save progress

data/cloth3d_io.py

@@ -223,9 +223,12 @@ def _todict(matobj):
 
 
 # can i cache map?
-def read_posed_garment_frame(folder, id, garment, frame, map, mask=None, shape=None, shapedirs=None, pose=None, unshape=False, deorient=False):
+def read_posed_garment_frame(folder, id, garment, frame, map=None, mask=None, shape=None, shapedirs=None, pose=None, unshape=False, deorient=False):
     pc16_path = os.path.join(folder, id, garment + '.pc16')
     verts = readPC2Frame(pc16_path, frame, True)
+
+    if map is None:
+        map = sio.loadmat(os.path.join(folder, id, garment + '_map.mat'))['map'].reshape((-1))
     verts = verts[map, :]
 
     if unshape:

data/curvatures.py

@@ -5,6 +5,7 @@ import argparse
 import random
 import string
 import time
+import networkx as nx
 import tables as tb
 import numpy as np
 import trimesh as tm
@@ -18,22 +19,18 @@ from scipy.sparse.csgraph import floyd_warshall, dijkstra
 
 sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/..')
 
-from data.cloth3d_io import readPC2, readPC2Frame, writePC2, readOBJ
+from data.cloth3d_io import readPC2, readPC2Frame, writePC2, readOBJ, read_garment_mask, read_posed_garment_frame
 from custom_utils.custom_utils import _maskFaces
 # from FeatureLines.superSMPL.smpl import SMPL
 
+
 def get_body():
-    smpl = SMPL('FeatureLines/superSMPL')
-    pose = np.zeros((1, 72), dtype=np.float32)
-    beta = np.zeros((1, 11), dtype=np.float32)
-    R = smpl.run_rodrigues(pose)
-    T, _, _ = smpl.run(R, beta, True)
-    return np.squeeze(T)
+    body = readOBJ('custom_data/superSMPL.obj')
+    return body[0]
 
 
 def get_skirt_body():
-    body = readOBJ('FeatureLines/superSMPL_skirt.obj')
-
+    body = readOBJ('custom_data/superSMPL_skirt.obj')
     return body[0]
 
 
@@ -44,8 +41,6 @@ def export_to_ply(mesh, file):
     output_file.close()
 
 
-
-
 def get_closest_n_points(verts, idx, n):
     dist = sp.spatial.distance.cdist(verts[idx, :], verts)
     dist[dist == 0] = 1e9
@@ -61,9 +56,11 @@ def histedges_equalN(x, nbin):
                      np.sort(x))
 
 
-
 def k_neighbours(k):
-    body = get_skirt_body()
+    if is_skirt:
+        body = get_skirt_body()
+    else:
+        body = get_body()
     adj = np.ones((14475, 14475)) * 9999 # ???
     diagonal = np.linspace(0, 14474, 14475, dtype=np.int32)
     m = tm.Trimesh(body, F, process=False, validate=False)
@@ -73,10 +70,13 @@ def k_neighbours(k):
     adj[edges[:, 1], edges[:, 0]] = lengths
     adj[diagonal, diagonal] = 0
 
-    adj = csr_matrix(adj)
-    dist = dijkstra(adj, directed=False, unweighted=False, limit=0.5)
+    # G = nx.convert_matrix.from_numpy_array(adj)
 
-    np.save('MeshUtils/dijkstra_skirt.npy', dist)
+    adj = csr_matrix(adj)
+    dist = dijkstra(adj, directed=False, unweighted=False, limit=0.1)
+
+    skirt_modifier = '_skirt' if is_skirt else ''
+    np.save('custom_data/dijkstra' + skirt_modifier + '.npy', dist)
 
     # dist = floydWarshall(adj, 14475)
 
@@ -86,20 +86,68 @@ def k_neighbours(k):
     pass
 
 
+class Data:
+    def __init__(self):
+        self.dist = None
+        self.mask = None
+        self.faces = None
+
+
+class Cache:
+    def __init__(self, folder, neighbourhood, frames):
+        self.cache = dict()
+
+        for frame in tqdm.tqdm(frames):
+            id = frame.split()[0]
+            frame_nr = int(frame.split()[1])
+            garment = frame.split()[2]
+            if id in self.cache.keys():
+                continue
+
+            self.cache[id] = Data()
+
+            mask = read_garment_mask(folder, id, garment)  #np.load(os.path.join(folder, 'mesh_mask', f'{id}.npy')).astype(bool)
+            k_neighbors = np.argsort(dist[mask, :][:, mask], axis=-1)[:, :neighbourhood] #cloud.get_neighbors(k=neighbourhood)
+
+            _, faces = _maskFaces(np.zeros((14475,3)), F, mask) #np.load(os.path.join(folder, 'faces', f'{id}.npy'))
+            v = read_posed_garment_frame(folder, id, garment, frame_nr)[mask,:]
+            m = tm.Trimesh(v, faces, process=False, validate=False)
+            outliers = np.array([len(v) for v in m.vertex_neighbors]) == 0
+            outliers = np.nonzero(outliers)[0]
+            outliers_n_neighbours = get_closest_n_points(v, outliers, 2)
+            outliers_faces = np.concatenate((outliers[:, np.newaxis], outliers_n_neighbours), axis=-1)
+            faces = np.concatenate((faces, outliers_faces), axis=0)
+
+            G = tm.graph.vertex_adjacency_graph(m)
+            for i in range(v.shape[0]):
+                for k in range(25):
+                    assert nx.has_path(G, i, k_neighbors[i, k]), f'No path between {i} and {k_neighbors[i, k]}'
+
+            self.cache[id].k_neighbors = k_neighbors
+            self.cache[id].mask = mask
+            self.cache[id].faces = faces
+
+    def __getitem__(self, id):
+        return self.cache[id]
+
+
+
 def calculate_dist(folder, neighbourhood, frames):
-    out = dict()
+    dist = dict()
     # frames = frames[int(args.start):int(args.end)]
 
     for frame in tqdm.tqdm(frames):
-        id = frame.split('_')[0]
-        if id in out.keys():
+        id = frame.split()[0]
+        garment = frame.split()[2]
+        if id in dist.keys():
             continue
 
-        mask = np.load(os.path.join(folder, 'mesh_mask', f'{id}.npy')).astype(bool)
+        mask = read_garment_mask(folder, id, garment)  #np.load(os.path.join(folder, 'mesh_mask', f'{id}.npy')).astype(bool)
         k_neighbors = np.argsort(dist[mask, :][:, mask], axis=-1)[:, :neighbourhood] #cloud.get_neighbors(k=neighbourhood)
-        out[id] = k_neighbors
+        dist[id] = k_neighbors
+
+    return dist
 
-    return out
 
 def generate_curvatures(folder, neighbourhood, frames):
 
@@ -107,36 +155,26 @@ def generate_curvatures(folder, neighbourhood, frames):
     # frames = frames[int(args.start):int(args.end)]
     # os.makedirs(os.path.join(folder, f'mesh_curvature_raw_{neighbourhood}'), exist_ok=True)
 
-    k_neighbors_cache = calculate_dist(folder, neighbourhood, frames)
+    cache = Cache(folder, neighbourhood, frames)
 
     for frame in tqdm.tqdm(frames):
 
-        id = frame.split('_')[0]
-        frame_nr = frame.split('_')[1]
-        garment = frame.split('_')[2]
+        id = frame.split()[0]
+        frame_nr = int(frame.split()[1])
+        garment = frame.split()[2]
     
         # bodies = readPC2(os.path.join(folder, id, 'Body_posed.pc16'), True)['V']
         # offsetss = readPC2(os.path.join(folder, id, garment + '_registered.pc16'), True)['V']
-        mask = np.load(os.path.join(folder, 'mesh_mask', f'{id}.npy')).astype(bool)
-        _, faces = _maskFaces(np.zeros((14475,3)), F, mask) #np.load(os.path.join(folder, 'faces', f'{id}.npy'))
-        v = np.load(os.path.join(folder, 'mesh_posed', f'{id}_{frame_nr}.npz'))['mesh_posed'][mask,:]
+        # mask = np.load(os.path.join(folder, 'mesh_mask', f'{id}.npy')).astype(bool)
+        mask = cache[id].mask
+        faces = cache[id].faces
+        v = read_posed_garment_frame(folder, id, garment, frame_nr)[mask,:]
         
         m = tm.Trimesh(v, faces, process=False, validate=False)
-
-        outliers = np.array([len(v) for v in m.vertex_neighbors]) == 0
-        outliers = np.nonzero(outliers)[0]
-        outliers_n_neighbours = get_closest_n_points(v, outliers, 2)
-        outliers_faces = np.concatenate((outliers[:, np.newaxis], outliers_n_neighbours), axis=-1)
-        faces = np.concatenate((faces, outliers_faces), axis=0)
-
-        verts = v
-
-        m = tm.Trimesh(verts, faces, process=False, validate=False)
         export_to_ply(m, temp_file)
-
         cloud = PyntCloud.from_file(temp_file)
 
-        k_neighbors = k_neighbors_cache[id] # np.argsort(dist[mask, :][:, mask], axis=-1)[:, :neighbourhood] #cloud.get_neighbors(k=neighbourhood)
+        k_neighbors = cache[id].k_neighbors
         ev = cloud.add_scalar_field("eigen_values", k_neighbors=k_neighbors)
         cloud.add_scalar_field("curvature", ev=ev)
         curvature = np.array(cloud.points["curvature(" + str(neighbourhood+1) + ")"])
@@ -145,7 +183,11 @@ def generate_curvatures(folder, neighbourhood, frames):
         
         # np.savez_compressed(os.path.join(folder, f'mesh_curvature_raw_{neighbourhood}', f'{id}_{frame_nr}.npz'), mesh_curvature_raw=out)
         group = h5file.get_node(f'/{id}/{frame_nr}/{garment}')
-        h5file.create_array(group, "curvature_raw", out)
+        if f'curvature_raw' in group:
+            array = h5file.get_node(f'/{id}/{frame_nr}/{garment}/curvature_raw')
+            array[:] = out
+        else:
+            h5file.create_array(group, "curvature_raw", out)
 
     return None
 
@@ -259,7 +301,7 @@ if __name__ == '__main__':
     parser = argparse.ArgumentParser()
     parser.add_argument("-f", "--folder", help = "process the given folder", default=r'/home/workspace/data/dataset/cloth3d/train')
     parser.add_argument("-s", "--start", help = "start of range", default=0)
-    parser.add_argument("-e", "--end", help = "end of range", default=10)
+    parser.add_argument("-e", "--end", help = "end of range", default=1000)
     parser.add_argument("-n", "--name", help = "end of range", default="lhunor")
     args = parser.parse_args()
 
@@ -268,6 +310,7 @@ if __name__ == '__main__':
     F = np.load("custom_utils/smpl_faces" + skirt_modifier + ".npy").astype(np.int32)
     # k_neighbours(k=25)
 
+
     folder = args.folder
     frames_file = 'frames_all.txt'
 

data/preprocessing.py

@@ -119,7 +119,7 @@ def create_extras_file(folder):
         lines = [line.strip() for line in lines]
     frames = lines
 
-    for frame in tqdm(frames):
+    for frame in tqdm(frames[:1000]):
         # add a new empty group to the root group for each frame
         id, frame_nr, garment = frame.split()
         if not id in h5file.root: