Update app.py

app.py

@@ -65,17 +65,17 @@ trans_model = MarianMTModel.from_pretrained(model_name)
 def caption_random_image():
 
     # AA: pick random row - from DF
-    sample = df.sample(1).iloc[0]
+    ##sample = df.sample(1).iloc[0]
 
     # BB: Pick a random image path - image from folder
-    ##img_path = random.choice(image_paths)
+    img_path = random.choice(image_paths)
 
     # BB: Load into PIL - image from folder - image from folder
-    ##image = Image.open(img_path).convert("RGB")
+    image = Image.open(img_path).convert("RGB")
 
 
     # AA: Image - for DF
-    image = sample["image"]
+    ##image = sample["image"]
 
     # Unconditional image captioning
     inputs = processor(image, return_tensors="pt")
@@ -84,9 +84,9 @@ def caption_random_image():
     caption_eng = processor.decode(out[0], skip_special_tokens=True)
 
     # Translate caption from English to Spanish
-    ##trans_inputs = trans_tokenizer.encode(caption_eng, return_tensors="pt")
-    ##trans_out = trans_model.generate(trans_inputs)
-    ##caption_es = trans_tokenizer.decode(trans_out[0], skip_special_tokens=True)
+    trans_inputs = trans_tokenizer.encode(caption_eng, return_tensors="pt")
+    trans_out = trans_model.generate(trans_inputs)
+    caption_es = trans_tokenizer.decode(trans_out[0], skip_special_tokens=True)
 
     return image, caption_eng, caption_es
 
@@ -96,8 +96,8 @@ demo = gr.Interface(
     inputs=None,
     outputs=[
         gr.Image(type="pil", label="Random Image"),
-        gr.Textbox(label="Caption (English)")
-        ##gr.Textbox(label="Caption (Spanish)")
+        gr.Textbox(label="Caption (English)"),
+        gr.Textbox(label="Caption (Spanish)")
     ],
     title="Image Captioning (with English to Spanish translation)",
     description="Selects a random image (from either the local folder or henryscheible/coco data subset); generates a BLIP caption; then translates the (English) caption to Spanish."