how to specify the traing param lr and lr_step about centernet HOT 5 CLOSED

Hi,

1. The program use progress to dynamically print logs to the screen. If it does not work, you can set --print_iters 1 to use the standard python print function. The log, as well as a tensorboard log, is also saved to exp/ctdet/$exp_id.
2. The learning rate 5e-4 is set for batchsize 128, you will need to linearly scale it to your batchsize (in your case, 5e-4 * 47 / 128).
3. It is recommended to test with fewer epochs first, e.g., --num_epochs 70 --lr_step 60.
4. The "best" model (with the lowest loss) is usually not the best one with the highest AP.

from centernet.

@xingyizhou thank you.

from centernet.

@xingyizhou The learning rate 5e-4 is set for batchsize 128 on 8 GPUs (batchsize 16 on each GPU). If I use 2 GPUs and batchsize is 40, should I set lr = 5e-4 * (40 / 2) / (128 / 8) ?

from centernet.

Anybody knows why?
The "best" model (with the lowest loss) is usually not the best one with the highest AP.
Many thanks!

from centernet.

the program runs using nohup, and i can not see the loss and progress.

I can see the loss with this cmd:
nohup python main.py ctdet --exp_id coco_dla --batch_size 16 --master_batch 1 --lr 6.25e-5 -
-gpus 4,0 --print_iter 1 --num_workers 0 >../trian_log.json 2>&1 &

from centernet.