second.pytorch

second.pytorch copied to clipboard

config files - need explanation (fhd vs largea vs lowa vs mhead vs mida), differences between config files, how to choose, etc.

1

Can somebody explain the naming of the config files? I gather `all` means detects all objects (car, pedestrian, cyclist, etc.) vs `car` means only detects cars. Also I gather `pp`...

CDahmsSpireon

Segmentation fault (core dumped)

4

**System:** Ubuntu 18.04.4 LTS Cuda 10.2 python3.6 I'm not using any conda env When I run this: `python3 create_data.py kitti_data_prep --data_path=KITTI_DATASET_ROOT ` **I get this on my console:** ``` /home//.local/lib/python3.6/site-packages/numba/cuda/envvars.py:17:...

nanaBaah

RuntimeError: cannot perform reduction function max on tensor with no elements (Custom Dataset)

2

Hi, I would like to ask about the error. I trained a custom dataset in kitti format. The training goes well, however when the eval result start processing, the error...

StephenEkaputra

train.py following ''has no field named "fmodel"

11

Hi. I try to train.py with cmd: python3 train.py train --config_path=/root/second.pytorch/second/configs/car.config --model_dir=/root/model/second_model but encountered following error message Traceback (most recent call last): File "train.py", line 660, in fire.Fire() File "/root/anaconda3/envs/py34/lib/python3.6/site-packages/fire/core.py",...

swordzxz

google.protobuf.text_format.ParseError: 10:5 : Message type "second.protos.VoxelNet" has no field named "num_class".

6

Traceback (most recent call last): File "./pytorch/train.py", line 647, in fire.Fire() File "/home/jin/anaconda3/lib/python3.6/site-packages/fire/core.py", line 138, in Fire component_trace = _Fire(component, args, parsed_flag_args, context, name) File "/home/jin/anaconda3/lib/python3.6/site-packages/fire/core.py", line 468, in _Fire...

Jin123learn

hi, I am really confused about the max_num_epochs=160 and steps=30950 in yourt car.fhd.config. It seems that I train the code following the steps=3.950 but not max_num_epochs. So how can I...

mc171819

Low performance in multiclass detection

2

Hi, I wanted to train a pointpillar model to classify 3 class and I modified the configure as: model: { second: { voxel_generator { point_cloud_range : [0, -39.68, -3, 69.12,...

smell-fishy

Error on evaluating on pretrained car_fhd

18

Hi, I'm getting the following error on trying to evaluate the model using the pretrained weights in `car_fhd`. If anyone has a workaround, kindly let me know. Thanks! ``` python...

themousepotato

Hello, blogger. I want to ask. I followed the steps. Others are okay. When the trian step , the pc show : no such directiory ""/KITTI_DATASER_ROOT/training/ver..._reduce/xxxxxx.bin" and xxxxxx.bin is always...

shell-fpga

Bounding boxes are not coming accurate

8

Hi, I'm getting the following image as the result on visualizing 3D bounding boxes after evaluation using pretrained models. I've used `car_lite`. I've evaluated the model on the training set...

themousepotato