Asking about the Mask-Rcnn training strategy about irn HOT 2 CLOSED

Hi @vicchu
You may try with smaller image size and smaller training steps.

SOLVER:
WEIGHT_DECAY: 0.0001
LR_POLICY: steps_with_decay
BASE_LR: 0.01
GAMMA: 0.1
MAX_ITER: 18000
STEPS: [0, 12000, 16000]
TRAIN:
WEIGHTS: https://s3-us-west-2.amazonaws.com/detectron/ImageNetPretrained/MSRA/R-50.pkl
DATASETS: ('voc_2012_train',)
SCALES: (512,)
MAX_SIZE: 800
BATCH_SIZE_PER_IM: 512
RPN_PRE_NMS_TOP_N: 2000 # Per FPN level
IMS_PER_BATCH: 4
TEST:
DATASETS: ('voc_2012_val',)
SCALE: 512
MAX_SIZE: 800
NMS: 0.5
RPN_PRE_NMS_TOP_N: 1000 # Per FPN level
RPN_POST_NMS_TOP_N: 1000
OUTPUT_DIR: .

from irn.

Hi @jiwoon-ahn
After try the parameters you offered ,I still can not get the same result.
But i have try larger image size,the result is closer to what the paper report.

from irn.