Update app.py

app.py

@@ -116,13 +116,13 @@ pipe.to(device=DEVICE)
 #pipe.vae = torch.compile(pipe.vae)
 
 
-im_embs = torch.zeros(1, 1, 1, 1280, device=DEVICE, dtype=dtype)
-output = pipe(prompt='a person', guidance_scale=0, added_cond_kwargs={}, ip_adapter_image_embeds=[im_embs], num_inference_steps=STEPS)
-leave_im_emb, _ = pipe.encode_image(
- output.frames[0][len(output.frames[0])//2], DEVICE, 1, output_hidden_state
-)
-assert len(output.frames[0]) == 16
-leave_im_emb.detach().to('cpu')
+#im_embs = torch.zeros(1, 1, 1, 1280, device=DEVICE, dtype=dtype)
+#output = pipe(prompt='a person', guidance_scale=0, added_cond_kwargs={}, ip_adapter_image_embeds=[im_embs], num_inference_steps=STEPS)
+#leave_im_emb, _ = pipe.encode_image(
+# output.frames[0][len(output.frames[0])//2], DEVICE, 1, output_hidden_state
+#)
+#assert len(output.frames[0]) == 16
+#leave_im_emb.detach().to('cpu')
 
 
 @spaces.GPU()
@@ -191,10 +191,10 @@ def get_user_emb(embs, ys):
  print('ys are longer than embs; popping latest rating')
  ys.pop(-1)
  
- feature_embs = np.array(torch.stack([embs[i].squeeze().to('cpu') for i in indices] + [leave_im_emb.to('cpu').squeeze()]).to('cpu'))
+ feature_embs = np.array(torch.stack([embs[i].squeeze().to('cpu') for i in indices]]).to('cpu'))
  #scaler = preprocessing.StandardScaler().fit(feature_embs)
  #feature_embs = scaler.transform(feature_embs)
- chosen_y = np.array([ys[i] for i in indices] + [0])
+ chosen_y = np.array([ys[i] for i in indices])
  
  print('Gathering coefficients')
  #lin_class = Ridge(fit_intercept=False).fit(feature_embs, chosen_y)