Update app.py

app.py

@@ -12,46 +12,52 @@ from imagebind.models.imagebind_model import ModalityType
 import torch.nn as nn
 
 
-device = "cuda:0" if torch.cuda.is_available() else "cpu"
+device = "cpu" #"cuda:0" if torch.cuda.is_available() else "cpu"
 model = imagebind_model.imagebind_huge(pretrained=True)
 model.eval()
 model.to(device)
 
-def image_text_zeroshot(image, text_list):
-    image_paths = [image]
-    labels = [label.strip(" ") for label in text_list.strip(" ").split("|")]
-    inputs = {
-        ModalityType.TEXT: data.load_and_transform_text(labels, device),
-        ModalityType.VISION: data.load_and_transform_vision_data(image_paths, 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 = {label: score for label, score in zip(labels, scores)}
-
-    return score_dict
-
-def main():
-    inputs = [
-        gr.inputs.Textbox(lines=1, label="texts"),
-        gr.inputs.Image(type="filepath", label="Output image")
-    ]
-
-    iface = gr.Interface(
-        image_text_zeroshot(image, text_list),
-        inputs,
-        "label",
-        description="""...""",
-        title="ImageBind",
-    )
-
-    iface.launch()
+# def image_text_zeroshot(image, text_list):
+#     image_paths = [image]
+#     labels = [label.strip(" ") for label in text_list.strip(" ").split("|")]
+#     inputs = {
+#         ModalityType.TEXT: data.load_and_transform_text(labels, device),
+#         ModalityType.VISION: data.load_and_transform_vision_data(image_paths, 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 = {label: score for label, score in zip(labels, scores)}
+
+#     return score_dict
+
+# def main():
+#     inputs = [
+#         gr.inputs.Textbox(lines=1, label="texts"),
+#         gr.inputs.Image(type="filepath", label="Output image")
+#     ]
+
+#     iface = gr.Interface(
+#         image_text_zeroshot(image, text_list),
+#         inputs,
+#         "label",
+#         description="""...""",
+#         title="ImageBind",
+#     )
+
+#     iface.launch()
+
+def image_classifier(inp):
+    return {'cat': 0.3, 'dog': 0.7}
+
+demo = gr.Interface(fn=image_classifier, inputs="image", outputs="label")
+demo.launch()