Skip to content

M
maskrcnn
Commit ebc593a2 authored by Sameer Indarapu's avatar Sameer Indarapu Committed by Francisco Massa
Browse files
Options

FIxed comment for # of RoIs per minibatch (#398) 

Since IMS_PER_BATCH is global, it shouldn't be multiplied with the # of GPUs.
parent 48d0f138
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
maskrcnn_benchmark/config/defaults.py
View file @ ebc593a2
...@@ -176,7 +176,7 @@ _C.MODEL.ROI_HEADS.BG_IOU_THRESHOLD = 0.5 ...@@ -176,7 +176,7 @@ _C.MODEL.ROI_HEADS.BG_IOU_THRESHOLD = 0.5
_C.MODEL.ROI_HEADS.BBOX_REG_WEIGHTS = (10., 10., 5., 5.) _C.MODEL.ROI_HEADS.BBOX_REG_WEIGHTS = (10., 10., 5., 5.)
# RoI minibatch size *per image* (number of regions of interest [ROIs]) # RoI minibatch size *per image* (number of regions of interest [ROIs])
# Total number of RoIs per training minibatch = # Total number of RoIs per training minibatch =
# TRAIN.BATCH_SIZE_PER_IM * TRAIN.IMS_PER_BATCH * NUM_GPUS # TRAIN.BATCH_SIZE_PER_IM * TRAIN.IMS_PER_BATCH
# E.g., a common configuration is: 512 * 2 * 8 = 8192 # E.g., a common configuration is: 512 * 2 * 8 = 8192
_C.MODEL.ROI_HEADS.BATCH_SIZE_PER_IMAGE = 512 _C.MODEL.ROI_HEADS.BATCH_SIZE_PER_IMAGE = 512
# Target fraction of RoI minibatch that is labeled foreground (i.e. class > 0) # Target fraction of RoI minibatch that is labeled foreground (i.e. class > 0)
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment