Update app.py

app.py

@@ -6,23 +6,32 @@ import skimage.io as io
 import PIL.Image
 import difflib
 import ViTCoAtt
+import cnn-rnn
 from build_vocab import Vocabulary
 
 
+    
 
 # Caption generation functions
 def generate_caption_clipgpt(image, max_tokens, temperature):
-  caption = clipGPT.generate_caption_clipgpt(image, max_tokens, temperature)
-  return caption
+    caption = clipGPT.generate_caption_clipgpt(image, max_tokens, temperature)
+    return caption
 
 def generate_caption_vitgpt(image, max_tokens, temperature):
-  caption = vitGPT.generate_caption(image, max_tokens, temperature)
-  return caption
+    caption = vitGPT.generate_caption(image, max_tokens, temperature)
+    return caption
 
 def generate_caption_vitCoAtt(image):
-  caption = ViTCoAtt.CaptionSampler.main(image)
-  return caption
+    caption = ViTCoAtt.CaptionSampler.main(image)
+    return caption
 
+def generate_caption_cnnrnn(image):
+    # with open('/content/Image_features_ecoder_decoder.pickle', 'rb') as f:
+        # Xnet_features = pickle.load(f)
+        # image = Xnet_features[image]
+        # caption = cnn-rnn.get_result(image)
+        caption = ""
+        return caption
 
 
 with gr.Row():
@@ -49,6 +58,9 @@ def predict(img, model_name, max_tokens, temperature):
       return generate_caption_vitgpt(img, max_tokens, temperature)
     elif model_name == "ViT-CoAttention":
       return generate_caption_vitCoAtt(img)
+    elif model_name == "Baseline Model CNN-RNN":
+        print(img)
+      return generate_caption_cnnrnn(img)
     else:
       return "Caption generation for this model is not yet implemented."