Update app.py

app.py

@@ -17,22 +17,22 @@ model = imagebind_model.imagebind_huge(pretrained=True)
 model.eval()
 model.to(device)
 
-def image_text_zeroshot(texts):
-    labels = [texts]
-    inputs = {
-        ModalityType.TEXT: data.load_and_transform_text(labels, device)
-    }
-
-    with torch.no_grad():
-        embeddings = model(inputs)
-
-    # scores = (
-    #     torch.softmax(
-    #         embeddings[ModalityType.VISION] @ embeddings[ModalityType.TEXT].T, dim=-1
-    #     )
-    #     .squeeze(0)
-    #     .tolist()
-    # )
+def image_text_zeroshot(text):
+    # labels = [text]
+    # inputs = {
+    #     ModalityType.TEXT: data.load_and_transform_text(labels, device)
+    # }
+
+    # with torch.no_grad():
+    #     embeddings = model(inputs)
+
+    # # scores = (
+    # #     torch.softmax(
+    # #         embeddings[ModalityType.VISION] @ embeddings[ModalityType.TEXT].T, dim=-1
+    # #     )
+    # #     .squeeze(0)
+    # #     .tolist()
+    # # )
 
     score_dict = "./assets/ICA-Logo.png" #{label: score for label, score in zip(labels, scores)}
 
@@ -42,11 +42,14 @@ def image_text_zeroshot(texts):
 def main():
 
     iface = gr.Interface(
-        fn= image_text_zeroshot(texts),
-        inputs = gr.inputs.Textbox(lines=1, label="texts"),
-        outputs = gr.inputs.Image(type="filepath", label="Output image"),
-        description="""...""",
-        title="ImageBind",
+        fn=image_text_zeroshot,
+        inputs="text",
+        outputs="file",
+        live=True,
+        capture_session=True,
+        title="Texto para Imagem",
+        description="Digite um texto e obtenha uma imagem com o texto.",
+        allow_flagging=False,
     )
 
     iface.launch()