GFLA error

log.txt

> python test.py --name=pose_fashion_checkpoints --model=pose --attn_layer=2,3 --kernel_size=2=5,3=3 --gpu_id=0 --dataset_mode=fashion --dataroot=./dataset/fashion --results_dir=./eval_results/fashion

--------------Options--------------
angle: False
attn_layer: [2, 3]
batchSize: 1
checkpoints_dir: ./result
continue_train: False
dataroot: ./dataset/fashion
dataset_mode: fashion
display_env: posefashioncheckpoints
display_id: 1
display_port: 8096
display_single_pane_ncols: 0
display_winsize: 256
fid_gt_path: None
gpu_ids: 0
image_nc: 3
init_type: orthogonal
isTrain: False
kernel_size: {'2': 5, '3': 3}
lambda_content: 0.5
lambda_correct: 5.0
lambda_g: 2.0
lambda_rec: 5.0
lambda_regularization: 0.0025
lambda_style: 500.0
layers: 3
load_size: 256
max_dataset_size: 9223372036854775807
model: pose
nThreads: 8
name: pose_fashion_checkpoints
netD: res
netG: pose
old_size: (256, 176)
phase: test
ratio_g2d: 0.1
results_dir: ./eval_results/fashion
save_input: False
scale: False
serial_batches: True
shift: False
structure_nc: 18
use_spect_d: True
use_spect_g: False
which_iter: latest
----------------End----------------
Loading data pairs ...
Loading data pairs finished ...
dataset [FashionDataset] of size 8570 was created
testing images = 8570
Network [PoseGenerator] was created. Total number of parameters: 14.0474 million. To see the architecture, do print(network).
THCudaCheck FAIL file=/pytorch/aten/src/THC/generic/THCTensorMathPairwise.cu line=225 error=11 : invalid argument
Traceback (most recent call last):
  File "test.py", line 18, in <module>
    model = create_model(opt)
  File "/home/ubuntu/Global-Flow-Local-Attention/model/__init__.py", line 32, in create_model
    instance = model(opt)
  File "/home/ubuntu/Global-Flow-Local-Attention/model/pose_model.py", line 65, in __init__
    norm='instance', activation='LeakyReLU', extractor_kz=opt.kernel_size)
  File "/home/ubuntu/Global-Flow-Local-Attention/model/networks/__init__.py", line 37, in define_g
    return create_network(netG_cls, opt, **parameter_dic)
  File "/home/ubuntu/Global-Flow-Local-Attention/model/networks/__init__.py", line 28, in create_network
    net.init_weights(opt.init_type)
  File "/home/ubuntu/Global-Flow-Local-Attention/model/networks/base_network.py", line 55, in init_weights
    self.apply(init_func)
  File "/home/ubuntu/anaconda3/envs/gfla/lib/python3.6/site-packages/torch/nn/modules/module.py", line 242, in apply
    module.apply(fn)
  File "/home/ubuntu/anaconda3/envs/gfla/lib/python3.6/site-packages/torch/nn/modules/module.py", line 242, in apply
    module.apply(fn)
  File "/home/ubuntu/anaconda3/envs/gfla/lib/python3.6/site-packages/torch/nn/modules/module.py", line 242, in apply
    module.apply(fn)
  [Previous line repeated 1 more time]
  File "/home/ubuntu/anaconda3/envs/gfla/lib/python3.6/site-packages/torch/nn/modules/module.py", line 243, in apply
    fn(self)
  File "/home/ubuntu/Global-Flow-Local-Attention/model/networks/base_network.py", line 47, in init_func
    init.orthogonal_(m.weight.data, gain=gain)
  File "/home/ubuntu/anaconda3/envs/gfla/lib/python3.6/site-packages/torch/nn/init.py", line 356, in orthogonal_
    q, r = torch.qr(flattened)
RuntimeError: cuda runtime error (11) : invalid argument at /pytorch/aten/src/THC/generic/THCTensorMathPairwise.cu:225