vic

cmr-human36m demo error

5

这个函数报错： vertex, align_state = registration(vertex, uv_point_pred[0], self.j_regressor, data['K'][0].cpu().numpy(), args.size, uv_conf=uv_pred_conf[0], poly=poly) ValueError: matmul: Input operand 1 has a mismatch in its core dimension 0, with gufunc signature (n?,k),(k,m?)->(n?,m?) (size 6890...

ImportError: Module use of python27.dll conflicts with this version of Python.

5

(python35) D:\Program Files (x86)\PortableGit\bin\Faster-RCNN_TF>python ./tools/ demo.py --model E:\Proj\deeplearning\VGGnet_fast_rcnn_iter_70000.ckpt Traceback (most recent call last): File "./tools/demo.py", line 4, in from fast_rcnn.test import im_detect File "D:\Program Files (x86)\PortableGit\bin\Faster-RCNN_TF\tools\..\lib\fast_ rcnn\test.py", line 17, in...

unknown reconstruction result using BFM model, need help

1

At first, I get bfm2009_model from 01_MorphableModel.mat. Then I use texture_coordinates from stn/BFM_UV.mat (size of [2 53490], range [0 1])and texture_triangle_indices from" bfm2009_model['tl'] - 1". However, the obj result of...

model放好了 run_model 出现这个错误 把run_mode.pyl里的batch_size值改小 还是报这个错

1

2018-03-13 15:20:04.122000: I C:\tf_jenkins\workspace\rel-win\M\windows-gpu\PY\3 6\tensorflow\core\common_runtime\bfc_allocator.cc:680] Stats: Limit: 1631711232 InUse: 1229069056 MaxInUse: 1631711232 NumAllocs: 51 MaxAllocSize: 422898176 2018-03-13 15:20:04.122000: W C:\tf_jenkins\workspace\rel-win\M\windows-gpu\PY\3 6\tensorflow\core\common_runtime\bfc_allocator.cc:279] *_______________________* **************************************************************************x 2018-03-13 15:20:04.123000: W C:\tf_jenkins\workspace\rel-win\M\windows-gpu\PY\3 6\tensorflow\core\framework\op_kernel.cc:1202] OP_REQUIRES failed...

hi, i try to replace resnet netwrok in HMR by mobilenet v3, according to your work. however, i found the training becomes not convernge and the loss becomes larger. I...

about the 3d rotate with 2d rotate

5

in the data_processor.random_rotate(), the returned joint2d is right:  however the returned joint3d is weird:  and the returned mano output is : 

感谢你的复现工作，我发现scale和tans loss无法下降， 预训练完成后还是几千的loss，test时效果也很差，请问会是哪里的问题呢？

black dots appear in background of merged result when super-resolution params > 0

3

After training model, in the merge_SAEHD.sh process, black dots appear in the background of merged result while the super-resolution param is set 5. The dots disappear when the super-resolution param...