Remove pykeops for space ZeroGPU demo.

app.py

@@ -87,14 +87,14 @@ DEFAULT_SETTINGS = {
 FLOAT_SLIDERS = {
     # name: (min, max, step)
     "deepfeat_conf.fmap.lambda_": (1e-3, 10.0, 1e-3),
-    "sds_conf.zoomout": (1e-3, 10.0, 1e-3),
-    "diffusion.time": (1e-3, 10.0, 1e-3),
+    "diffusion.time": (0.1, 10.0, 0.1),
     "loss.sds": (1e-3, 10.0, 1e-3),
     "loss.proper": (1e-3, 10.0, 1e-3),
 }
 
 INT_SLIDERS = {
     "opt.n_loop": (1, 5000, 1),
+    "sds_conf.zoomout": (31, 50, 1),
 }
 
 
@@ -223,7 +223,7 @@ with gr.Blocks(title="DiffuMatch demo") as demo:
     with gr.Accordion("Settings", open=True):
         with gr.Row():
             lambda_val = gr.Slider(minimum=FLOAT_SLIDERS["deepfeat_conf.fmap.lambda_"][0], maximum=FLOAT_SLIDERS["deepfeat_conf.fmap.lambda_"][1], step=FLOAT_SLIDERS["deepfeat_conf.fmap.lambda_"][2], value=1, label="deepfeat_conf.fmap.lambda_")
-            zoomout_val = gr.Slider(minimum=FLOAT_SLIDERS["sds_conf.zoomout"][0], maximum=FLOAT_SLIDERS["sds_conf.zoomout"][1], step=FLOAT_SLIDERS["sds_conf.zoomout"][2], value=40, label="sds_conf.zoomout")
+            zoomout_val = gr.Slider(minimum=INT_SLIDERS["sds_conf.zoomout"][0], maximum=INT_SLIDERS["sds_conf.zoomout"][1], step=INT_SLIDERS["sds_conf.zoomout"][2], value=40, label="sds_conf.zoomout")
             time_val = gr.Slider(minimum=FLOAT_SLIDERS["diffusion.time"][0], maximum=FLOAT_SLIDERS["diffusion.time"][1], step=FLOAT_SLIDERS["diffusion.time"][2], value=1, label="diffusion.time")
         with gr.Row():
             nloop_val = gr.Slider(minimum=INT_SLIDERS["opt.n_loop"][0], maximum=INT_SLIDERS["opt.n_loop"][1], step=INT_SLIDERS["opt.n_loop"][2], value=300, label="opt.n_loop")

utils/mesh.py

@@ -31,7 +31,7 @@ def list_files(folder_path, name_filter, alphanum_sort=False):
     else:
         return sorted(file_list)
 
-def find_mesh_files(directory: Path, extensions: set=MESH_EXTENSIONS, alphanum_sort=False) -> list[Path]:
+def find_mesh_files(directory, extensions, alphanum_sort=False): # Path, extensions: set=MESH_EXTENSIONS, alphanum_sort=False) -> list[Path]:
     """
     Recursively find all files in 'directory' whose suffix (lowercased) is in 'extensions'.
     Returns a list of Path objects.

utils/torch_fmap.py

@@ -1,6 +1,5 @@
 import torch
 import torch.nn.functional as F
-from pykeops.torch import LazyTensor
 
 
 def euclidean_dist(x, y):
@@ -33,14 +32,14 @@ def extract_p2p_torch(reps_shape, reps_template):
         # print((evecs0_dzo @ fmap01_final.squeeze().T).shape)
         # print(evecs1_dzo.shape)
         reps_shape_torch = torch.from_numpy(reps_shape).float().cuda()
-        G_i = LazyTensor(reps_shape_torch[:, None, :].contiguous())  # (M**2, 1, 2)
+        G_i = (reps_shape_torch[:, None, :].contiguous())  # (M**2, 1, 2)
         reps_template_torch = torch.from_numpy(reps_template).float().cuda()
-        X_j = LazyTensor(reps_template_torch[None, :, :n_ev].contiguous())  # (1, N, 2)
+        X_j = (reps_template_torch[None, :, :n_ev].contiguous())  # (1, N, 2)
         D_ij = ((G_i - X_j) ** 2).sum(-1)  # (M**2, N) symbolic matrix of squared distances
-        indKNN = D_ij.argKmin(1, dim=0).squeeze()  # Grid <-> Samples, (M**2, K) integer tensor
+        indKNN = torch.argmin(D_ij, dim=0).squeeze()  # Grid <-> Samples, (M**2, K) integer tensor
         # pmap10_ref = FM_to_p2p(fmap01_final.detach().squeeze().cpu().numpy(), s_dict['evecs'], template_dict['evecs'])
         # print(indKNN[:10], pmap10_ref[:10])
-        indKNN_2 = D_ij.argKmin(1, dim=1).squeeze()
+        indKNN_2 = torch.argmin(D_ij, dim=1).squeeze()
     return indKNN.detach().cpu().numpy(), indKNN_2.detach().cpu().numpy()
 
 def extract_p2p_torch_fmap(fmap_shape_template, evecs_shape, evecs_template):
@@ -48,13 +47,13 @@ def extract_p2p_torch_fmap(fmap_shape_template, evecs_shape, evecs_template):
     with torch.no_grad():
         # print((evecs0_dzo @ fmap01_final.squeeze().T).shape)
         # print(evecs1_dzo.shape)
-        G_i = LazyTensor((evecs_shape[:, :n_ev] @ fmap_shape_template.squeeze().T)[:, None, :].contiguous())  # (M**2, 1, 2)
-        X_j = LazyTensor(evecs_template[None, :, :n_ev].contiguous())  # (1, N, 2)
+        G_i = ((evecs_shape[:, :n_ev] @ fmap_shape_template.squeeze().T)[:, None, :].contiguous())  # (M**2, 1, 2)
+        X_j = (evecs_template[None, :, :n_ev].contiguous())  # (1, N, 2)
         D_ij = ((G_i - X_j) ** 2).sum(-1)  # (M**2, N) symbolic matrix of squared distances
-        indKNN = D_ij.argKmin(1, dim=0).squeeze()  # Grid <-> Samples, (M**2, K) integer tensor
+        indKNN = torch.argmin(D_ij, dim=0).squeeze()  # Grid <-> Samples, (M**2, K) integer tensor
         # pmap10_ref = FM_to_p2p(fmap01_final.detach().squeeze().cpu().numpy(), s_dict['evecs'], template_dict['evecs'])
         # print(indKNN[:10], pmap10_ref[:10])
-        indKNN_2 = D_ij.argKmin(1, dim=1).squeeze()
+        indKNN_2 = torch.argmin(D_ij, dim=1).squeeze()
     return indKNN.detach().cpu().numpy(), indKNN_2.detach().cpu().numpy()
 
 def wlstsq(A, B, w):