Created
February 23, 2022 11:45
-
-
Save botcs/5b2196fddbc327eb2b27dccdcae794b1 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
bottom_up_features, expt_flops, real_flops, gate_tensor = self.backbone(x, step_rate) | |
File "/data/engs-tvg-depth/csbotos/miniconda3/envs/dyndet/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl | |
return forward_call(*input, **kwargs) | |
File "/home/csbotos/github/fbscript/DynamicRouting/./dl_lib/modeling/dynamic_arch/dynamic_backbone.py", line 300, in forward | |
self.all_cell_list[layer_index][_cell_index]( | |
File "/data/engs-tvg-depth/csbotos/miniconda3/envs/dyndet/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl | |
return forward_call(*input, **kwargs) | |
File "/home/csbotos/github/fbscript/DynamicRouting/./dl_lib/modeling/dynamic_arch/dynamic_cell.py", line 273, in forward | |
result_list[2].append(h_l_down * gate_weights_beta_down) | |
(function _print_stack) | |
[02/23 11:40:22 dl_lib.engine.hooks]: Total training time: 0:00:33 (0:00:00 on hooks) | |
Traceback (most recent call last): | |
File "/home/csbotos/github/fbscript/DynamicRouting/tools/train_net.py", line 174, in <module> | |
launch( | |
File "/home/csbotos/github/fbscript/DynamicRouting/./dl_lib/engine/launch.py", line 51, in launch | |
mp.spawn( | |
File "/data/engs-tvg-depth/csbotos/miniconda3/envs/dyndet/lib/python3.9/site-packages/torch/multiprocessing/spawn.py", line 230, in spawn | |
return start_processes(fn, args, nprocs, join, daemon, start_method='spawn') | |
File "/data/engs-tvg-depth/csbotos/miniconda3/envs/dyndet/lib/python3.9/site-packages/torch/multiprocessing/spawn.py", line 188, in start_processes | |
while not context.join(): | |
File "/data/engs-tvg-depth/csbotos/miniconda3/envs/dyndet/lib/python3.9/site-packages/torch/multiprocessing/spawn.py", line 150, in join | |
raise ProcessRaisedException(msg, error_index, failed_process.pid) | |
torch.multiprocessing.spawn.ProcessRaisedException: | |
-- Process 2 terminated with the following error: | |
Traceback (most recent call last): | |
File "/data/engs-tvg-depth/csbotos/miniconda3/envs/dyndet/lib/python3.9/site-packages/torch/multiprocessing/spawn.py", line 59, in _wrap | |
fn(i, *args) | |
File "/home/csbotos/github/fbscript/DynamicRouting/./dl_lib/engine/launch.py", line 93, in _distributed_worker | |
main_func(*args) | |
File "/home/csbotos/github/fbscript/DynamicRouting/tools/train_net.py", line 161, in main | |
res = trainer.train() | |
File "/home/csbotos/github/fbscript/DynamicRouting/./dl_lib/engine/custom.py", line 204, in train | |
super().train(self.start_iter, self.max_iter) | |
File "/home/csbotos/github/fbscript/DynamicRouting/./dl_lib/engine/train_loop.py", line 136, in train | |
self.run_step() | |
File "/home/csbotos/github/fbscript/DynamicRouting/./dl_lib/engine/train_loop.py", line 517, in run_step | |
losses.backward() | |
File "/data/engs-tvg-depth/csbotos/miniconda3/envs/dyndet/lib/python3.9/site-packages/torch/_tensor.py", line 307, in backward | |
torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs) | |
File "/data/engs-tvg-depth/csbotos/miniconda3/envs/dyndet/lib/python3.9/site-packages/torch/autograd/__init__.py", line 154, in backward | |
Variable._execution_engine.run_backward( | |
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [1, 1, 1, 1]], which is output 0 of AsStridedBackward0, is at version 2; expected version 0 instead. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later. Good luck!bottom_up_features, expt_flops, real_flops, gate_tensor = self.backbone(x, step_rate) | |
File "/data/engs-tvg-depth/csbotos/miniconda3/envs/dyndet/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl | |
return forward_call(*input, **kwargs) | |
File "/home/csbotos/github/fbscript/DynamicRouting/./dl_lib/modeling/dynamic_arch/dynamic_backbone.py", line 300, in forward | |
self.all_cell_list[layer_index][_cell_index]( | |
File "/data/engs-tvg-depth/csbotos/miniconda3/envs/dyndet/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl | |
return forward_call(*input, **kwargs) | |
File "/home/csbotos/github/fbscript/DynamicRouting/./dl_lib/modeling/dynamic_arch/dynamic_cell.py", line 273, in forward | |
result_list[2].append(h_l_down * gate_weights_beta_down) | |
(function _print_stack) | |
[02/23 11:40:22 dl_lib.engine.hooks]: Total training time: 0:00:33 (0:00:00 on hooks) | |
Traceback (most recent call last): | |
File "/home/csbotos/github/fbscript/DynamicRouting/tools/train_net.py", line 174, in <module> | |
launch( | |
File "/home/csbotos/github/fbscript/DynamicRouting/./dl_lib/engine/launch.py", line 51, in launch | |
mp.spawn( | |
File "/data/engs-tvg-depth/csbotos/miniconda3/envs/dyndet/lib/python3.9/site-packages/torch/multiprocessing/spawn.py", line 230, in spawn | |
return start_processes(fn, args, nprocs, join, daemon, start_method='spawn') | |
File "/data/engs-tvg-depth/csbotos/miniconda3/envs/dyndet/lib/python3.9/site-packages/torch/multiprocessing/spawn.py", line 188, in start_processes | |
while not context.join(): | |
File "/data/engs-tvg-depth/csbotos/miniconda3/envs/dyndet/lib/python3.9/site-packages/torch/multiprocessing/spawn.py", line 150, in join | |
raise ProcessRaisedException(msg, error_index, failed_process.pid) | |
torch.multiprocessing.spawn.ProcessRaisedException: | |
-- Process 2 terminated with the following error: | |
Traceback (most recent call last): | |
File "/data/engs-tvg-depth/csbotos/miniconda3/envs/dyndet/lib/python3.9/site-packages/torch/multiprocessing/spawn.py", line 59, in _wrap | |
fn(i, *args) | |
File "/home/csbotos/github/fbscript/DynamicRouting/./dl_lib/engine/launch.py", line 93, in _distributed_worker | |
main_func(*args) | |
File "/home/csbotos/github/fbscript/DynamicRouting/tools/train_net.py", line 161, in main | |
res = trainer.train() | |
File "/home/csbotos/github/fbscript/DynamicRouting/./dl_lib/engine/custom.py", line 204, in train | |
super().train(self.start_iter, self.max_iter) | |
File "/home/csbotos/github/fbscript/DynamicRouting/./dl_lib/engine/train_loop.py", line 136, in train | |
self.run_step() | |
File "/home/csbotos/github/fbscript/DynamicRouting/./dl_lib/engine/train_loop.py", line 517, in run_step | |
losses.backward() | |
File "/data/engs-tvg-depth/csbotos/miniconda3/envs/dyndet/lib/python3.9/site-packages/torch/_tensor.py", line 307, in backward | |
torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs) | |
File "/data/engs-tvg-depth/csbotos/miniconda3/envs/dyndet/lib/python3.9/site-packages/torch/autograd/__init__.py", line 154, in backward | |
Variable._execution_engine.run_backward( | |
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [1, 1, 1, 1]], which is output 0 of AsStridedBackward0, is at version 2; expected version 0 instead. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later. Good luck! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment