UniAD

UniAD copied to clipboard

messi bailando

1

meesi dancing

endika605

It seems that multi batches is not supported now. I set samples_per_gpu to 2, but it went wrong. Did I set the wrong parameter?

ustcjasonliu

Function _load_future_anns_plan is not defined

2

I was going through the code, and I found following lines in loading.py. But I couldn't find the definition of the function. So I wondered whether this is important or...

sunstarchan

GPU memory is not released after training process is stopped

1

Hi, thank you for sharing your work ^^ I have a problem that: ### The GPU memory is not released if I forcibly stop the training process (by using Ctrl-C...

thunguyenth

WARNING!!!!, Only can be used for obtain inference speed!!!! load checkpoint from local path: ./ckpts/uniad_base_track_map.pth The model and loaded state dict do not match exactly

1

While I'm in Evaluation Example run this line of code: . /tools/uniad_dist_eval.sh . /projects/configs/stage1_track_map/base_track_map.py . /ckpts/uniad_base_track_map.pth 8 Error when running this line of code Can anyone help me? WARNING!!!!, Only...

Andrea010725

Error during train stage2_e2e

2

I used 6 A100 to train the model of stage2_e2e. After completing the fourth epoch, an error occurred.Error as shown below。   This mistake is easy to repeat. Please...

DeepBehavier

Question: how can i export onnx ?

6

wangqiuya

Have you deployed this model to edge devices, and which level hardware is needed?

LebronRemonJames

If I want to extent the forecast time, which parameter do I need to modify?

CCarlossss

AssertionError: MMCV==1.4.0 is used but incompatible. Please install mmcv>=2.0.0rc4, <2.2.0.

1

### **Please solve the MMCV version problem, thank you.** I am also considering the issue of the giteckout version. ### **ERROR** ``` nohup: ignoring input /root/anaconda3/envs/hhhhh/lib/python3.8/site-packages/torch/distributed/launch.py:178: FutureWarning: The module torch.distributed.launch...

DDEONSIK