Upload 6 files

README.md

@@ -0,0 +1,22 @@
+# Image Classification (CPU/GPU)
+
+- **Model:** torchvision `mobilenet_v2` pretrained on ImageNet (Apache-2.0)
+- **Task:** Predict top-5 ImageNet classes for a given image.
+- **Note:** Here we just provide the resources for to run this models in the laptops we didn't develop this entire models we just use the open source models for the experiment this model is developed by TorchVision / PyTorch
+
+## Quick start (any project)
+
+```bash
+# 1) Create env
+python -m venv venv && source .venv/bin/activate  # Windows: ./venv/Scripts/activate
+
+# 2) Install deps
+pip install -r requirements.txt
+
+# 3) Run
+python main.py --help
+```
+
+> Tip: If you have a GPU + CUDA, PyTorch will auto-use it. If not, everything runs on CPU (slower but works).
+
+---

inference.py

@@ -0,0 +1,50 @@
+import torch
+from torchvision import models
+from PIL import Image
+import urllib.request
+import os
+
+# URL for ImageNet class labels
+IMAGENET_URL = "https://raw.githubusercontent.com/pytorch/hub/master/imagenet_classes.txt"
+
+def load_labels():
+    with urllib.request.urlopen(IMAGENET_URL) as f:
+        labels = [s.strip() for s in f.read().decode("utf-8").splitlines()]
+    return labels
+
+# Device selection
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# Load model
+model = models.mobilenet_v2(weights=models.MobileNet_V2_Weights.DEFAULT).to(device).eval()
+preprocess = models.MobileNet_V2_Weights.DEFAULT.transforms()
+
+# Online image
+online_image_url = "https://upload.wikimedia.org/wikipedia/commons/9/9a/Pug_600.jpg"
+online_image_path = "online_image.jpg"
+urllib.request.urlretrieve(online_image_url, online_image_path)
+
+# Offline image from same directory
+offline_image_path = "remiai.png"  # Replace with your actual image filename
+
+# Function to run inference
+def classify_image(image_path):
+    img = Image.open(image_path).convert("RGB")
+    x = preprocess(img).unsqueeze(0).to(device)
+    with torch.no_grad():
+        logits = model(x)
+        probs = torch.softmax(logits, dim=-1)[0]
+        top5 = torch.topk(probs, 5)
+
+    labels = load_labels()
+    print(f"Results for: {image_path}")
+    for p, idx in zip(top5.values, top5.indices):
+        print(f"{labels[idx]}: {float(p):.4f}")
+    print()
+
+# Run inference on both images
+classify_image(online_image_path)
+if os.path.exists(offline_image_path):
+    classify_image(offline_image_path)
+else:
+    print(f"Offline image '{offline_image_path}' not found.")

main.py

@@ -0,0 +1,34 @@
+import argparse, json, torch
+from torchvision import models, transforms
+from PIL import Image
+import urllib.request
+
+IMAGENET_URL = "https://raw.githubusercontent.com/pytorch/hub/master/imagenet_classes.txt"
+
+def load_labels():
+    with urllib.request.urlopen(IMAGENET_URL) as f:
+        labels = [s.strip() for s in f.read().decode("utf-8").splitlines()]
+    return labels
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--image", type=str, default=None, help="Path to an image")
+    args = parser.parse_args()
+
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    model = models.mobilenet_v2(weights=models.MobileNet_V2_Weights.DEFAULT).to(device).eval()
+
+    preprocess = models.MobileNet_V2_Weights.DEFAULT.transforms()
+    img = Image.open(args.image).convert("RGB") if args.image else Image.new("RGB", (224,224), "white")
+    x = preprocess(img).unsqueeze(0).to(device)
+    with torch.no_grad():
+        logits = model(x)
+        probs = torch.softmax(logits, dim=-1)[0]
+        top5 = torch.topk(probs, 5)
+
+    labels = load_labels()
+    for p, idx in zip(top5.values, top5.indices):
+        print(f"{labels[idx]}: {float(p):.4f}")
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,10 @@
+torch==2.1.0
+torchvision==0.16.0
+torchaudio==2.1.0
+transformers==4.38.2
+datasets==2.18.0
+Pillow==10.2.0
+numpy==1.26.4
+tqdm==4.66.2
+sentencepiece==0.1.99
+sentence-transformers==2.6.1