测试自己的数据

[luocha0107]

作者你好，我跑完提供数据的demo后，尝试在自己的数据上测试，将rgb_size改为（2158，3844），相机内参也做了相应更改，但是运行的时候出现以下错误： logging improved. Overwriting config with config_version None img_size [384, 512] /root/miniconda3/envs/gs_model/lib/python3.9/site-packages/torch/functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /opt/conda/conda-bld/pytorch_1678402412426/work/aten/src/ATen/native/TensorShape.cpp:3483.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Params passed to Resize transform: width: 512 height: 384 resize_target: True keep_aspect_ratio: True ensure_multiple_of: 32 resize_method: minimal Using pretrained resource local::./tools/zoe/models/ZoeD_M12_N.pt Loaded successfully No module 'xformers'. Proceeding without it. ControlLDM: Running in eps-prediction mode DiffusionWrapper has 859.52 M params. making attention of type 'vanilla' with 512 in_channels Working with z of shape (1, 4, 32, 32) = 4096 dimensions. making attention of type 'vanilla' with 512 in_channels Loaded model config from [./tools/controlnet/models/control_v11f1p_sd15_depth.yaml] Loaded state_dict from [./tools/controlnet/models/v1-5-pruned.ckpt] Loaded state_dict from [./tools/controlnet/models/control_v11f1p_sd15_depth_ft.pth] Seed set to 12344 We force to use step-150 (~150 rather than 150) for our control process use 20 steps! source-feat:['rgb_df', 'rgb_gf'] target-feat:['dpt_df', 'dpt_gf'] weight: [0.5 0.5] we use zoe-ransac solver for source-rgb and target-dpt! Estimating zoe-depth for rgb on demo: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:00<00:00, 9289.71it/s] 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [02:17<00:00, 68.83s/it] 0%| | 0/1 [00:00<?, ?it/s]/root/miniconda3/envs/gs_model/lib/python3.9/site-packages/torchvision/transforms/functional.py:1603: UserWarning: The default value of the antialias parameter of all the resizing transforms (Resize(), RandomResizedCrop(), etc.) will change from None to True in v0.17, in order to be consistent across the PIL and Tensor backends. To suppress this warning, directly pass antialias=True (recommended, future default), antialias=None (current default, which means False for Tensors and True for PIL), or antialias=False (only works on Tensors - PIL will still use antialiasing). This also applies if you are using the inference transforms from the models weights: update the call to weights.transforms(antialias=True). warnings.warn( 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:12<00:00, 12.33s/it] Evaling on demo... 0%| | 0/1 [00:00<?, ?it/s] Traceback (most recent call last): File "/root/data_user/ysl/FreeReg/demo.py", line 150, in mm_reg.run() File "/root/data_user/ysl/FreeReg/demo.py", line 121, in run self.eval() File "/root/data_user/ysl/FreeReg/demo.py", line 109, in eval self.evalor.run({'demo':self.meta}) File "/root/data_user/ysl/FreeReg/pipeline/gen_eval.py", line 67, in run smatch_xyz, tmatch_xyz = self.eval_pair(stype, ttype, sitem, titem, pps) File "/root/data_user/ysl/FreeReg/pipeline/gen_eval.py", line 46, in eval_pair gts, smask = self.eval_mask(source_type,sitem) File "/root/data_user/ysl/FreeReg/pipeline/gen_eval.py", line 34, in eval_mask gtd = gtd[uv[:,1],uv[:,0]] IndexError: index 986 is out of bounds for axis 0 with size 968

这是什么原因呢

[wyclike]

请问有解决吗

[luocha0107]

请问有解决吗 i'sry，时间太久了，已经忘记有没有解决这这个问题了，并且我已经放弃了这个方法

[wyclike]

好的~