A new codebase for popular Scene Graph Generation methods (2020). Visualization & Scene Graph Extraction on custom images/datasets are provided. It's also a PyTorch implementation of paper “Unbiased Scene Graph Generation from Biased Training CVPR 2020”
MIT License
1.03k
stars
228
forks
source link
How to pretrain Faster RCNN with VGG-16 and no FPN? #122
Could you please share the config file and command for training Faster RCNN with VGG-16 as backbone and no FPN used? I tried to train it but the program outputs NAN losses.
The config I used was:
MODEL:
META_ARCHITECTURE: "GeneralizedRCNN"
BACKBONE:
CONV_BODY: "VGG-16" # R-101-FPN
RESNETS:
BACKBONE_OUT_CHANNELS: 512
RELATION_ON: True
ATTRIBUTE_ON: False
FLIP_AUG: False # if there is any left-right relation, FLIP AUG should be false
RPN:
USE_FPN: False
ANCHOR_SIZES: (32, 64, 128, 256, 512)
ANCHOR_STRIDE: (16, )
ASPECT_RATIOS: (0.23232838, 0.63365731, 1.28478321, 3.15089189) # from neural-motifs
PRE_NMS_TOP_N_TRAIN: 6000
PRE_NMS_TOP_N_TEST: 6000
POST_NMS_TOP_N_TRAIN: 1000
POST_NMS_TOP_N_TEST: 1000
FPN_POST_NMS_TOP_N_TRAIN: 1000
FPN_POST_NMS_TOP_N_TEST: 1000
FPN_POST_NMS_PER_BATCH: False
RPN_MID_CHANNEL: 512
ROI_HEADS:
USE_FPN: False
POSITIVE_FRACTION: 0.5
BG_IOU_THRESHOLD: 0.3
BATCH_SIZE_PER_IMAGE: 256
DETECTIONS_PER_IMG: 80
NMS_FILTER_DUPLICATES: True
Hello,
Could you please share the config file and command for training Faster RCNN with VGG-16 as backbone and no FPN used? I tried to train it but the program outputs NAN losses.
The config I used was:
and the command I used was
Thank you very much~