The first part is to change VGG16 to VGG16_BN.from model.vgg import vgg16_bnThe second part is the changes to decom_vgg16 in faster_rcnn_vgg16.py
def decom_vgg16():
# the 30th layer of features is relu of conv5_3
if opt.torch_pretrain:
model = vgg16_bn(pretrained=False)
if not opt.load_path:
model.load_state_dict(t.load(opt.torch_pretrain_path))
else:
model = vgg16_bn(not opt.load_path)
features = list(model.features)[:43]
classifier = model.classifier
classifier = list(classifier)
del classifier[6]
if not opt.use_drop:
del classifier[5]
del classifier[2]
classifier = nn.Sequential(*classifier)
# freeze top4 conv
for layer in features[:14]:
for p in layer.parameters():
p.requires_grad = False
return nn.Sequential(*features), classifier
The training results
fasterrcnn_12171601_16_0.5808726427518627
May I ask why the accuracy is low?What can be done to improve the accuracy?
I changed two parts:
The first part is to change VGG16 to VGG16_BN.
from model.vgg import vgg16_bn
The second part is the changes to decom_vgg16 in faster_rcnn_vgg16.pyThe training results fasterrcnn_12171601_16_0.5808726427518627
May I ask why the accuracy is low?What can be done to improve the accuracy?