Update app.py

app.py

@@ -55,9 +55,13 @@ device='cpu'
 encoder_checkpoint = "nlpconnect/vit-gpt2-image-captioning"
 decoder_checkpoint = "nlpconnect/vit-gpt2-image-captioning"
 model_checkpoint = "nlpconnect/vit-gpt2-image-captioning"
+print("------------------------- 1 -------------------------\n")
 feature_extractor = ViTFeatureExtractor.from_pretrained(encoder_checkpoint)
-tokenizer = AutoTokenizer.from_pretrained(decoder_checkpoint)
+print("------------------------- 2 -------------------------\n")
+tokenizer = AutoTokenizer.from_pretrained(decoder_checkpoint
+print("------------------------- 3 -------------------------\n")
 model = VisionEncoderDecoderModel.from_pretrained(model_checkpoint).to(device)
+print("------------------------- 4 -------------------------\n")
 
 
 def predict(image,max_length=64, num_beams=4):
@@ -69,13 +73,13 @@ def predict(image,max_length=64, num_beams=4):
   return caption_text 
 
 
-
+print("------------------------- 5 -------------------------\n")
 input = gr.inputs.Image(label="Upload any Image", type = 'pil', optional=True)
 output = gr.outputs.Textbox(type="auto",label="Captions")
 examples = [f"example{i}.jpg" for i in range(1,7)]
-
+print("------------------------- 6 -------------------------\n")
 title = "Image Captioning "
-description = "Made by : shreyasdixit.tech"
+description = "NTT Data"
 interface = gr.Interface(
             
         fn=predict,