search

kangpeilun / VastGaussian

This is an unofficial Implementation
Apache License 2.0
360 stars 26 forks source link

ValueError: cannot reshape array of size 1 into shape (3,3) #9

Open xvbai0317 opened 5 months ago

xvbai0317 commented 5 months ago

2024-06-03 02:34:20.940364: I tensorflow/core/util/port.cc:110] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable TF_ENABLE_ONEDNN_OPTS=0. 2024-06-03 02:34:21.013904: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. Traceback (most recent call last): File "/home/xzj/project/VastGaussian-master/train_vast.py", line 323, in train_main() File "/home/xzj/project/VastGaussian-master/train_vast.py", line 283, in train_main rot = np.array(lp.rot).reshape([3, 3]) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ValueError: cannot reshape array of size 1 into shape (3,3)

用的是tandt_db数据集

Livioni commented 5 months ago

请使用Versions-that-perform-Manhattan-alignment 分支下的脚本。 问题应该出现在参数传入上

https://github.com/kangpeilun/VastGaussian/blob/586384a1103029cd81966d6cd74a5e8827c7de75/arguments/parameters.py#L60 下面的应该是正确的：

    parser.add_argument("--pos", nargs=3, type=float, default = (0.0,0.0,0.0))       # 点云平移
    parser.add_argument("--rot", nargs=3, type=float, default = (0.0,0.0,0.0))       # 点云平移

@kangpeilun