image blob

app.py

@@ -23,18 +23,26 @@ class App:
         return model
 
     @torch.inference_mode()
-    def __call__(self, model_name, image):
-        if image is None:
+    def __call__(self, model_name, image_blob):
+        if image_blob is None:
             return '', []
+        
+        # Decode base64 image blob and convert to PIL Image
+        image_data = base64.b64decode(image_blob)
+        image = Image.open(BytesIO(image_data)).convert('RGB')
+        
         model = self._get_model(model_name)
-        image = self._preprocess(image.convert('RGB')).unsqueeze(0)
+        image = self._preprocess(image).unsqueeze(0)
+        
         # Greedy decoding
         pred = model(image).softmax(-1)
         label, _ = model.tokenizer.decode(pred)
         raw_label, raw_confidence = model.tokenizer.decode(pred, raw=True)
+        
         # Format confidence values
         max_len = 25 if model_name == 'crnn' else len(label[0]) + 1
         conf = list(map('{:0.1f}'.format, raw_confidence[0][:max_len].tolist()))
+        
         return label[0], [raw_label[0][:max_len], conf]