Issue with SV2LSTG model training

[bingood]

I'm encountering an error when training the SV2LSTG temporal model, while the single-frame LG-CVS model works correctly.

The single-frame LG-CVS model training works fine:

mim train mmdet configs/models/faster_rcnn/lg_ds_faster_rcnn.py

But when I try to train the SV2LSTG model:

mim train mmdet configs/temporal_models/faster_rcnn/sv2lstg_faster_rcnn_10.py

I get this error:

Traceback (most recent call last): File "/home/bingood/miniconda3/envs/latentgraph/lib/python3.8/site-packages/mmdet/.mim/tools/train.py", line 121, in <module> main() File "/home/bingood/miniconda3/envs/latentgraph/lib/python3.8/site-packages/mmdet/.mim/tools/train.py", line 117, in main runner.train() File "/home/bingood/miniconda3/envs/latentgraph/lib/python3.8/site-packages/mmengine/runner/runner.py", line 1721, in train model = self.train_loop.run() # type: ignore File "/home/bingood/miniconda3/envs/latentgraph/lib/python3.8/site-packages/mmengine/runner/loops.py", line 278, in run self.run_iter(data_batch) File "/home/bingood/miniconda3/envs/latentgraph/lib/python3.8/site-packages/mmengine/runner/loops.py", line 301, in run_iter outputs = self.runner.model.train_step( File "/home/bingood/miniconda3/envs/latentgraph/lib/python3.8/site-packages/mmengine/model/base_model/base_model.py", line 114, in train_step losses = self._run_forward(data, mode='loss') # type: ignore File "/home/bingood/miniconda3/envs/latentgraph/lib/python3.8/site-packages/mmengine/model/base_model/base_model.py", line 340, in _run_forward results = self(**data, mode=mode) File "/home/bingood/miniconda3/envs/latentgraph/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "/home/bingood/miniconda3/envs/latentgraph/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) File "/home/bingood/miniconda3/envs/latentgraph/lib/python3.8/site-packages/mmdet/models/detectors/base.py", line 92, in forward return self.loss(inputs, data_samples) File "/home/bingood/SurgLatentGraph/model/sv2lstg.py", line 110, in loss feats, graphs, clip_results, _ = self.extract_feat(batch_inputs, filtered_batch_data_samples, losses) File "/home/bingood/SurgLatentGraph/model/sv2lstg.py", line 658, in extract_feat feats, graphs, detached_results, results, _, _ = self.lg_detector.extract_lg( ValueError: not enough values to unpack (expected 6, got 5) Traceback (most recent call last): File "/home/bingood/miniconda3/envs/latentgraph/bin/mim", line 8, in <module> sys.exit(cli()) File "/home/bingood/miniconda3/envs/latentgraph/lib/python3.8/site-packages/click/core.py", line 1161, in __call__ return self.main(*args, **kwargs) File "/home/bingood/miniconda3/envs/latentgraph/lib/python3.8/site-packages/click/core.py", line 1082, in main rv = self.invoke(ctx) File "/home/bingood/miniconda3/envs/latentgraph/lib/python3.8/site-packages/click/core.py", line 1697, in invoke return _process_result(sub_ctx.command.invoke(sub_ctx)) File "/home/bingood/miniconda3/envs/latentgraph/lib/python3.8/site-packages/click/core.py", line 1443, in invoke return ctx.invoke(self.callback, **ctx.params) File "/home/bingood/miniconda3/envs/latentgraph/lib/python3.8/site-packages/click/core.py", line 788, in invoke return __callback(*args, **kwargs) File "/home/bingood/miniconda3/envs/latentgraph/lib/python3.8/site-packages/mim/commands/train.py", line 100, in cli is_success, msg = train( File "/home/bingood/miniconda3/envs/latentgraph/lib/python3.8/site-packages/mim/commands/train.py", line 261, in train ret = subprocess.check_call( File "/home/bingood/miniconda3/envs/latentgraph/lib/python3.8/subprocess.py", line 364, in check_call raise CalledProcessError(retcode, cmd) subprocess.CalledProcessError: Command '['/home/bingood/miniconda3/envs/latentgraph/bin/python', '/home/bingood/miniconda3/envs/latentgraph/lib/python3.8/site-packages/mmdet/.mim/tools/train.py', 'configs/temporal_models/faster_rcnn/sv2lstg_faster_rcnn_10.py', '--launcher', 'none']' returned non-zero exit status 1.

The error seems to be related to a mismatch in the number of values returned from self.lg_detector.extract_lg() - the code expects 6 values but only receives 5.

Is there something I'm missing in the setup for the temporal models?

[amanzanorodriguez]

Did you find how to solve it? I'm facing the same error... thanks!

[adit98]

Hi,

Apologies for the delay - there was a small issue due to a merge conflict, it should be resolved now.