diff --git a/core/nbv_dataset.py b/core/nbv_dataset.py index 5777602..6583e5b 100644 --- a/core/nbv_dataset.py +++ b/core/nbv_dataset.py @@ -4,10 +4,10 @@ import PytorchBoot.namespace as namespace import PytorchBoot.stereotype as stereotype from PytorchBoot.config import ConfigManager from PytorchBoot.utils.log_util import Log - import torch import os import sys +import time sys.path.append(r"/data/hofee/project/nbv_rec/nbv_reconstruction") @@ -51,7 +51,7 @@ class NBVReconstructionDataset(BaseDataset): scene_name_list.append(scene_name) return scene_name_list - def get_datalist(self, bias=False): + def get_datalist(self): datalist = [] for scene_name in self.scene_name_list: seq_num = DataLoadUtil.get_label_num(self.root_dir, scene_name) @@ -80,18 +80,16 @@ class NBVReconstructionDataset(BaseDataset): for data_pair in label_data["data_pairs"]: scanned_views = data_pair[0] next_best_view = data_pair[1] - accept_probability = scanned_views[-1][1] - if accept_probability > np.random.rand(): - datalist.append( - { - "scanned_views": scanned_views, - "next_best_view": next_best_view, - "seq_max_coverage_rate": max_coverage_rate, - "scene_name": scene_name, - "label_idx": seq_idx, - "scene_max_coverage_rate": scene_max_coverage_rate, - } - ) + datalist.append( + { + "scanned_views": scanned_views, + "next_best_view": next_best_view, + "seq_max_coverage_rate": max_coverage_rate, + "scene_name": scene_name, + "label_idx": seq_idx, + "scene_max_coverage_rate": scene_max_coverage_rate, + } + ) return datalist def preprocess_cache(self): @@ -117,8 +115,13 @@ class NBVReconstructionDataset(BaseDataset): except Exception as e: Log.error(f"Save cache failed: {e}") - def voxel_downsample_with_mask(self, pts, voxel_size): - pass + def voxel_downsample_with_mapping(self, point_cloud, voxel_size=0.003): + voxel_indices = np.floor(point_cloud / voxel_size).astype(np.int32) + unique_voxels, inverse, counts = np.unique(voxel_indices, axis=0, return_inverse=True, return_counts=True) + idx_sort = np.argsort(inverse) + idx_unique = idx_sort[np.cumsum(counts)-counts] + downsampled_points = point_cloud[idx_unique] + return downsampled_points, inverse def __getitem__(self, index): @@ -132,6 +135,9 @@ class NBVReconstructionDataset(BaseDataset): scanned_coverages_rate, scanned_n_to_world_pose, ) = ([], [], []) + start_time = time.time() + start_indices = [0] + total_points = 0 for view in scanned_views: frame_idx = view[0] coverage_rate = view[1] @@ -153,8 +159,12 @@ class NBVReconstructionDataset(BaseDataset): n_to_world_trans = n_to_world_pose[:3, 3] n_to_world_9d = np.concatenate([n_to_world_6d, n_to_world_trans], axis=0) scanned_n_to_world_pose.append(n_to_world_9d) + total_points += len(downsampled_target_point_cloud) + start_indices.append(total_points) + end_time = time.time() + #Log.info(f"load data time: {end_time - start_time}") nbv_idx, nbv_coverage_rate = nbv[0], nbv[1] nbv_path = DataLoadUtil.get_path(self.root_dir, scene_name, nbv_idx) cam_info = DataLoadUtil.load_cam_info(nbv_path) @@ -167,14 +177,27 @@ class NBVReconstructionDataset(BaseDataset): best_to_world_9d = np.concatenate( [best_to_world_6d, best_to_world_trans], axis=0 ) - - combined_scanned_views_pts = np.concatenate(scanned_views_pts, axis=0) - voxel_downsampled_combined_scanned_pts_np = PtsUtil.voxel_downsample_point_cloud(combined_scanned_views_pts, 0.002) - random_downsampled_combined_scanned_pts_np = PtsUtil.random_downsample_point_cloud(voxel_downsampled_combined_scanned_pts_np, self.pts_num) + combined_scanned_views_pts = np.concatenate(scanned_views_pts, axis=0) + voxel_downsampled_combined_scanned_pts_np, inverse = self.voxel_downsample_with_mapping(combined_scanned_views_pts, 0.003) + random_downsampled_combined_scanned_pts_np, random_downsample_idx = PtsUtil.random_downsample_point_cloud(voxel_downsampled_combined_scanned_pts_np, self.pts_num, require_idx=True) + + all_idx_unique = np.arange(len(voxel_downsampled_combined_scanned_pts_np)) + all_random_downsample_idx = all_idx_unique[random_downsample_idx] + scanned_pts_mask = [] + for idx, start_idx in enumerate(start_indices): + if idx == len(start_indices) - 1: + break + end_idx = start_indices[idx+1] + view_inverse = inverse[start_idx:end_idx] + view_unique_downsampled_idx = np.unique(view_inverse) + view_unique_downsampled_idx_set = set(view_unique_downsampled_idx) + mask = np.array([idx in view_unique_downsampled_idx_set for idx in all_random_downsample_idx]) + scanned_pts_mask.append(mask) data_item = { "scanned_pts": np.asarray(scanned_views_pts, dtype=np.float32), # Ndarray(S x Nv x 3) "combined_scanned_pts": np.asarray(random_downsampled_combined_scanned_pts_np, dtype=np.float32), # Ndarray(N x 3) + "scanned_pts_mask": np.asarray(scanned_pts_mask, dtype=np.bool), # Ndarray(N) "scanned_coverage_rate": scanned_coverages_rate, # List(S): Float, range(0, 1) "scanned_n_to_world_pose_9d": np.asarray(scanned_n_to_world_pose, dtype=np.float32), # Ndarray(S x 9) "best_coverage_rate": nbv_coverage_rate, # Float, range(0, 1) @@ -200,7 +223,9 @@ class NBVReconstructionDataset(BaseDataset): collate_data["scanned_n_to_world_pose_9d"] = [ torch.tensor(item["scanned_n_to_world_pose_9d"]) for item in batch ] - + collate_data["scanned_pts_mask"] = [ + torch.tensor(item["scanned_pts_mask"]) for item in batch + ] ''' ------ Fixed Length ------ ''' collate_data["best_to_world_pose_9d"] = torch.stack( @@ -209,12 +234,14 @@ class NBVReconstructionDataset(BaseDataset): collate_data["combined_scanned_pts"] = torch.stack( [torch.tensor(item["combined_scanned_pts"]) for item in batch] ) + for key in batch[0].keys(): if key not in [ "scanned_pts", "scanned_n_to_world_pose_9d", "best_to_world_pose_9d", "combined_scanned_pts", + "scanned_pts_mask", ]: collate_data[key] = [item[key] for item in batch] return collate_data @@ -230,10 +257,9 @@ if __name__ == "__main__": torch.manual_seed(seed) np.random.seed(seed) config = { - "root_dir": "/data/hofee/data/new_full_data", - "model_dir": "../data/scaled_object_meshes", + "root_dir": "/data/hofee/nbv_rec_part2_preprocessed", "source": "nbv_reconstruction_dataset", - "split_file": "/data/hofee/data/new_full_data_list/OmniObject3d_train.txt", + "split_file": "/data/hofee/data/sample.txt", "load_from_preprocess": True, "ratio": 0.5, "batch_size": 2, diff --git a/core/pipeline.py b/core/pipeline.py index 1050628..8d89930 100644 --- a/core/pipeline.py +++ b/core/pipeline.py @@ -91,25 +91,49 @@ class NBVReconstructionPipeline(nn.Module): "scanned_n_to_world_pose_9d" ] # List(B): Tensor(S x 9) + scanned_pts_mask_batch = data["scanned_pts_mask"] # List(B): Tensor(N) + device = next(self.parameters()).device embedding_list_batch = [] combined_scanned_pts_batch = data["combined_scanned_pts"] # Tensor(B x N x 3) - global_scanned_feat = self.pts_encoder.encode_points( - combined_scanned_pts_batch, require_per_point_feat=False + global_scanned_feat, per_point_feat_batch = self.pts_encoder.encode_points( + combined_scanned_pts_batch, require_per_point_feat=True ) # global_scanned_feat: Tensor(B x Dg) - - for scanned_n_to_world_pose_9d in scanned_n_to_world_pose_9d_batch: - scanned_n_to_world_pose_9d = scanned_n_to_world_pose_9d.to(device) # Tensor(S x 9) + batch_size = len(scanned_n_to_world_pose_9d_batch) + for i in range(batch_size): + seq_len = len(scanned_n_to_world_pose_9d_batch[i]) + scanned_n_to_world_pose_9d = scanned_n_to_world_pose_9d_batch[i].to(device) # Tensor(S x 9) + scanned_pts_mask = scanned_pts_mask_batch[i] # Tensor(S x N) + per_point_feat = per_point_feat_batch[i] # Tensor(N x Dp) + partial_point_feat_seq = [] + for j in range(seq_len): + partial_per_point_feat = per_point_feat[scanned_pts_mask[j]] + if partial_per_point_feat.shape[0] == 0: + partial_point_feat = torch.zeros(per_point_feat.shape[1], device=device) + else: + partial_point_feat = torch.mean(partial_per_point_feat, dim=0) # Tensor(Dp) + partial_point_feat_seq.append(partial_point_feat) + partial_point_feat_seq = torch.stack(partial_point_feat_seq, dim=0) # Tensor(S x Dp) + pose_feat_seq = self.pose_encoder.encode_pose(scanned_n_to_world_pose_9d) # Tensor(S x Dp) - seq_embedding = pose_feat_seq + + seq_embedding = torch.cat([partial_point_feat_seq, pose_feat_seq], dim=-1) + embedding_list_batch.append(seq_embedding) # List(B): Tensor(S x (Dp)) seq_feat = self.seq_encoder.encode_sequence(embedding_list_batch) # Tensor(B x Ds) main_feat = torch.cat([seq_feat, global_scanned_feat], dim=-1) # Tensor(B x (Ds+Dg)) if torch.isnan(main_feat).any(): + for i in range(len(main_feat)): + if torch.isnan(main_feat[i]).any(): + scanned_pts_mask = scanned_pts_mask_batch[i] + Log.info(f"scanned_pts_mask shape: {scanned_pts_mask.shape}") + Log.info(f"scanned_pts_mask sum: {scanned_pts_mask.sum()}") + import ipdb + ipdb.set_trace() Log.error("nan in main_feat", True) return main_feat