Update README.md

README.md

@@ -6,30 +6,48 @@ tags:
 datasets:
 - imagefolder
 model-index:
-- name: paligemma_Malaysian_plate_recognition2
+- name: paligemma_Malaysian_plate_recognition
   results: []
 ---
 
 <!-- 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. -->
 
-# paligemma_Malaysian_plate_recognition2
+# paligemma_Malaysian_plate_recognition
 
-This model is a fine-tuned version of [google/paligemma-3b-pt-224](https://huggingface.co/google/paligemma-3b-pt-224) on the imagefolder dataset.
+This model is a fine-tuned version of [google/paligemma-3b-pt-224](https://huggingface.co/google/paligemma-3b-pt-224) on the Malaysian license plate dataset.
 
-## Model description
 
-More information needed
 
-## Intended uses & limitations
+``` python
 
-More information needed
+from PIL import Image
+import torch
+from transformers import PaliGemmaProcessor, PaliGemmaForConditionalGeneration, BitsAndBytesConfig, TrainingArguments, Trainer
+import time
 
-## Training and evaluation data
+model = PaliGemmaForConditionalGeneration.from_pretrained('NYUAD-ComNets/paligemma_Malaysian_plate_recognition',torch_dtype=torch.bfloat16)
 
-More information needed
+input_text ="extract the text from the image"
+
+processor = PaliGemmaProcessor.from_pretrained("google/paligemma-3b-pt-224")
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+model.to(device)
+
+input_image = Image.open('/home/jovyan/work/image/'+k)
+        
+inputs = processor(text=input_text, images=input_image, padding="longest", do_convert_rgb=True, return_tensors="pt").to(device)
+inputs = inputs.to(dtype=model.dtype)
+
+with torch.no_grad():
+     output = model.generate(**inputs, max_length=500)
+
+result=processor.decode(output[0], skip_special_tokens=True)[len(input_text):].strip()
+
+```
 
-## Training procedure
 
 ### Training hyperparameters
 
@@ -45,9 +63,6 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_steps: 2
 - num_epochs: 5
 
-### Training results
-
-
 
 ### Framework versions