Shouwei Ruan

Hi 葵酱！： 我正在尝试利用训练好的NeRF模型生成特定相机位姿（θ，φ）下的视角图像。 我想了解在 `dataset/llff` 中 `spheric_pose(theta, phi, radius)` 的矩阵变换含义，这可能涉及到一些计算图形学的问题，我不知道该从何去了解 就是这部分的矩阵运算含义： ```python def spheric_pose(theta, phi, radius): trans_t = lambda t : np.array([ [1,0,0,0], [0,1,0,-0.9*t], [0,0,1,t], [0,0,0,1], ]) rot_phi = lambda...

cv2.error

1

(base) C:\Users\茅场晶彦\PycharmProjects\age-estimation-pytorch-master>python train.py --data_dir C:\Users\茅场晶彦\PycharmProjects\age-estimation-pytorch-master\appa-real-release TRAIN.BATCH_SIZE 8 MODEL.ARCH resnet34 => creating model 'resnet34' 0%| | 0/499 [00:00

At your suggestion, I've tried [ python train.py --data_dir /appa-real-release TRAIN.BATCH_SIZE 16 MODEL.ARCH resnet34] But after downloading the model, it says: => creating model 'resnet34' Traceback (most recent call last):...

Download Object Errror

12

Hi, mattdeitke While downloading, I encountered some issues. Here is the script I used: ``` annotations = oxl.get_annotations(download_dir="~/.objaverse" ) sampled_df = annotations.groupby('fileType').apply(lambda x: x.sample(1)).reset_index(drop=True) sampled_df = sampled_df[sampled_df['fileType'] == 'obj'].reset_index(drop=True) oxl.download_objects(download_dir='./objaverse',...

I am thrilled about the work you are doing! Thank you for your contributions to the community, and for making it possible to generate 3D representations from non-aligned 2D inputs....