python testBatchModel.py testBatchModel.txt ../data/robert/
Prepare image ../data/paper/imgs/test3dfacedetection.jpg:
Number of faces detected: 1
CNN Model loaded to regress 3D Shape and Texture!
('> Processing image: ', '../data/robert//imgs/test3dfacedetection.png', ' ', 'test3dfacedetection.png', ' ', '1/1')
/root/anaconda2/lib/python2.7/site-packages/skimage/transform/warps.py:84: UserWarning: The default mode, 'constant', will be changed to 'reflect' in skimage 0.15.
warn("The default mode, 'constant', will be changed to 'reflect' in "
Regress bump maps
Traceback (most recent call last):
File "testBatchModel.py", line 183, in <module>
bumpMapRegressor.estimateBump(bumpModel_path, data_out + "/imList.txt", data_out + "/bump/")
File "/home/pythonhack/extreme_3d_faces-master/demoCode/bumpMapRegressor.py", line 336, in estimateBump
net.load_state_dict(torch.load(modelPath));
File "/root/anaconda2/lib/python2.7/site-packages/torch/serialization.py", line 261, in load
return load(f, map_location, pickle_module)
File "/root/anaconda2/lib/python2.7/site-packages/torch/serialization.py", line 409, in load
result = unpickler.load()
File "/root/anaconda2/lib/python2.7/site-packages/torch/serialization.py", line 380, in persistent_load
data_type(size), location)
File "/root/anaconda2/lib/python2.7/site-packages/torch/serialization.py", line 86, in default_restore_location
result = fn(storage, location)
File "/root/anaconda2/lib/python2.7/site-packages/torch/serialization.py", line 68, in cuda_deserialize
return obj.cuda(device)
File "/root/anaconda2/lib/python2.7/site-packages/torch/utils.py", line 61, in cuda
with torch.cuda.device(device):
File "/root/anaconda2/lib/python2.7/site-packages/torch/cuda/init.py", line 186, in enter
lazy_init()
File "/root/anaconda2/lib/python2.7/site-packages/torch/cuda/init.py", line 120, in lazy_init
check_driver()
File "/root/anaconda2/lib/python2.7/site-packages/torch/cuda/init.py", line 62, in check_driver
http://www.nvidia.com/Download/index.aspx""")
AssertionError:
Found no NVIDIA driver on your system. Please check that you
have an NVIDIA GPU and installed a driver from
http://www.nvidia.com/Download/index.aspx
Segmentation fault
[root@master@/home/pythonhack/extreme_3d_faces-master/demoCode@16:36:55]
2130 $ vi "/root/anaconda2/lib/python2.7/site-packages/torch/serialization.py"
[root@master@/home/pythonhack/extreme_3d_faces-master/demoCode@16:37:25]
2131 $ vi +68 "/root/anaconda2/lib/python2.7/site-packages/torch/serialization.py"
[root@master@/home/pythonhack/extreme_3d_faces-master/demoCode@16:37:48]
2132 $ python testBatchModel.py testBatchModel.txt ../data/robert/
Prepare image ../data/paper/imgs/test3dfacedetection.jpg:
Number of faces detected: 1
CNN Model loaded to regress 3D Shape and Texture!
('> Processing image: ', '../data/robert//imgs/test3dfacedetection.png', ' ', 'test3dfacedetection.png', ' ', '1/1')
/root/anaconda2/lib/python2.7/site-packages/skimage/transform/warps.py:84: UserWarning: The default mode, 'constant', will be changed to 'reflect' in skimage 0.15.
warn("The default mode, 'constant', will be changed to 'reflect' in "
Regress bump maps
['add', 'and', 'array', 'array_wrap', 'bool', 'class', 'deepcopy', 'delattr', 'delitem', 'dict', 'div', 'doc', 'eq', 'float', 'format', 'ge', 'getattribute', 'getitem', 'getstate', 'gt', 'hash', 'iadd', 'iand', 'idiv', 'ilshift', 'imul', 'init', 'int', 'invert', 'ior', 'ipow', 'irshift', 'isub', 'iter', 'itruediv', 'ixor', 'le', 'len', 'long', 'lshift', 'lt', 'matmul', 'mod', 'module', 'mul', 'ne', 'neg', 'new', 'nonzero', 'or', 'pow', 'radd', 'rdiv', 'reduce', 'reduce_ex', 'repr', 'rmul', 'rpow', 'rshift', 'rsub', 'rtruediv', 'setattr', 'setitem', 'setstate', 'sizeof', 'str', 'sub', 'subclasshook', 'truediv', 'weakref', 'xor', 'advanced_index_add', 'advanced_index_select', 'cdata', 'check_advanced_indexing', 'new_with_metadata_file', 'set_index', 'sparse_mask', 'torch', 'write_metadata', 'abs', 'abs', 'acos', 'acos', 'add', 'add', 'addbmm', 'addbmm', 'addcdiv', 'addcdiv', 'addcmul', 'addcmul', 'addmm', 'addmm', 'addmv', 'addmv', 'addr', 'addr', 'apply', 'asin', 'asin', 'atan', 'atan2', 'atan2', 'atan', 'baddbmm', 'baddbmm', 'bernoulli', 'bernoulli', 'bmm', 'btrifact', 'btrisolve', 'byte', 'cauchy', 'ceil', 'ceil', 'char', 'chunk', 'clamp', 'clamp', 'clone', 'contiguous', 'copy', 'cos', 'cos', 'cosh', 'cosh_', 'cpu', 'cross', 'cuda', 'cumprod', 'cumsum', 'data', 'data_ptr', 'diag', 'dim', 'dist', 'div', 'div_', 'dot', 'double', 'eig', 'element_size', 'eq', 'eq_', 'equal', 'erf', 'erf_', 'erfinv', 'erfinv_', 'exp', 'exp_', 'expand', 'expand_as', 'exponential_', 'fill_', 'float', 'floor', 'floor_', 'fmod', 'fmod_', 'frac', 'frac_', 'gather', 'ge', 'ge_', 'gels', 'geometric_', 'geqrf', 'ger', 'gesv', 'gt', 'gt_', 'half', 'histc', 'index', 'index_add_', 'index_copy_', 'index_fill_', 'index_select', 'int', 'inverse', 'is_contiguous', 'is_cuda', 'is_pinned', 'is_same_size', 'is_set_to', 'is_shared', 'is_signed', 'is_sparse', 'kthvalue', 'le', 'le_', 'lerp', 'lerp_', 'lgamma', 'lgamma_', 'log', 'log1p', 'log1p_', 'log_', 'log_normal_', 'long', 'lt', 'lt_', 'map2_', 'map_', 'masked_copy_', 'masked_fill_', 'masked_scatter_', 'masked_select', 'matmul', 'max', 'mean', 'median', 'min', 'mm', 'mode', 'mul', 'mul_', 'multinomial', 'mv', 'narrow', 'ndimension', 'ne', 'ne_', 'neg', 'neg_', 'nelement', 'new', 'nonzero', 'norm', 'normal_', 'numel', 'numpy', 'orgqr', 'ormqr', 'permute', 'pin_memory', 'potrf', 'potri', 'potrs', 'pow', 'pow_', 'prod', 'pstrf', 'put_', 'qr', 'random_', 'reciprocal', 'reciprocal_', 'remainder', 'remainder_', 'renorm', 'renorm_', 'repeat', 'resize_', 'resize_as_', 'round', 'round_', 'rsqrt', 'rsqrt_', 'scatter_', 'scatter_add_', 'select', 'set_', 'shape', 'share_memory_', 'short', 'sigmoid', 'sigmoid_', 'sign', 'sign_', 'sin', 'sin_', 'sinh', 'sinh_', 'size', 'sort', 'split', 'sqrt', 'sqrt_', 'squeeze', 'squeeze_', 'std', 'storage', 'storage_offset', 'storage_type', 'stride', 'sub', 'sub_', 'sum', 'svd', 'symeig', 't', 't_', 'take', 'tan', 'tan_', 'tanh', 'tanh_', 'tolist', 'topk', 'trace', 'transpose', 'transpose_', 'tril', 'tril_', 'triu', 'triu_', 'trtrs', 'trunc', 'trunc_', 'type', 'type_as', 'unfold', 'uniform_', 'unsqueeze', 'unsqueeze_', 'var', 'view', 'view_as', 'zero_']
Recover the 3D models
cd ../bin; ./TestBump -batch ../data/robert//imList.txt ../data/robert//3D/ ../data/robert//shape ../data/robert//bump ../data/robert//bump ../3DMM_model/BaselFaceModel_mod.h5 ../dlib_model/shape_predictor_68_face_landmarks.dat ../data/robert//imgs; cd ../demoCode
load ../3DMM_model/BaselFaceModel_mod.h5
Process ../data/robert//imgs/test3dfacedetection.png
Process
sh: line 1: 23333 Segmentation fault ./TestBump -batch ../data/robert//imList.txt ../data/robert//3D/ ../data/robert//shape ../data/robert//bump ../data/robert//bump ../3DMM_model/BaselFaceModel_mod.h5 ../dlib_model/shape_predictor_68_face_landmarks.dat ../data/robert//imgs
Segmentation fault
注:尽管bash命令报错 Segmentation fault,需要的ply文件还是生成了。