update

app.py

@@ -44,7 +44,7 @@ def image_text_zeroshot(image, text_list):
 def main():
     inputs = [
         gr.inputs.Textbox(lines=1, label="texts"),
-        gr.inputs.Image(type="filepath", label="Input image")
+        gr.inputs.Image(type="filepath", label="Output image")
     ]
 
     iface = gr.Interface(

requirements.txt

@@ -3,6 +3,8 @@ torchvision==0.14.0
 torchaudio==0.13.0
 pytorchvideo @ git+https://github.com/facebookresearch/pytorchvideo.git@28fe037d212663c6a24f373b94cc5d478c8c1a1d
 timm==0.6.7
+proj
+geos
 ftfy
 regex
 einops