cscribano / cerberus Goto Github PK
View Code? Open in Web Editor NEWSimple and Effective All-In-One Automotive Perception Model with Multi Task Learning
Simple and Effective All-In-One Automotive Perception Model with Multi Task Learning
Traceback (most recent call last):
File "compressor.py", line 260, in
trainer_run()
File "compressor.py", line 211, in trainer_run
trainer.fit(model, train_loader, val_loader)
File "/home/inferno/anaconda3/envs/cerberus/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 768, in fit
self._call_and_handle_interrupt(
File "/home/inferno/anaconda3/envs/cerberus/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 721, in _call_and_handle_interrupt
return trainer_fn(*args, **kwargs)
File "/home/inferno/anaconda3/envs/cerberus/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 809, in _fit_impl
results = self._run(model, ckpt_path=self.ckpt_path)
File "/home/inferno/anaconda3/envs/cerberus/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 1234, in _run
results = self._run_stage()
File "/home/inferno/anaconda3/envs/cerberus/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 1321, in _run_stage
return self._run_train()
File "/home/inferno/anaconda3/envs/cerberus/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 1343, in _run_train
self._run_sanity_check()
File "/home/inferno/anaconda3/envs/cerberus/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 1411, in _run_sanity_check
val_loop.run()
File "/home/inferno/anaconda3/envs/cerberus/lib/python3.8/site-packages/pytorch_lightning/loops/base.py", line 204, in run
self.advance(*args, **kwargs)
File "/home/inferno/anaconda3/envs/cerberus/lib/python3.8/site-packages/pytorch_lightning/loops/dataloader/evaluation_loop.py", line 154, in advance
dl_outputs = self.epoch_loop.run(self._data_fetcher, dl_max_batches, kwargs)
File "/home/inferno/anaconda3/envs/cerberus/lib/python3.8/site-packages/pytorch_lightning/loops/base.py", line 204, in run
self.advance(*args, **kwargs)
File "/home/inferno/anaconda3/envs/cerberus/lib/python3.8/site-packages/pytorch_lightning/loops/epoch/evaluation_epoch_loop.py", line 127, in advance
output = self._evaluation_step(**kwargs)
File "/home/inferno/anaconda3/envs/cerberus/lib/python3.8/site-packages/pytorch_lightning/loops/epoch/evaluation_epoch_loop.py", line 222, in _evaluation_step
output = self.trainer._call_strategy_hook("validation_step", *kwargs.values())
File "/home/inferno/anaconda3/envs/cerberus/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 1763, in _call_strategy_hook
output = fn(*args, **kwargs)
File "/home/inferno/anaconda3/envs/cerberus/lib/python3.8/site-packages/pytorch_lightning/strategies/strategy.py", line 344, in validation_step
return self.model.validation_step(*args, **kwargs)
File "compressor.py", line 118, in validation_step
preds = self.forward(img)
File "compressor.py", line 92, in forward
pred = self.backbone(img)
File "/home/inferno/anaconda3/envs/cerberus/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/inferno/Downloads/loconav/CERBERUS/models/cerberus.py", line 78, in forward
scn_out = self.head_scn(small, argmax=inference)
File "/home/inferno/anaconda3/envs/cerberus/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/inferno/Downloads/loconav/CERBERUS/models/heads.py", line 96, in forward
w_pred, s_pred, t_pred = torch.split(x, self.cls_splits, 1)
File "/home/inferno/anaconda3/envs/cerberus/lib/python3.8/site-packages/torch/functional.py", line 189, in split
return tensor.split(split_size_or_sections, dim)
File "/home/inferno/anaconda3/envs/cerberus/lib/python3.8/site-packages/torch/_tensor.py", line 611, in split
return super(Tensor, self).split_with_sizes(split_size, dim)
RuntimeError: start (14) + length (4) exceeds dimension size (16).
Thank you for the author's contribution. In this framework, It was very easy and effective to use the BDD100K open dataset for training. Therefore, I would like to further fine-tune the model using actual experimental scene data. The annotation work for object detection and scene classification can be done easily in the format of BDD100K.
However, I would like to ask for the author's suggestion on how to annotate road lines for lane detection in a proper way?
Hi, looking for a quantized model if you can make avaialble
Traceback (most recent call last):
File "inference/run.py", line 19, in
from dataset.utils.transforms import Preproc
ModuleNotFoundError: No module named 'dataset'
Hi cant find the pth files in the link,kindly fix
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.