 163, 125], "dark": [31, 31, 31], "branching bleached": [252, 231, 240], "branching dead": [123, 50, 86], "branching alive": [226, 91, 157], "stylophora alive": [255, 111, 194], "pocillopora alive": [255, 146, 150], "acropora alive": [236, 128, 255], "table acropora alive": [189, 119, 255], "table acropora dead": [85, 53, 116], "millepora": [244, 150, 115], "turbinaria": [228, 255, 119], "other coral bleached": [250, 224, 225], "other coral dead": [114, 60, 61], "other coral alive": [224, 118, 119], "massive/meandering alive": [236, 150, 21], "massive/meandering dead": [134, 86, 18], "massive/meandering bleached": [255, 248, 228], "meandering alive": [230, 193, 0], "meandering dead": [119, 100, 14], "meandering bleached": [251, 243, 216], "transect line": [0, 255, 0], "transect tools": [8, 205, 12], "sea urchin": [0, 142, 255], "sea cucumber": [0, 231, 255], "anemone": [0, 255, 189], "sponge": [240, 80, 80], "clam": [189, 255, 234], "other animal": [0, 255, 255], "trash": [255, 0, 134], "seagrass": [125, 222, 125], "crown of thorn": [179, 245, 234], "dead clam": [89, 155, 134]}
+    label2colorhex = {k:'#%02x%02x%02x' % tuple(v) for k,v in label2color.items()}
+    print(label2colorhex)
+
+    with gr.Blocks(title="Coral Segmentation with SegFormer") as demo:
+        gr.Markdown("""<h1><center>Coral Segmentation with SegFormer</center></h1>""") 
+        with gr.Row():
+            img_input = gr.Image(type="pil", label="Input image")
+            img_output = gr.AnnotatedImage(label="Predictions", color_map=label2colorhex)
+
+        section_btn = gr.Button("Segment Image")
+        section_btn.click(partial(segment_image, preprocessor=preprocessor, model=model), img_input, img_output)
+        
+        example_files = os.listdir('assets/examples')
+        example_files.sort()
+        print(example_files)
+        example_files = [os.path.join('assets/examples', filename) for filename in example_files]
+
+        gr.Examples(examples=example_files, inputs=img_input, outputs=img_output)
+
+    demo.launch()