Upload 2 files

app.py

@@ -4,11 +4,10 @@ import torch
 import numpy as np
 import cv2
 import matplotlib.pyplot as plt
-import base64
-import json
-
-from segment_anything import sam_model_registry, SamPredictor
-from segment_anything.utils.onnx import SamOnnxModel
+from typing import Tuple, Dict
+from timeit import default_timer as timer
+from skimage import io, transform
+import os
 
 import torch.nn.functional as F
 
@@ -23,6 +22,23 @@ model_type = "vit_b"
 medsam_model = create_sam_model(model_type,checkpoint,device)
 
 # 3.Predict fn
+def show_mask(mask, ax):
+    color = np.array([30/255, 144/255, 255/255, 0.6])
+    h, w = mask.shape[-2:]
+    mask_image = mask.reshape(h, w, 1) * color.reshape(1, 1, -1)
+    ax.imshow(mask_image)
+
+def show_points(coords, labels, ax, marker_size=375):
+    pos_points = coords[labels==1]
+    neg_points = coords[labels==0]
+    ax.scatter(pos_points[:, 0], pos_points[:, 1], color='green', marker='*', s=marker_size, edgecolor='white', linewidth=1.25)
+    ax.scatter(neg_points[:, 0], neg_points[:, 1], color='red', marker='*', s=marker_size, edgecolor='white', linewidth=1.25)
+
+def show_box(box, ax):
+    x0, y0 = box[0], box[1]
+    w, h = box[2] - box[0], box[3] - box[1]
+    ax.add_patch(plt.Rectangle((x0, y0), w, h, edgecolor='green', facecolor=(0,0,0,0), lw=2))
+
 @torch.no_grad()
 def medsam_inference(medsam_model, img_embed, box_1024, H, W):
     box_torch = torch.as_tensor(box_1024, dtype=torch.float, device=img_embed.device)

model.py

@@ -1,9 +1,6 @@
-import torch
-import numpy as np
-import cv2
+
 import matplotlib.pyplot as plt
-from segment_anything import sam_model_registry, SamPredictor
-from segment_anything.utils.onnx import SamOnnxModel
+from segment_anything import sam_model_registry
 import torch.nn.functional as F
 
 def create_sam_model(model_type, checkpoint, device: str = "cpu"):