zpdesu / sean Goto Github PK
View Code? Open in Web Editor NEWSEAN: Image Synthesis with Semantic Region-Adaptive Normalization (CVPR 2020, Oral)
Home Page: https://zpdesu.github.io/SEAN/
License: Other
SEAN: Image Synthesis with Semantic Region-Adaptive Normalization (CVPR 2020, Oral)
Home Page: https://zpdesu.github.io/SEAN/
License: Other
Help, please! I used skimage.measure.compare_ssim
to your CelebA-HQ_pretrained
on the test set and got a result SSIM of 0.54 which was supposed to be 0.73 as in your paper. The generated image looks just fine with high reconstruction quality. Would you please tell me where has gone wrong? (actually other metrics went wrong too. https://github.com/mseitzer/pytorch-fid got a FID of 30 but was supposed to be 17.66)
Here's my code:
def ssim_score(generated_images, reference_images):
ssim_score_list = []
for reference_image, generated_image in zip(reference_images, generated_images):
ssim = skimage.measure.compare_ssim(reference_image, generated_image, multichannel=True,
data_range=generated_image.max() - generated_image.min())
ssim_score_list.append(ssim)
return np.mean(ssim_score_list)
I get an error when I run test.py
!python test.py --checkpoints_dir "" --name CelebA-HQ_pretrained --load_size 256 --crop_size 256 --dataset_mode custom --label_dir /content/SEAN/imgs/colormaps --image_dir /content/SEAN/imgs/colormaps --label_nc 19 --no_instance --gpu_ids 0
----------------- Options ---------------
aspect_ratio: 1.0
batchSize: 1
cache_filelist_read: False
cache_filelist_write: False
checkpoints_dir: [default: ./checkpoints]
contain_dontcare_label: False
crop_size: 256
dataroot: ./datasets/cityscapes/
dataset_mode: custom [default: coco]
display_winsize: 256
gpu_ids: 0
how_many: inf
image_dir: /content/SEAN/imgs/colormaps [default: None]
init_type: xavier
init_variance: 0.02
instance_dir:
isTrain: False [default: None]
label_dir: /content/SEAN/imgs/colormaps [default: None]
label_nc: 19 [default: 13]
load_from_opt_file: False
load_size: 256
max_dataset_size: 9223372036854775807
model: pix2pix
nThreads: 28
name: CelebA-HQ_pretrained [default: label2coco]
nef: 16
netG: spade
ngf: 64
no_flip: True
no_instance: True [default: False]
no_pairing_check: False
norm_D: spectralinstance
norm_E: spectralinstance
norm_G: spectralspadesyncbatch3x3
num_upsampling_layers: normal
output_nc: 3
phase: test
preprocess_mode: resize_and_crop
results_dir: ./results/
serial_batches: True
status: test
use_vae: False
which_epoch: latest
z_dim: 256
----------------- End -------------------
dataset [CustomDataset] of size 2 was created
Network [SPADEGenerator] was created. Total number of parameters: 266.9 million. To see the architecture, do print(network).
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [32,0,0], thread: [160,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [32,0,0], thread: [161,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [32,0,0], thread: [162,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [32,0,0], thread: [163,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [32,0,0], thread: [164,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [32,0,0], thread: [165,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [32,0,0], thread: [166,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [32,0,0], thread: [167,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [32,0,0], thread: [168,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [32,0,0], thread: [169,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [32,0,0], thread: [170,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [32,0,0], thread: [171,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [32,0,0], thread: [172,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [32,0,0], thread: [173,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [32,0,0], thread: [174,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [32,0,0], thread: [175,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [32,0,0], thread: [181,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [32,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [33,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [34,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [35,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [36,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [37,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [38,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [39,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [40,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [41,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [42,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [43,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [44,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [45,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [46,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [47,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [48,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [49,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [50,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [51,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [52,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [53,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [54,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [55,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [56,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [57,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [58,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [59,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [60,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [61,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [62,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [63,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [96,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [97,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [98,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [99,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [100,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [101,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [102,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [103,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [104,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [105,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [106,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [107,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [108,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [109,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [110,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [111,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [112,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [113,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [114,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [115,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [116,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [117,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [118,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [119,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [120,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [121,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [122,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [123,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [124,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [125,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [126,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [127,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [160,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [161,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [162,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [163,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [165,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [166,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [167,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [168,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [169,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [170,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [171,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [172,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [173,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [174,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [175,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [176,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [177,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [178,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [179,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [180,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [181,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [182,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [183,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [184,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [185,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [186,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [187,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [188,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [189,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [190,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo<Real, IndexType>, TensorInfo<long, IndexType>, Real, int, IndexType) [with IndexType = unsigned int, Real = float, Dims = -1]: block: [10,0,0], thread: [191,0,0] Assertion `indexValue >= 0 && indexValue < tensor.sizes[dim]` failed.
Traceback (most recent call last):
File "test.py", line 37, in <module>
generated = model(data_i, mode='inference')
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 547, in __call__
result = self.forward(*input, **kwargs)
File "/content/SEAN/models/pix2pix_model.py", line 58, in forward
fake_image = self.save_style_codes(input_semantics, real_image, obj_dic)
File "/content/SEAN/models/pix2pix_model.py", line 205, in save_style_codes
fake_image = self.netG(input_semantics, real_image, obj_dic=obj_dic)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 547, in __call__
result = self.forward(*input, **kwargs)
File "/content/SEAN/models/networks/generator.py", line 79, in forward
x = self.fc(x)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 547, in __call__
result = self.forward(*input, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/conv.py", line 343, in forward
return self.conv2d_forward(input, self.weight)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/conv.py", line 340, in conv2d_forward
self.padding, self.dilation, self.groups)
RuntimeError: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED
Hi, why your results in Table 2 (cityspaces and ade) different from those from SPADE paper while you used the same dataset train/test splits? For instance, results of SPADE on cityscapes are 62.3 mIoU, 81.9 accu and 71.8 FID, but you reported 57.88 mIoU, 93.59 accu and 50.38 FID, respectively.
Hi, thanks for your excellent work! By the way, I have some question about the work:
Hello there, I'm trying to train the model on ADE20K dataset, but after a few epoches of training, the losses turned into NaN and D_real turned into 0.000(generated blank images). Would you please tell me what could be the problem? Thanks a lot!
Here's how I trained:
python train.py --name ADE --load_size 256 --crop_size 256 --dataset_mode custom --label_dir /home/ADEChallengeData2016/annotations/training --image_dir /home/ADEChallengeData2016/images/training --label_nc 151 --no_instance --batchSize 2 --gpu_ids 7
Traceback (most recent call last):
File "run_UI.py", line 457, in update_entire_feature
if cb_status and i in self.label_count:
AttributeError: 'Ex' object has no attribute 'label_count'
Abort trap: 6
Hi, what does 'ACE' means? Does anybody know? Thanks
Hello,
I'm reimplementing your work in TensorFlow.
I have some questions about the input range.
Based on your code, input image is [-1, 1] , segmentation map is [0, 255].
Am I right?
Furthermore, PSNR and SSIM are calculated in RGB domain or Y domain?
Hi,
Thanks for the great work! I wonder that if there is a way to generate images with style images and mask but not using run_UI.py? Because I cannot run the UI demo successfully. Thanks a lot!
Hi, can you provide the pretrained models on cityscapes and ade20k datasets? SEAN is a wonderful work. Thanks
Hi ! Thank you for your great work. I was wondering if it was somehow possible to use your framework to synthesize faces with custom/arbitrary style codes (i.e. not with a style image as input but directly with the style encodings) ? In order to perform walks/interpolations in the style latent space for instance. Thanks a lot :)
QObject::moveToThread: Current thread (0x5de04f0) is not the object's thread (0x646e910).
Cannot move to target thread (0x5de04f0)
qt.qpa.plugin: Could not load the Qt platform plugin "xcb" in "/home/muneeb/Desktop/projects/face_style/SEAN/.env/lib/python3.8/site-packages/cv2/qt/plugins" even though it was found.
This application failed to start because no Qt platform plugin could be initialized. Reinstalling the application may fix this problem.
Available platform plugins are: xcb, eglfs, linuxfb, minimal, minimalegl, offscreen, vnc, wayland-egl, wayland, wayland-xcomposite-egl, wayland-xcomposite-glx, webgl.
Aborted (core dumped)
Thanks for your contribution, @ZPdesu, but I have some questions about your paper.
I try to change code to use torch.ditributed. But, It will done without errors in
SEAN/models/networks/normalization.py
Line 119 in 04c7536
torch.randn(x.shape[0], x.shape[3], x.shape[2], 1).cuda()
. It is weird.When you want to change the style for an image which you download online, do you have to train or finetune the model again?
Thanks for providing good code.
I want to use a custom image with pretrained model.
But when I create the original custom image with the custom image and mask it gives weird results.
It produces accurate results when using celebAMask images, but not accurate results when using custom images.
How can I solve this?
Note: I used the Bisenet model to generate the mask. -> Here
trying to continue train CelebA-HQ_pretrained using your provided checkpoints and got this error
size mismatch for fc.weight: copying a param with shape torch.Size([1024, 19, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 20, 3, 3])
.
the model changed?
How can I only reconstruct face like your paper?
I want to preserve hair style and just change face.
But there is no option to choose it.
Hello,
Thanks for providing source-code of this amazing work.
I am trying to reproduce your work line-by-line, and found a lot of implementation unclear. Hopefully, you would help to clarify the following questions:
The code function and module namings are very confusing. The region-based adaptive method from the paper is called SEAN, while in this repo is called ACE. I hope the author (if having some time) could slightly modify the code into a more readable way. This would significantly help the readers to easily catch up with the detailed idea, since the majority code base is from SPADE.
What's the intuition for the last ResBlk degraded into standard SPADE block rather than using the SEAN across all layers?
From the paper (and the code), the loss function is exactly the same from SPADE and pix2pix. I am wondering, how to have the reconstruction* signal to push the generator generates the same input data? Just from the perceptual loss and feature matching loss?
So the entire training only does reconstruction, or other words, GAN training, using the same style code extracted from the same training data? Only after it fully converges, then we re-shuffle style code from different data to perform style transfer. Am I understanding this correctly? So we shouldn't reshuffle the style code during training?
Thanks very much for the help.
Best,
I used the Bisenet to parse the face on my dataset and used your script in util/CelebMask-HQ/Data_preprocessing/v_mask.py ,but I get the different color ,so I want to known how to generate the color parsing map the same with you? Thanks!!!
----------------- Options ---------------
aspect_ratio: 1.0
batchSize: 1
cache_filelist_read: False
cache_filelist_write: False
checkpoints_dir: ./checkpoints
contain_dontcare_label: False
crop_size: 256
dataroot: ./datasets/cityscapes/
dataset_mode: custom [default: coco]
display_winsize: 256
gpu_ids: 0
how_many: inf
image_dir: datasets/CelebA-HQ/test/images [default: None]
init_type: xavier
init_variance: 0.02
instance_dir:
isTrain: False [default: None]
label_dir: datasets/CelebA-HQ/test/labels [default: None]
label_nc: 19 [default: 13]
load_from_opt_file: False
load_size: 256
max_dataset_size: 9223372036854775807
model: pix2pix
nThreads: 28
name: CelebA-HQ_pretrained [default: label2coco
nef: 16
netG: spade
ngf: 64
no_flip: True
no_instance: True [default: False]
no_pairing_check: False
norm_D: spectralinstance
norm_E: spectralinstance
norm_G: spectralspadesyncbatch3x3
num_upsampling_layers: normal
output_nc: 3
phase: test
preprocess_mode: resize_and_crop
results_dir: ./results/
serial_batches: True
status: test
use_vae: False
which_epoch: latest
z_dim: 256
----------------- End -------------------
QStandardPaths: XDG_RUNTIME_DIR not set, defaulting to '/tmp/runtime-root'
Network [SPADEGenerator] was created. Total number of parameters: 266.9 million. To
/home/user/anaconda3/envs/sean/lib/python3.6/site-packages/torch/nn/functional.py:1350: UserWarning: nn.functional.sigmoid is deprecated. Use torch.sigmoid instead.
warnings.warn("nn.functional.sigmoid is deprecated. Use torch.sigmoid instead.")
/home/user/anaconda3/envs/sean/lib/python3.6/site-packages/torch/nn/functional.py:1339: UserWarning: nn.functional.tanh is deprecated. Use torch.tanh instead.
warnings.warn("nn.functional.tanh is deprecated. Use torch.tanh instead.")
Traceback (most recent call last):
File "run_UI.py", line 566, in
ex = ExWindow(opt)
File "run_UI.py", line 35, in init
self.EX = Ex(opt)
File "run_UI.py", line 74, in init
self.init_screen()
File "run_UI.py", line 106, in init_screen
self.run_deep_model()
File "run_UI.py", line 127, in run_deep_model
qim = QImage(generated_img.data, generated_img.shape[1], generated_img.shape[0], QImage.Format_RGB888)
TypeError: arguments did not match any overloaded call:
QImage(): too many arguments
QImage(int, int, QImage.Format): argument 1 has unexpected type 'memoryview'
QImage(bytes, int, int, QImage.Format): argument 1 has unexpected type 'memoryview'
QImage(sip.voidptr, int, int, QImage.Format): argument 1 has unexpected type 'memoryview'
QImage(bytes, int, int, int, QImage.Format): argument 1 has unexpected type 'memoryview'
QImage(sip.voidptr, int, int, int, QImage.Format): argument 1 has unexpected type 'memoryview'
QImage(List[str]): argument 1 has unexpected type 'memoryview'
QImage(str, format: str = None): argument 1 has unexpected type 'memoryview'
QImage(QImage): argument 1 has unexpected type 'memoryview'
QImage(Any): too many arguments
I can't get the UI to work. Any ideas?
qt.qpa.plugin: Could not load the Qt platform plugin "xcb" in "/home/student/anaconda3/envs/sean_env/lib/python3.7/site-packages/cv2/qt/plugins" even though it was found.
This application failed to start because no Qt platform plugin could be initialized. Reinstalling the application may fix this problem.
any suggestion?
all the other pretrained model works fine!
currently using ubuntu server from VScode
Thanks you for sharing your amazing work. I'm new to pytorch and find your code clean and tought me a lot. I found no code of computing metrics such as SSIM/RMSE/PSNR/FID as mentioned in the paper and I wanna know how you implemented that. Would you please upload those code? Thanks!
Also, I'm running training.py SO SLOWLY on a single nvidia 2080ti with batch_size of 2. It's like a few hours not even one epoch finished. Do you have any idea?
Hi, thanks for your work!
I have a question about the SEAN module implementation detail. In the de-normalization process, why did you add an extra 1 to the gamma? i.e., out = normalized * (1 + gamma_final) + beta_final
.
Why 1+gamma here? According to Eq. (1) of the paper, it is gramma exactly.
Thanks for your interesting work, i am a little confused with this paragraph of codes, is that means each class in the semantic label map needs a linear layer? So, are there 150 linear layers in the ADE20k dataset??? Can you tell me how to implement your method in the ADE20k in details?
SEAN/models/networks/normalization.py
Line 209 in 04c7536
hello,
question1:did you try synthesis of 512*512 size ? Can the model solve synthesis mission of 512 size ?i trained 512 size model with celeba-HQ, synthesis images are not clear and not similar to input images, i just trained 3epoches,
question2: did you try IN instead of BN in generator?i found synthesis results of test datasets ,not very clear, lost some details,i guess using IN instead of BN may improve synthesis results.
Hello,
In SEAN paper, in Figure 4B, there is a ReLu in the shortcut. However in your code, there is no activation in the shortcut that is applied to ace_s
. Which one is used to generate the results demonstrated in the paper?
Thanks!
SEAN/models/networks/architecture.py
Line 90 in 04c7536
Hi, Thank you for your code.
I have question about the nonsense situation.
As you know, visualizer.display_current_results save function saves the result images. Maybe the result from generator 'G' outputs with latest weights learned.
However, the synthesized image from the inference mode by test.py, is being terrible even though train-set and test-set are same. It makes nonsense. Because I saw already the G can makes good synthesized images from same dataset. While 50~100 epoch, I can see always good synthesized images. And the weight file should get same result in inference mode. is it right?
is that anything that I missed?
Thank you.
Thank you very much for making the code accessible!
I was pleasantly surprised that the training command works exactly as in SPADE.
Instead of semantic image synthesis, I am interested in paired image to image translation tasks as in pix2pixHD (domain A -> domain B with paired images of the same name), Over in the SPADE repo the same question was asked multiple times, however, with no answer yet:
NVlabs/SPADE#46
NVlabs/SPADE#112
Is it possible to have a paired image2image translation with the SEAN model? If not, can you recommend some state of the art model that is more recent compared to pix2pixHD? pix2pixHD is nice, but even the SPADE authors found several improvements over it in their ablation study in the SPADE paper.
Thank you.
Traceback (most recent call last):
File "train.py", line 47, in
trainer.run_generator_one_step(data_i)
File "/d6295745ef534beab3ce2490bedcd8ab/lxy/inkpaint/SEAN/trainers/pix2pix_trainer.py", line 35, in run_generator_one_step
g_losses, generated = self.pix2pix_model(data, mode='generator')
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 541, in call
result = self.forward(*input, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/parallel/data_parallel.py", line 150, in forward
return self.module(*inputs[0], **kwargs[0])
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 541, in call
result = self.forward(*input, **kwargs)
File "/d6295745ef534beab3ce2490bedcd8ab/lxy/inkpaint/SEAN/models/pix2pix_model.py", line 45, in forward
input_semantics, real_image)
File "/d6295745ef534beab3ce2490bedcd8ab/lxy/inkpaint/SEAN/models/pix2pix_model.py", line 144, in compute_generator_loss
input_semantics, real_image, compute_kld_loss=self.opt.use_vae)
File "/d6295745ef534beab3ce2490bedcd8ab/lxy/inkpaint/SEAN/models/pix2pix_model.py", line 196, in generate_fake
fake_image = self.netG(input_semantics, real_image)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 541, in call
result = self.forward(*input, **kwargs)
File "/d6295745ef534beab3ce2490bedcd8ab/lxy/inkpaint/SEAN/models/networks/generator.py", line 84, in forward
x = self.head_0(x, seg, style_codes, obj_dic=obj_dic)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 541, in call
result = self.forward(*input, **kwargs)
File "/d6295745ef534beab3ce2490bedcd8ab/lxy/inkpaint/SEAN/models/networks/architecture.py", line 75, in forward
dx = self.ace_0(x, seg, style_codes, obj_dic)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 541, in call
result = self.forward(*input, **kwargs)
File "/d6295745ef534beab3ce2490bedcd8ab/lxy/inkpaint/SEAN/models/networks/normalization.py", line 157, in forward
middle_mu = F.relu(self.getattr('fc_mu' + str(j))(style_codes[i][j]))
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 585, in getattr
type(self).name, name))
AttributeError: 'ACE' object has no attribute 'fc_mu105'
I have meet this question, someone can help me?
hello, which pretrained segmentation model do you use to evaluate the mIOU and acc on CelebAMask-HQ dataset?
I use the mask images as label(background is 0,foreground is 255),but it can not work when "--label_nc"==2 or == 256.Only when I change the mask images(background is 0,foreground is 1) ,and set "--label_nc"==2,it works.I don't know why it can works.
Is it the problem of the custom datasets?
Great job !
Your work can control the style via the mask areas, I want to do some work about controlling the resolution via the mask area, could you please give me some advices?
Thanks!!!
I tried to run run_UI.py.
I can't get the interpolated results
First - I don't understand how to apply a style image on an Opened Image.
When I select one of the styles on the right side, the image, doesn't appear in the bottom part of the GUI window. (as it happened in the video that is attached).
I tried to press "mask" button, and style_linear_interpolation method runs but the saved images in style_interpolation folder, are all the same; it looks that self.obj_dic doesn't effect the generate_img. (even though odj_dic is updated according to the alpha and the styles in the loop)
Can you please show how exactly to use the UI (not the demo video, cause I can't get it from there)
Thanks in advance
Hi, while reading the code I noticed that SPADEResnetBlock.shortcut() doesn't apply an activation function between ACE and Conv.
Since it's different from Figure 4 (B) in the paper, could you explain the reason for it? Thank you in advance
CelebA-HQ/test/labels
how can i get these labels? what did u use as labels?
Hi,
Thanks a lot for uploading such a wonderful work. I have been trying to test this model, Not sure what I am doing wrong.
I downloaded the test dataset and the checkpoints you have uploaded, I am sure the paths are correct for the test command.
The reconstructed images that I am getting are almost same as the input images, I am really confused why.
This is the link to the result I am getting.
Hello, thanks for the great work.
I just wonder how did you implement region-wise pooling and SEAN block on ADE20k dataset.
In CelebA dataset, it might manageable via for-loop since the number of styles is 19 whereas not sure it is possible to the ADE20k since it has more than 100 styles (or classes).
So could you share some experiences about the implementation or training/testing time in this dataset?
Hello, my terminal hangs if I try to run the training code with more than 1 gpu. Do I need to write some additional code to support multiple GPUs? If so, where?
Greeting!
I want to ask a question about if you need the label mask of the style image in the testing phase. I notice that the label mask of the style image and the input layout may be very different, e.g. the samples in the ADE20K dataset. When encoding the style, it is natural to use a corresponding segmentation mask to do the "region-wise average pooling" for the style image.
Thank you.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.