Upload 4 files

README.md

@@ -0,0 +1,28 @@
+# Image Captioning (CPU/GPU)
+
+- **Model:** `nlpconnect/vit-gpt2-image-captioning` (MIT)
+- **Task:** Generate a caption 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 nlpconnect
+
+## 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).
+
+---
+and while running the main.py code using command then only you the output 
+**Use:** python main.py --image remiai.png or python main.py --image sample.jpg 
+
+other wise you get the output like this 
+usage: main.py [-h] --image IMAGE
+error: the following arguments are required: --image

main.py

@@ -0,0 +1,27 @@
+import argparse, torch
+from transformers import VisionEncoderDecoderModel, ViTImageProcessor, AutoTokenizer
+from PIL import Image
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--image", type=str, required=True)
+    parser.add_argument("--max_length", type=int, default=20)
+    args = parser.parse_args()
+
+    model_id = "nlpconnect/vit-gpt2-image-captioning"
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+    model = VisionEncoderDecoderModel.from_pretrained(model_id).to(device)
+    feature_extractor = ViTImageProcessor.from_pretrained(model_id)
+    tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+    img = Image.open(args.image).convert("RGB")
+    pixel_values = feature_extractor(images=[img], return_tensors="pt").pixel_values.to(device)
+
+    with torch.no_grad():
+        output_ids = model.generate(pixel_values, max_length=args.max_length)[0]
+    caption = tokenizer.decode(output_ids, skip_special_tokens=True)
+    print(caption)
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,10 @@
+torch>=2.0.0
+torchvision>=0.15.0
+transformers>=4.40.0
+sentence-transformers>=2.2.2
+easyocr>=1.7.1
+openai-whisper>=20231106
+TTS>=0.22.0
+pillow>=9.5.0
+accelerate>=0.26.0
+numpy>=1.24.0