Update app.py

app.py

@@ -80,13 +80,15 @@ def generate_motion(text, vqvae_model, transformer_model):
         with torch.no_grad():
             clip_features = clip_model.encode_text(text_encoded).float()
         
-        motion_indices = transformer_model.sample(clip_features, False)  # Ensure the input to the transformer is float
+        motion_indices = transformer_model.sample(clip_features, False)
         pred_pose = vqvae_model.forward_decoder(motion_indices)
         pred_xyz = recover_from_ric((pred_pose * std + mean).float(), 22)
     
     return pred_xyz.cpu().numpy().reshape(-1, 22, 3)
 
 def create_animation(joints, title="3D Motion", save_path="static/animation.gif"):
+    os.makedirs(os.path.dirname(save_path), exist_ok=True)
+
     fig = plt.figure(figsize=(10, 10))
     ax = fig.add_subplot(111, projection='3d')
     data = np.array(joints).T
@@ -101,7 +103,7 @@ def create_animation(joints, title="3D Motion", save_path="static/animation.gif"
     ani.save(save_path, writer=PillowWriter(fps=20))
     plt.close(fig)
     return save_path
-
+    
 def infer(text):
     motion_data = generate_motion(text, vqvae_model, transformer_model)
     gif_path = create_animation(motion_data)
@@ -109,9 +111,9 @@ def infer(text):
 
 with gr.Blocks(css=".container { max-width: 800px; margin: auto; }") as demo:
     with gr.Column():
-        gr.Markdown("## 3D Motion Generation on " + ("GPU" if device == "cuda" else "CPU"))
+        gr.Markdown("## 3D Human Motion Generation on " + ("GPU" if device == "cuda" else "CPU"))
         text_input = gr.Textbox(label="Describe the action", placeholder="Enter text description for the action here...")
-        output_image = gr.Image(label="Generated Motion Animation")
+        output_image = gr.Image(label="Generated Human Motion")
         submit_button = gr.Button("Generate Motion")
         
         submit_button.click(