黎自鸿
黎自鸿
Hello ,I download the dtu .But the path is like this,data/dtu/scan1/pair.txt.But i find that in the dtu.yaml , the ROOT_DIR of TRAIN is data/dtu2.How should i do with the data...
您好，我运行了您的生成代码，发现运行的效果很不错，对您的模型很感兴趣，所以想继续深入了解一下训练代码，但是我发现您的配置文件中关于数据的文件配置项，data: target: src.data.objaverse.DataModuleFromConfig params: batch_size: 2 num_workers: 8 train: target: src.data.objaverse.ObjaverseData params: root_dir: data/objaverse meta_fname: filtered_obj_name.json input_image_dir: rendering_random_32views target_image_dir: rendering_random_32views input_view_num: 6 target_view_num: 4 total_view_n: 32 fov: 50 camera_rotation: true...
Hello,i'm interested in this work，but i can't find the training code in your train.py.When will you submit your whole training code ?it will be so grateful for me if you...
Hello ， i read your paper and i find that you render 16 views from an elevation of 30 degrees and azimuth linearly spaced across 360 degrees.I am interested in...
你好，我在运行训练代码，model.py文件里面这一段： input_c2ws=torch.tensor(batch['input_c2ws']) print(input_c2ws.shape) #nput_c2ws=np.array(batch['input_c2ws'].cpu()) input_c2ws=input_c2ws.reshape(input_c2ws.shape[0],-1) #input_c2ws=input_c2ws.flatten(-2) input_Ks = batch['input_Ks'].flatten(-2) input_extrinsics = input_c2ws[:, :, :12]， 报了IndexError: too many indices for tensor of dimension 2的错误，我的input_c2ws是6*4*4的list，所以源代码的flatten操作我改成了reshape，变换后应该是6*16，但是input_c2ws[:, :, :12]这一行就执行不了，所以想问问看您之前跑的时候的input_c2ws的维度具体是多少呢？是我这边的维度有错么
Hello，i‘m trying to run the training code ,but i find that the max_epochs: is setted to -1。it will be grateful if you can tell me how many epoches did you...