windows10 python3.7 CUDA80 pytorch1.0.0
2022.6.5 记录
TRAINING:
python main.py --exp_name=dgcnn_1024 --model=dgcnn --num_points=1024 --k=20 --use_sgd=True
$ python main.py --exp_name=dgcnn_1024 --model=dgcnn --num_points=1024 --k=20 --use_sgd=True
Namespace(batch_size=32, dataset='modelnet40', dropout=0.5, emb_dims=1024, epochs=250, eval=False, exp_name='dgcnn_1024', k=20, lr=0.001, model='dgcnn', model_path='', momentum=0.9, no_cuda=False, num_points=1024, seed=1, test_batch_size=16, use_sgd=True)
Using GPU : 0 from 1 devices
DGCNN(
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(bn3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(bn4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(bn5): BatchNorm1d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv1): Sequential(
(0): Conv2d(6, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.2)
)
(conv2): Sequential(
(0): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.2)
)
(conv3): Sequential(
(0): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.2)
)
(conv4): Sequential(
(0): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.2)
)
(conv5): Sequential(
(0): Conv1d(512, 1024, kernel_size=(1,), stride=(1,), bias=False)
(1): BatchNorm1d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.2)
)
(linear1): Linear(in_features=2048, out_features=512, bias=False)
(bn6): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(dp1): Dropout(p=0.5)
(linear2): Linear(in_features=512, out_features=256, bias=True)
(bn7): BatchNorm1d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(dp2): Dropout(p=0.5)
(linear3): Linear(in_features=256, out_features=40, bias=True)
)
Let's use 1 GPUs!
Use SGD
Traceback (most recent call last):
File "main.py", line 225, in
train(args, io)
File "main.py", line 86, in train
logits = model(data)
File "E:anacondaenvsPyTorchlibsite-packagestorchnnmodulesmodule.py", line 489, in __call__
result = self.forward(*input, **kwargs)
File "E:anacondaenvsPyTorchlibsite-packagestorchnnparalleldata_parallel.py", line 141, in forward
return self.module(*inputs[0], **kwargs[0])
File "E:anacondaenvsPyTorchlibsite-packagestorchnnmodulesmodule.py", line 489, in __call__
result = self.forward(*input, **kwargs)
File "D:▒▒▒▒Pointsdgcnn-masterpytorchmodel.py", line 137, in forward
x = get_graph_feature(x3, k=self.k)
File "D:▒▒▒▒Pointsdgcnn-masterpytorchmodel.py", line 51, in get_graph_feature
feature = torch.cat((feature-x, x), dim=3).permute(0, 3, 1, 2).contiguous()
RuntimeError: CUDA out of memory. Tried to allocate 320.00 MiB (GPU 0; 4.00 GiB total capacity; 2.97 GiB already allocated; 69.76 MiB free; 17.82 MiB cached)
