PointMVSNet icon indicating copy to clipboard operation
PointMVSNet copied to clipboard

About test

Open Jackye001 opened this issue 5 years ago • 2 comments

@callmeray I have met some problem in testing ,I dont know whether you have met the problem

2019-12-11 13:51:42,269 pointmvsnet.utils.checkpoint INFO: Loading checkpoint from outputs/dtu_wde3/model_pretrained.pth flow: 0 /home/smartcity/yechunkai3.6/lib/python3.6/site-packages/torch/nn/functional.py:2423: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details. "See the documentation of nn.Upsample for details.".format(mode)) flow: 1 flow: 2 Traceback (most recent call last): File "pointmvsnet/test.py", line 141, in main() File "pointmvsnet/test.py", line 137, in main test(cfg, output_dir, isCPU=isCPU) File "pointmvsnet/test.py", line 103, in test isCPU=isCPU, File "pointmvsnet/test.py", line 69, in test_model preds = model(data_batch, image_scales, inter_scales, isFlow=True, isTest=True) File "/home/smartcity/yechunkai3.6/lib/python3.6/site-packages/torch/nn/modules/module.py", line 489, in call result = self.forward(*input, **kwargs) File "/home/smartcity/yechunkai3.6/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 143, in forward outputs = self.parallel_apply(replicas, inputs, kwargs) File "/home/smartcity/yechunkai3.6/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 153, in parallel_apply return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)]) File "/home/smartcity/yechunkai3.6/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 83, in parallel_apply raise output File "/home/smartcity/yechunkai3.6/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 59, in _worker output = module(*input, **kwargs) File "/home/smartcity/yechunkai3.6/lib/python3.6/site-packages/torch/nn/modules/module.py", line 489, in call result = self.forward(*input, **kwargs) TypeError: forward() missing 3 required positional arguments: 'data_batch', 'img_scales', and 'inter_scales'

Jackye001 avatar Dec 11 '19 06:12 Jackye001

@callmeray
I have already solved the problem above , the problem is caused by using multiple GPU. I add os.environ['CUDA_VISIBLE_DEVICES']='0' in the Test script ,then it runs successfully.

Jackye001 avatar Dec 11 '19 06:12 Jackye001

@callmeray I have already solved the problem above , the problem is caused by using multiple GPU. I add os.environ['CUDA_VISIBLE_DEVICES']='0' in the Test script ,then it runs successfully.

Can Test script get the results of the paper ? like acc and comp

cuge1995 avatar Sep 21 '20 13:09 cuge1995