How does the batch_size parameter influence the accuracy about gsm HOT 3 OPEN

For Diving48, we used a batch size of 8, trained for 20 epochs with a dropout of 0.7 (see Sec. 4.2 in the paper). If you are still getting a lower accuracy, train the model for 30 epochs.

from gsm.

python main.py diving48 RGB --arch InceptionV3 --num_segments 16 --consensus_type avg --batch-size 8 --iter_size 2 --dropout 0.7 --lr 0.01 --warmup 10 --epochs 20 --eval-freq 5 --gd 20 --run_iter 1 -j 16 --npb --gsm

So, is this OK?

from gsm.

Use the following setting:

python main.py diving48 RGB --arch InceptionV3 --num_segments 16 --consensus_type avg --batch-size 8 --iter_size 1 --dropout 0.7 --lr 0.01 --warmup 10 --epochs 20 --eval-freq 5 --gd 20 --run_iter 1 -j 16 --npb --gsm

from gsm.