Try1

app.py

@@ -1,15 +1,15 @@
 
-import os
-import subprocess
-import sys
-import requests
-import zipfile
-import gradio as gr
-import torch
+import matplotlib.pyplot as plt
 import numpy as np
+import torch
 from torchvision.transforms import ToTensor
 from PIL import Image
+import io
 import cv2
+import gradio as gr
+import os
+import requests
+import zipfile
 
 # Ensure the necessary model files are available
 def download_file(url, destination):
@@ -24,38 +24,12 @@ if not os.path.exists("weights/sam_vit_h_4b8939.pth"):
 
 # Clone EfficientSAM repository if not already cloned
 if not os.path.exists("EfficientSAM"):
-    subprocess.run(["git", "clone", "https://github.com/yformer/EfficientSAM.git"])
-
-# Add EfficientSAM to Python path
-sys.path.append(os.path.abspath("EfficientSAM"))
-
-# Install dependencies
-subprocess.run(["pip", "install", "git+https://github.com/facebookresearch/segment-anything.git"])
-
-from segment_anything import sam_model_registry, SamAutomaticMaskGenerator
-from efficient_sam.build_efficient_sam import build_efficient_sam_vits
-
-# Constants
-DEVICE = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
-MODEL_TYPE = "vit_h"
-CHECKPOINT_PATH = "weights/sam_vit_h_4b8939.pth"
-EFF_SAM_ZIP_PATH = "weights/efficient_sam_vits.pt.zip"
-EFF_SAM_EXTRACT_DIR = "weights/efficient_sam_vits"
+    os.makedirs("EfficientSAM", exist_ok=True)
+    os.system("git clone https://github.com/yformer/EfficientSAM.git EfficientSAM")
 
-# Load SAM model
-sam = sam_model_registry[MODEL_TYPE](checkpoint=CHECKPOINT_PATH).to(device=DEVICE)
-mask_generator_sam = SamAutomaticMaskGenerator(sam)
+os.chdir("EfficientSAM")
 
-# Download EfficientSAM weights if not present
-if not os.path.exists(EFF_SAM_ZIP_PATH):
-    download_file("https://example.com/path/to/efficient_sam_vits.pt.zip", EFF_SAM_ZIP_PATH)
-
-# Extract EfficientSAM weights if not already extracted
-if not os.path.exists(EFF_SAM_EXTRACT_DIR):
-    with zipfile.ZipFile(EFF_SAM_ZIP_PATH, 'r') as zip_ref:
-        zip_ref.extractall(EFF_SAM_EXTRACT_DIR)
-
-efficient_sam_vits_model = build_efficient_sam_vits()
+!pip install git+https://github.com/facebookresearch/segment-anything.git
 
 from segment_anything.utils.amg import (
     batched_mask_to_box,
@@ -79,7 +53,6 @@ def process_small_region(rles):
         unchanged = unchanged and not changed
         new_masks.append(torch.as_tensor(mask).unsqueeze(0))
         scores.append(float(unchanged))
-
     masks = torch.cat(new_masks, dim=0)
     boxes = batched_mask_to_box(masks)
     keep_by_nms = batched_nms(
@@ -170,6 +143,18 @@ def process_image(image):
 
     return [image, sam_annotated_image, efficient_sam_annotated_image]
 
+# Download EfficientSAM model
+if not os.path.exists("weights/efficient_sam_vits.pt.zip"):
+    download_file("https://example.com/path/to/efficient_sam_vits.pt.zip", "weights/efficient_sam_vits.pt.zip")
+
+# Extract EfficientSAM model
+with zipfile.ZipFile("weights/efficient_sam_vits.pt.zip", 'r') as zip_ref:
+    zip_ref.extractall("weights")
+
+from efficient_sam.build_efficient_sam import build_efficient_sam_vits
+efficient_sam_vits_model = build_efficient_sam_vits()
+efficient_sam_vits_model.eval()
+
 # Gradio interface
 interface = gr.Interface(
     fn=process_image,
@@ -181,5 +166,3 @@ interface = gr.Interface(
 
 interface.launch(debug=True)
 
-
-