vobecant

Thank you very much for your response! Given that you provide also a list of Waymo scenes for training, does it mean that you have trained a model using the...

Thank you for your reply. I suppose that the reported results are for the `standard AP` (11 points) and not for the new `AP_40` with 40 points, right? Also, the...

@sparro12, `faster.py` does just the detection. You then need to run `src/tools/kitti-object-eval-python/evaluate.py` for the evaluation.

I have the same problem.

I trained the network using the following setup ``` MODEL: WEIGHT: "catalog://ImageNetPretrained/DLA34" INPUT: FLIP_PROB_TRAIN: 0.5 SHIFT_SCALE_PROB_TRAIN: 0.3 OUTPUT_DIR: "./tools/logs_trainOnTrain_120ep" DATASETS: DETECT_CLASSES: ("Car", "Cyclist", "Pedestrian") TRAIN: ("kitti_train",) TEST: ("kitti_train",) TRAIN_SPLIT: "train"...

@nikhil-nakhate I didn't make any additional changes. I run this exact command: ``` now=$(date +"%Y%m%d_%H%M%S") EXPNAME=SMOKE_trainOnTrain_120ep_${now} JOB_FILE=./jobs/${EXPNAME}.job g=4 NUMCPUS=16 CONFIG_FILE=/path/to/SMOKE/configs/smoke_trainOnTrain_testOnVal_120ep.yaml python tools/plain_train_net.py --num-gpus 4 --config-file ${CONFIG_FILE} ``` To get the...

I would be interested in this as well.

> Actually, I just found the bug. I was using resnet architecture, that I modified by myself instead of using the resnet architecture from this repo. My bad. After correcting...

@wang-xinyu You are welcome. I am glad that it helps.

Hi, I am also interested whether you are going to share the trained model. It would be trully useful. Thanks in advance!