Update app.py

app.py

@@ -12,13 +12,15 @@ def main():
     st.write("Drag and drop an image file here.")
 
     # Allow the user to upload an image file
-    uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
+    image = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
 
     if uploaded_file is not None:
         # Display the uploaded image
         image = Image.open(uploaded_file)
         st.image(image, caption="Uploaded Image", use_column_width=True)
 
+        question = st.text_input("What's your question?")
+
 # Model 1.
 # Model 1 gets input from the user.
 # User -> Model 1
@@ -62,3 +64,98 @@ gpt2_pipeline = pipeline(task="text-generation", model="gpt2")
 topic_model_1 = BERTopic.load(path="davanstrien/chat_topics")
 topic_model_2 = BERTopic.load(path="MaartenGr/BERTopic_ArXiv")
 
+ ###############################################################################
+
+# 5 MODEL INFERENCES.
+# User Input = Image + Question About The Image.
+# User -> Model 1 -> Model 2 -> Model 3 -> Model 4 -> Model 5
+
+# Model 1.
+
+vqa_pipeline_output = vqa_pipeline(image, question, top_k=5)[0]
+
+# Model 2.
+
+text = (
+    "I love "
+    + str(vqa_pipeline_output["answer"])
+    + " and I would like to know how to [MASK]."
+)
+bbu_pipeline_output = bbu_pipeline(text)
+
+# Model 3.
+
+utterance = bbu_pipeline_output[0]["sequence"]
+inputs = tokenizer(utterance, return_tensors="pt")
+result = facebook_model.generate(**inputs)
+facebook_model_output = tokenizer.decode(result[0])
+
+# Model 4.
+
+facebook_model_output = facebook_model_output.replace("<s> ", "")
+facebook_model_output = facebook_model_output.replace("<s>", "")
+facebook_model_output = facebook_model_output.replace("</s>", "")
+gpt2_pipeline_output = gpt2_pipeline(facebook_model_output)[0]["generated_text"]
+
+# Model 5.
+
+topic, prob = topic_model_1.transform(gpt2_pipeline_output)
+topic_model_1_output = topic_model_1.get_topic_info(topic[0])["Representation"][
+    0
+]
+
+topic, prob = topic_model_2.transform(gpt2_pipeline_output)
+topic_model_2_output = topic_model_2.get_topic_info(topic[0])["Representation"][
+    0
+]
+###############################################################################
+
+print()
+
+print("-" * 150)
+print("vqa_pipeline_output = ", vqa_pipeline_output)
+print("bbu_pipeline_output =", bbu_pipeline_output)
+print("facebook_model_output =", facebook_model_output)
+print("gpt2_pipeline_output =", gpt2_pipeline_output)
+print("topic_model_1_output =", topic_model_1_output)
+print("topic_model_2_output =", topic_model_2_output)
+
+print()
+
+print("-" * 150)
+print("SUMMARY")
+print("-" * 7)
+print("Your Image:", image)
+print("Your Question:", question)
+print("-" * 100)
+print(
+    "1. Highest Predicted Answer For Your Question:",
+    vqa_pipeline_output["answer"],
+    "\n",
+        )
+        print(text)
+        print(
+            "2. Highest Predicted Sequence On [MASK] Based on 1.:",
+            bbu_pipeline_output[0]["sequence"],
+            "\n",
+        )
+        print(
+            "3. Conversation Based On Previous Answer Based on 2.:",
+            facebook_model_output,
+            "\n",
+        )
+        print(
+            "4. Text Generated Based On Previous Answer Based on 3.:",
+            gpt2_pipeline_output,
+            "\n",
+        )
+        print(
+            "5. Highest Predicted Topic Model_1 For Previous The Answer Based on 4.:",
+            topic_model_1_output,
+            "\n",
+        )
+        print(
+            "6. Highest Predicted Topic Model_2 For Previous The Answer Based on 4.:",
+            topic_model_2_output,
+        )
+        print("-" * 150)