Update README.md

README.md

@@ -10,9 +10,10 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# image-caption-generator
+# Image-caption-generator
+
+This model is trained on [Flickr8k](https://www.kaggle.com/datasets/nunenuh/flickr8k) dataset to generate captions given an image.
 
-This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
 - eval_loss: 0.2536
 - eval_runtime: 25.369
@@ -21,19 +22,54 @@ It achieves the following results on the evaluation set:
 - epoch: 4.0
 - step: 3236
 
-## Model description
+# Running the model using transformers library
+
+1. Load the pre-trained model from the model hub
+    ```python
+    from transformers import VisionEncoderDecoderModel, ViTFeatureExtractor, AutoTokenizer
+    import torch
+    from PIL import Image
+    
+    model_name = "bipin/image-caption-generator"
+
+    # load model
+    model = VisionEncoderDecoderModel.from_pretrained(model_name)
+    feature_extractor = ViTFeatureExtractor.from_pretrained(model_name)
+    tokenizer = AutoTokenizer.from_pretrained("gpt2")
+
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    model.to(device)
+    ```
 
-More information needed
+2. Load the image for which the caption is to be generated
+    ```python
+    img_name = "flickr_data.jpg"
+    img = Image.open(img_name)
+    if img.mode != 'RGB':
+        img = img.convert(mode="RGB")
+    ```
 
-## Intended uses & limitations
+3. Pre-process the image
+    ```python
+    pixel_values = feature_extractor(images=[img], return_tensors="pt").pixel_values
+    pixel_values = pixel_values.to(device)
+    ```
 
-More information needed
+4. Generate the caption
+     ```python
+      max_length = 128
+      num_beams = 4
 
-## Training and evaluation data
+      # get model prediction
+      output_ids = model.generate(pixel_values, num_beams=num_beams, max_length=max_length)
 
-More information needed
+      # decode the generated prediction
+      preds = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+      print(preds)
+     ```
 
 ## Training procedure
+The procedure used to train this model can be found [here](https://bipinkrishnan.github.io/ml-recipe-book/image_captioning.html).
 
 ### Training hyperparameters