search

NVIDIA-AI-IOT / torch2trt

An easy to use PyTorch to TensorRT converter
MIT License
4.6k stars 676 forks source link

AttributeError: 'list' object has no attribute '_trt' #433

Closed Fan-loewe closed 4 years ago

Fan-loewe commented 4 years ago

Hello I want to use torch2trt to convert a mobilenet according to https://github.com/Daniil-Osokin/lightweight-human-pose-estimation-3d-demo.pytorch

when I am running model_trt = torch2trt.torch2trt(model, [data]), it shows me the following errors:

Traceback (most recent call last): File "demo_1.py", line 69, in model_trt = torch2trt.torch2trt(net.net, [data], fp16_mode=True, max_workspace_size=1<<25) File "/home/aegis/.virtualenvs/py3cv4/lib/python3.6/site-packages/torch2trt-0.1.0-py3.6-linux-aarch64.egg/torch2trt/torch2trt.py", line 540, in torch2trt ctx.mark_outputs(outputs, output_names) File "/home/aegis/.virtualenvs/py3cv4/lib/python3.6/site-packages/torch2trt-0.1.0-py3.6-linux-aarch64.egg/torch2trt/torch2trt.py", line 406, in mark_outputs trt_tensor = torch_output._trt AttributeError: 'list' object has no attribute '_trt'

In my model, all used layers are already defined in the torch2trt.converters.activation. So the reason is different from the error 'Tensor' object has no attribute '_trt'. I would appreciate it if there is any idea.

PS: my model looks like the following:

PoseEstimationWithMobileNet( (model): Sequential( (0): Sequential( (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (1): Sequential( (0): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False) (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(32, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) ) (2): Sequential( (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=64, bias=False) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) ) (3): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=128, bias=False) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) ) (4): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=128, bias=False) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) ) (5): Sequential( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256, bias=False) (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) ) (6): Sequential( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256, bias=False) (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) ) (7): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(2, 2), dilation=(2, 2), groups=512, bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) ) (8): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=512, bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) ) (9): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=512, bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) ) (10): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=512, bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) ) (11): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=512, bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) ) ) (cpm): Cpm( (align): Sequential( (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1)) (1): ReLU(inplace=True) ) (trunk): Sequential( (0): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=128, bias=False) (1): ELU(alpha=1.0, inplace=True) (2): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (3): ELU(alpha=1.0, inplace=True) ) (1): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=128, bias=False) (1): ELU(alpha=1.0, inplace=True) (2): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (3): ELU(alpha=1.0, inplace=True) ) (2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=128, bias=False) (1): ELU(alpha=1.0, inplace=True) (2): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (3): ELU(alpha=1.0, inplace=True) ) ) (conv): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): ReLU(inplace=True) ) ) (initial_stage): InitialStage( (trunk): Sequential( (0): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): ReLU(inplace=True) ) (1): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): ReLU(inplace=True) ) (2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): ReLU(inplace=True) ) ) (heatmaps): Sequential( (0): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): ReLU(inplace=True) ) (1): Sequential( (0): Conv2d(512, 19, kernel_size=(1, 1), stride=(1, 1)) ) ) (pafs): Sequential( (0): Sequential( (0): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1)) (1): ReLU(inplace=True) ) (1): Sequential( (0): Conv2d(512, 38, kernel_size=(1, 1), stride=(1, 1)) ) ) ) (refinement_stages): ModuleList( (0): RefinementStage( (trunk): Sequential( (0): RefinementStageBlock( (initial): Sequential( (0): Conv2d(185, 128, kernel_size=(1, 1), stride=(1, 1)) (1): ReLU(inplace=True) ) (trunk): Sequential( (0): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (1): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(2, 2), dilation=(2, 2)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) ) (1): RefinementStageBlock( (initial): Sequential( (0): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1)) (1): ReLU(inplace=True) ) (trunk): Sequential( (0): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (1): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(2, 2), dilation=(2, 2)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) ) (2): RefinementStageBlock( (initial): Sequential( (0): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1)) (1): ReLU(inplace=True) ) (trunk): Sequential( (0): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (1): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(2, 2), dilation=(2, 2)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) ) (3): RefinementStageBlock( (initial): Sequential( (0): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1)) (1): ReLU(inplace=True) ) (trunk): Sequential( (0): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (1): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(2, 2), dilation=(2, 2)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) ) (4): RefinementStageBlock( (initial): Sequential( (0): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1)) (1): ReLU(inplace=True) ) (trunk): Sequential( (0): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (1): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(2, 2), dilation=(2, 2)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) ) ) (heatmaps): Sequential( (0): Sequential( (0): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1)) (1): ReLU(inplace=True) ) (1): Sequential( (0): Conv2d(128, 19, kernel_size=(1, 1), stride=(1, 1)) ) ) (pafs): Sequential( (0): Sequential( (0): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1)) (1): ReLU(inplace=True) ) (1): Sequential( (0): Conv2d(128, 38, kernel_size=(1, 1), stride=(1, 1)) ) ) ) ) (Pose3D): Pose3D( (stem): Sequential( (0): ResBlock( (bottleneck): Sequential( (0): Sequential( (0): Conv2d(185, 92, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(92, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (1): Sequential( (0): Conv2d(92, 92, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(92, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (2): Sequential( (0): Conv2d(92, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) (align): Sequential( (0): Conv2d(185, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) (1): ResBlock( (bottleneck): Sequential( (0): Sequential( (0): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (1): Sequential( (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (2): Sequential( (0): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) ) (2): ResBlock( (bottleneck): Sequential( (0): Sequential( (0): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (1): Sequential( (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (2): Sequential( (0): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) ) (3): ResBlock( (bottleneck): Sequential( (0): Sequential( (0): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (1): Sequential( (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (2): Sequential( (0): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) ) (4): ResBlock( (bottleneck): Sequential( (0): Sequential( (0): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (1): Sequential( (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (2): Sequential( (0): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) ) ) (prediction): RefinementStageLight( (trunk): Sequential( (0): RefinementStageBlock( (initial): Sequential( (0): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1)) (1): ReLU(inplace=True) ) (trunk): Sequential( (0): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (1): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(2, 2), dilation=(2, 2)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) ) (1): RefinementStageBlock( (initial): Sequential( (0): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1)) (1): ReLU(inplace=True) ) (trunk): Sequential( (0): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (1): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(2, 2), dilation=(2, 2)) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) ) ) ) (feature_maps): Sequential( (0): Sequential( (0): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1)) (1): ReLU(inplace=True) ) (1): Sequential( (0): Conv2d(128, 57, kernel_size=(1, 1), stride=(1, 1)) ) ) ) ) )

Thanks a lot for the help!

austinmw commented 3 years ago

@Fan-loewe did you solve this?

Zhangppppp commented 2 years ago

@austinmw did you solve this?