CPU FLAG ISSUE - Githubissues

justmaulik commented 4 years ago

When Using --gpu_ids =-1 for cpu it gives below error but works smooth with gpu can anyone please give some highlight on this as i need to get the onnx export and then use with onnx on cpu.

Execution Command

!python test.py --dataroot /content/drive/My\ Drive/cars --name cars --netG global  --gpu_ids '-1' --resize_or_crop none --label_nc 0 --no_instance --how_many 10 --checkpoints_dir /content/drive/My\ Drive/Pix2pixtraining/pix2pixHD/checkpoints/ --which_epoch 100

------------ Options -------------
aspect_ratio: 1.0
batchSize: 1
checkpoints_dir: /content/drive/My Drive/Pix2pixtraining/pix2pixHD/checkpoints/
cluster_path: features_clustered_010.npy
data_type: 32
dataroot: /content/drive/My Drive/cars
display_winsize: 512
engine: None
export_onnx: None
feat_num: 3
fineSize: 512
fp16: False
gpu_ids: []
how_many: 10
input_nc: 3
instance_feat: False
isTrain: False
label_feat: False
label_nc: 0
loadSize: 1024
load_features: False
local_rank: 0
max_dataset_size: inf
model: pix2pixHD
nThreads: 2
n_blocks_global: 9
n_blocks_local: 3
n_clusters: 10
n_downsample_E: 4
n_downsample_global: 4
n_local_enhancers: 1
name: cars
nef: 16
netG: global
ngf: 64
niter_fix_global: 0
no_flip: False
no_instance: True
norm: instance
ntest: inf
onnx: None
output_nc: 3
phase: test
resize_or_crop: none
results_dir: ./results/
serial_batches: False
tf_log: False
use_dropout: False
use_encoded_image: False
verbose: False
which_epoch: 100
-------------- End ----------------
CustomDatasetDataLoader
dataset [AlignedDataset] was created
GlobalGenerator(
  (model): Sequential(
    (0): ReflectionPad2d((3, 3, 3, 3))
    (1): Conv2d(3, 64, kernel_size=(7, 7), stride=(1, 1))
    (2): InstanceNorm2d(64, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
    (3): ReLU(inplace=True)
    (4): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
    (5): InstanceNorm2d(128, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
    (6): ReLU(inplace=True)
    (7): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
    (8): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
    (9): ReLU(inplace=True)
    (10): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
    (11): InstanceNorm2d(512, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
    (12): ReLU(inplace=True)
    (13): Conv2d(512, 1024, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
    (14): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
    (15): ReLU(inplace=True)
    (16): ResnetBlock(
      (conv_block): Sequential(
        (0): ReflectionPad2d((1, 1, 1, 1))
        (1): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
        (2): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
        (3): ReLU(inplace=True)
        (4): ReflectionPad2d((1, 1, 1, 1))
        (5): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
        (6): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
      )
    )
    (17): ResnetBlock(
      (conv_block): Sequential(
        (0): ReflectionPad2d((1, 1, 1, 1))
        (1): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
        (2): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
        (3): ReLU(inplace=True)
        (4): ReflectionPad2d((1, 1, 1, 1))
        (5): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
        (6): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
      )
    )
    (18): ResnetBlock(
      (conv_block): Sequential(
        (0): ReflectionPad2d((1, 1, 1, 1))
        (1): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
        (2): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
        (3): ReLU(inplace=True)
        (4): ReflectionPad2d((1, 1, 1, 1))
        (5): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
        (6): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
      )
    )
    (19): ResnetBlock(
      (conv_block): Sequential(
        (0): ReflectionPad2d((1, 1, 1, 1))
        (1): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
        (2): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
        (3): ReLU(inplace=True)
        (4): ReflectionPad2d((1, 1, 1, 1))
        (5): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
        (6): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
      )
    )
    (20): ResnetBlock(
      (conv_block): Sequential(
        (0): ReflectionPad2d((1, 1, 1, 1))
        (1): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
        (2): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
        (3): ReLU(inplace=True)
        (4): ReflectionPad2d((1, 1, 1, 1))
        (5): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
        (6): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
      )
    )
    (21): ResnetBlock(
      (conv_block): Sequential(
        (0): ReflectionPad2d((1, 1, 1, 1))
        (1): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
        (2): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
        (3): ReLU(inplace=True)
        (4): ReflectionPad2d((1, 1, 1, 1))
        (5): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
        (6): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
      )
    )
    (22): ResnetBlock(
      (conv_block): Sequential(
        (0): ReflectionPad2d((1, 1, 1, 1))
        (1): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
        (2): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
        (3): ReLU(inplace=True)
        (4): ReflectionPad2d((1, 1, 1, 1))
        (5): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
        (6): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
      )
    )
    (23): ResnetBlock(
      (conv_block): Sequential(
        (0): ReflectionPad2d((1, 1, 1, 1))
        (1): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
        (2): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
        (3): ReLU(inplace=True)
        (4): ReflectionPad2d((1, 1, 1, 1))
        (5): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
        (6): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
      )
    )
    (24): ResnetBlock(
      (conv_block): Sequential(
        (0): ReflectionPad2d((1, 1, 1, 1))
        (1): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
        (2): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
        (3): ReLU(inplace=True)
        (4): ReflectionPad2d((1, 1, 1, 1))
        (5): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1))
        (6): InstanceNorm2d(1024, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
      )
    )
    (25): ConvTranspose2d(1024, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), output_padding=(1, 1))
    (26): InstanceNorm2d(512, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
    (27): ReLU(inplace=True)
    (28): ConvTranspose2d(512, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), output_padding=(1, 1))
    (29): InstanceNorm2d(256, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
    (30): ReLU(inplace=True)
    (31): ConvTranspose2d(256, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), output_padding=(1, 1))
    (32): InstanceNorm2d(128, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
    (33): ReLU(inplace=True)
    (34): ConvTranspose2d(128, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), output_padding=(1, 1))
    (35): InstanceNorm2d(64, eps=1e-05, momentum=0.1, affine=False, track_running_stats=False)
    (36): ReLU(inplace=True)
    (37): ReflectionPad2d((3, 3, 3, 3))
    (38): Conv2d(64, 3, kernel_size=(7, 7), stride=(1, 1))
    (39): Tanh()
  )
)
/content/pix2pixHD/models/pix2pixHD_model.py:128: UserWarning: volatile was removed and now has no effect. Use `with torch.no_grad():` instead.
  input_label = Variable(input_label, volatile=infer)
Traceback (most recent call last):
  File "test.py", line 59, in <module>
    generated = model.inference(data['label'], data['inst'], data['image'])
  File "/content/pix2pixHD/models/pix2pixHD_model.py", line 216, in inference
    fake_image = self.netG.forward(input_concat)
  File "/content/pix2pixHD/models/networks.py", line 211, in forward
    return self.model(input)             
  File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 722, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/container.py", line 117, in forward
    input = module(input)
  File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 722, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/conv.py", line 419, in forward
    return self._conv_forward(input, self.weight)
  File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/conv.py", line 416, in _conv_forward
    self.padding, self.dilation, self.groups)
RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same

WayneCho commented 4 years ago

I have the same issue and I solve this by adding a simple if...else.. statement to all the .cude parameters in the pix2pixHD_model.py. For example, replace inst_map = inst_map.data.cuda() by if not self.gpu_ids: inst_map = inst_map.data else: inst_map = inst_map.data.cuda() .

Viktor2k commented 3 years ago

Another alternative that in my opinion is cleaner is to add an instance variable called device in BaseModel.initialize like this

self.device = torch.device("cuda:0" if torch.cuda.is_available() and self.gpu_ids else "cpu")

That allows you to simply replace all occurrences of .cuda() with .to(device) in pix2pixHD_model.py. No need to wrap in if/else 🙌🏼

jv78v commented 1 year ago

I am also facing the same issue. And I also try this methods but it didn't work for me. Can you help me with the solution of train model on cpu.

zhangxiaojuan66 commented 1 year ago

你好，邮件已收到，祝你万事如意，生活愉快！

NVIDIA / pix2pixHD

CPU FLAG ISSUE #232