mirror of
https://github.com/huggingface/pytorch-image-models.git
synced 2025-06-03 15:01:08 +08:00
Finish with HRNet, weights and models updated. Improve consistency in model classifier/global pool treatment.
This commit is contained in:
Ross Wightman
parent
3ceeedc441
commit
3bef524f9c
@ -8,12 +8,15 @@ from collections import OrderedDict
|
||||
parser = argparse.ArgumentParser(description='PyTorch ImageNet Validation')
|
||||
parser.add_argument('--checkpoint', default='', type=str, metavar='PATH',
|
||||
help='path to latest checkpoint (default: none)')
|
||||
parser.add_argument('--output', default='./cleaned.pth', type=str, metavar='PATH',
|
||||
parser.add_argument('--output', default='', type=str, metavar='PATH',
|
||||
help='output path')
|
||||
parser.add_argument('--use-ema', dest='use_ema', action='store_true',
|
||||
help='use ema version of weights if present')
|
||||
|
||||
|
||||
_TEMP_NAME = './_checkpoint.pth'
|
||||
|
||||
|
||||
def main():
|
||||
args = parser.parse_args()
|
||||
|
||||
@ -40,13 +43,18 @@ def main():
|
||||
new_state_dict[name] = v
|
||||
print("=> Loaded state_dict from '{}'".format(args.checkpoint))
|
||||
|
||||
torch.save(new_state_dict, args.output)
|
||||
with open(args.output, 'rb') as f:
|
||||
torch.save(new_state_dict, _TEMP_NAME)
|
||||
with open(_TEMP_NAME, 'rb') as f:
|
||||
sha_hash = hashlib.sha256(f.read()).hexdigest()
|
||||
|
||||
checkpoint_base = os.path.splitext(args.checkpoint)[0]
|
||||
if args.output:
|
||||
checkpoint_root, checkpoint_base = os.path.split(args.output)
|
||||
checkpoint_base = os.path.splitext(checkpoint_base)[0]
|
||||
else:
|
||||
checkpoint_root = ''
|
||||
checkpoint_base = os.path.splitext(args.checkpoint)[0]
|
||||
final_filename = '-'.join([checkpoint_base, sha_hash[:8]]) + '.pth'
|
||||
shutil.move(args.output, final_filename)
|
||||
shutil.move(_TEMP_NAME, os.path.join(checkpoint_root, final_filename))
|
||||
print("=> Saved state_dict to '{}, SHA256: {}'".format(final_filename, sha_hash))
|
||||
else:
|
||||
print("Error: Checkpoint ({}) doesn't exist".format(args.checkpoint))
|
||||
|
||||
@ -1,97 +1,155 @@
|
||||
model,top1,top1_err,top5,top5_err,param_count,img_size,cropt_pct,interpolation
|
||||
resnet18,57.18,42.82,80.19,19.81,11.69,224,0.875,bilinear
|
||||
gluon_resnet18_v1b,58.32,41.68,80.96,19.04,11.69,224,0.875,bicubic
|
||||
seresnet18,59.81,40.19,81.68,18.32,11.78,224,0.875,bicubic
|
||||
tv_resnet34,61.2,38.8,82.72,17.28,21.8,224,0.875,bilinear
|
||||
spnasnet_100,61.21,38.79,82.77,17.23,4.42,224,0.875,bilinear
|
||||
mnasnet_100,61.91,38.09,83.71,16.29,4.38,224,0.875,bicubic
|
||||
fbnetc_100,62.43,37.57,83.39,16.61,5.57,224,0.875,bilinear
|
||||
gluon_resnet34_v1b,62.56,37.44,84,16,21.8,224,0.875,bicubic
|
||||
resnet34,62.82,37.18,84.12,15.88,21.8,224,0.875,bilinear
|
||||
seresnet34,62.89,37.11,84.22,15.78,21.96,224,0.875,bilinear
|
||||
densenet121,62.94,37.06,84.26,15.74,7.98,224,0.875,bicubic
|
||||
semnasnet_100,63.12,36.88,84.53,15.47,3.89,224,0.875,bicubic
|
||||
mobilenetv3_100,63.23,36.77,84.52,15.48,5.48,224,0.875,bicubic
|
||||
tv_resnet50,63.33,36.67,84.65,15.35,25.56,224,0.875,bilinear
|
||||
mixnet_s,63.38,36.62,84.71,15.29,4.13,224,0.875,bicubic
|
||||
resnet26,63.45,36.55,84.27,15.73,16,224,0.875,bicubic
|
||||
tf_mixnet_s,63.59,36.41,84.27,15.73,4.13,224,0.875,bicubic
|
||||
dpn68,64.22,35.78,85.18,14.82,12.61,224,0.875,bicubic
|
||||
tf_mixnet_m,64.27,35.73,85.09,14.91,5.01,224,0.875,bicubic
|
||||
tf_efficientnet_b0,64.29,35.71,85.25,14.75,5.29,224,0.875,bicubic
|
||||
efficientnet_b0,64.58,35.42,85.89,14.11,5.29,224,0.875,bicubic
|
||||
resnet26d,64.63,35.37,85.12,14.88,16.01,224,0.875,bicubic
|
||||
mixnet_m,64.69,35.31,85.47,14.53,5.01,224,0.875,bicubic
|
||||
densenet169,64.78,35.22,85.25,14.75,14.15,224,0.875,bicubic
|
||||
seresnext26_32x4d,65.04,34.96,85.65,14.35,16.79,224,0.875,bicubic
|
||||
tf_efficientnet_es,65.24,34.76,85.54,14.46,5.44,224,0.875,bicubic
|
||||
densenet201,65.28,34.72,85.67,14.33,20.01,224,0.875,bicubic
|
||||
dpn68b,65.6,34.4,85.94,14.06,12.61,224,0.875,bicubic
|
||||
resnet101,65.68,34.32,85.98,14.02,44.55,224,0.875,bilinear
|
||||
densenet161,65.85,34.15,86.46,13.54,28.68,224,0.875,bicubic
|
||||
gluon_resnet50_v1b,66.04,33.96,86.27,13.73,25.56,224,0.875,bicubic
|
||||
inception_v3,66.12,33.88,86.34,13.66,27.16,299,0.875,bicubic
|
||||
tv_resnext50_32x4d,66.18,33.82,86.04,13.96,25.03,224,0.875,bilinear
|
||||
seresnet50,66.24,33.76,86.33,13.67,28.09,224,0.875,bilinear
|
||||
tf_inception_v3,66.41,33.59,86.68,13.32,23.83,299,0.875,bicubic
|
||||
gluon_resnet50_v1c,66.54,33.46,86.16,13.84,25.58,224,0.875,bicubic
|
||||
adv_inception_v3,66.6,33.4,86.56,13.44,23.83,299,0.875,bicubic
|
||||
wide_resnet50_2,66.65,33.35,86.81,13.19,68.88,224,0.875,bilinear
|
||||
wide_resnet101_2,66.68,33.32,87.04,12.96,126.89,224,0.875,bilinear
|
||||
tf_mixnet_l,66.78,33.22,86.46,13.54,7.33,224,0.875,bicubic
|
||||
resnet50,66.81,33.19,87,13,25.56,224,0.875,bicubic
|
||||
tf_efficientnet_em,66.87,33.13,86.98,13.02,6.9,240,0.882,bicubic
|
||||
resnext50_32x4d,66.88,33.12,86.36,13.64,25.03,224,0.875,bicubic
|
||||
tf_efficientnet_b1,66.89,33.11,87.04,12.96,7.79,240,0.882,bicubic
|
||||
mixnet_l,66.97,33.03,86.94,13.06,7.33,224,0.875,bicubic
|
||||
resnet152,67.02,32.98,87.57,12.43,60.19,224,0.875,bilinear
|
||||
gluon_resnet50_v1s,67.1,32.9,86.86,13.14,25.68,224,0.875,bicubic
|
||||
seresnet101,67.15,32.85,87.05,12.95,49.33,224,0.875,bilinear
|
||||
gluon_resnet101_v1b,67.45,32.55,87.23,12.77,44.55,224,0.875,bicubic
|
||||
efficientnet_b1,67.55,32.45,87.29,12.71,7.79,240,0.882,bicubic
|
||||
seresnet152,67.55,32.45,87.39,12.61,66.82,224,0.875,bilinear
|
||||
gluon_resnet101_v1c,67.56,32.44,87.16,12.84,44.57,224,0.875,bicubic
|
||||
gluon_inception_v3,67.59,32.41,87.46,12.54,23.83,299,0.875,bicubic
|
||||
xception,67.67,32.33,87.57,12.43,22.86,299,0.8975,bicubic
|
||||
efficientnet_b2,67.8,32.2,88.2,11.8,9.11,260,0.89,bicubic
|
||||
resnext101_32x8d,67.85,32.15,87.48,12.52,88.79,224,0.875,bilinear
|
||||
seresnext50_32x4d,67.87,32.13,87.62,12.38,27.56,224,0.875,bilinear
|
||||
gluon_resnet50_v1d,67.91,32.09,87.12,12.88,25.58,224,0.875,bicubic
|
||||
dpn92,68.01,31.99,87.59,12.41,37.67,224,0.875,bicubic
|
||||
tf_efficientnet_el,68.18,31.82,88.35,11.65,10.59,300,0.904,bicubic
|
||||
gluon_resnext50_32x4d,68.28,31.72,87.32,12.68,25.03,224,0.875,bicubic
|
||||
dpn98,68.58,31.42,87.66,12.34,61.57,224,0.875,bicubic
|
||||
gluon_seresnext50_32x4d,68.67,31.33,88.32,11.68,27.56,224,0.875,bicubic
|
||||
dpn107,68.71,31.29,88.13,11.87,86.92,224,0.875,bicubic
|
||||
gluon_resnet101_v1s,68.72,31.28,87.9,12.1,44.67,224,0.875,bicubic
|
||||
ig_resnext101_32x48d,76.87,23.13,93.32,6.68,828.41,224,0.875,bilinear
|
||||
ig_resnext101_32x32d,76.84,23.16,93.19,6.81,468.53,224,0.875,bilinear
|
||||
tf_efficientnet_b7_ap,76.09,23.91,92.97,7.03,66.35,600,0.949,bicubic
|
||||
tf_efficientnet_b8_ap,76.09,23.91,92.73,7.27,87.41,672,0.954,bicubic
|
||||
ig_resnext101_32x16d,75.71,24.29,92.9,7.1,194.03,224,0.875,bilinear
|
||||
swsl_resnext101_32x8d,75.45,24.55,92.75,7.25,88.79,224,0.875,bilinear
|
||||
tf_efficientnet_b6_ap,75.38,24.62,92.44,7.56,43.04,528,0.942,bicubic
|
||||
tf_efficientnet_b7,74.72,25.28,92.22,7.78,66.35,600,0.949,bicubic
|
||||
tf_efficientnet_b5_ap,74.59,25.41,91.99,8.01,30.39,456,0.934,bicubic
|
||||
swsl_resnext101_32x4d,74.15,25.85,91.99,8.01,44.18,224,0.875,bilinear
|
||||
swsl_resnext101_32x16d,74.01,25.99,92.17,7.83,194.03,224,0.875,bilinear
|
||||
tf_efficientnet_b6,73.9,26.1,91.75,8.25,43.04,528,0.942,bicubic
|
||||
ig_resnext101_32x8d,73.66,26.34,92.15,7.85,88.79,224,0.875,bilinear
|
||||
tf_efficientnet_b5,73.54,26.46,91.46,8.54,30.39,456,0.934,bicubic
|
||||
tf_efficientnet_b4_ap,72.89,27.11,90.98,9.02,19.34,380,0.922,bicubic
|
||||
swsl_resnext50_32x4d,72.58,27.42,90.84,9.16,25.03,224,0.875,bilinear
|
||||
pnasnet5large,72.37,27.63,90.26,9.74,86.06,331,0.875,bicubic
|
||||
nasnetalarge,72.31,27.69,90.51,9.49,88.75,331,0.875,bicubic
|
||||
tf_efficientnet_b4,72.28,27.72,90.6,9.4,19.34,380,0.922,bicubic
|
||||
swsl_resnet50,71.69,28.31,90.51,9.49,25.56,224,0.875,bilinear
|
||||
ssl_resnext101_32x8d,71.49,28.51,90.47,9.53,88.79,224,0.875,bilinear
|
||||
ssl_resnext101_32x16d,71.4,28.6,90.55,9.45,194.03,224,0.875,bilinear
|
||||
tf_efficientnet_b3_ap,70.92,29.08,89.43,10.57,12.23,300,0.904,bicubic
|
||||
tf_efficientnet_b3,70.62,29.38,89.44,10.56,12.23,300,0.904,bicubic
|
||||
gluon_senet154,70.6,29.4,88.92,11.08,115.09,224,0.875,bicubic
|
||||
ssl_resnext101_32x4d,70.5,29.5,89.76,10.24,44.18,224,0.875,bilinear
|
||||
senet154,70.48,29.52,88.99,11.01,115.09,224,0.875,bilinear
|
||||
gluon_seresnext101_64x4d,70.44,29.56,89.35,10.65,88.23,224,0.875,bicubic
|
||||
gluon_resnet152_v1s,70.32,29.68,88.87,11.13,60.32,224,0.875,bicubic
|
||||
inception_resnet_v2,70.12,29.88,88.68,11.32,55.84,299,0.8975,bicubic
|
||||
gluon_seresnext101_32x4d,70.01,29.99,88.91,11.09,48.96,224,0.875,bicubic
|
||||
gluon_resnet152_v1d,69.95,30.05,88.47,11.53,60.21,224,0.875,bicubic
|
||||
gluon_resnext101_64x4d,69.69,30.31,88.26,11.74,83.46,224,0.875,bicubic
|
||||
ssl_resnext50_32x4d,69.69,30.31,89.42,10.58,25.03,224,0.875,bilinear
|
||||
ens_adv_inception_resnet_v2,69.52,30.48,88.5,11.5,55.84,299,0.8975,bicubic
|
||||
inception_v4,69.35,30.65,88.78,11.22,42.68,299,0.875,bicubic
|
||||
seresnext101_32x4d,69.34,30.66,88.05,11.95,48.96,224,0.875,bilinear
|
||||
gluon_resnet152_v1c,69.13,30.87,87.89,12.11,60.21,224,0.875,bicubic
|
||||
mixnet_xl,69,31,88.19,11.81,11.9,224,0.875,bicubic
|
||||
gluon_resnet101_v1d,68.99,31.01,88.08,11.92,44.57,224,0.875,bicubic
|
||||
gluon_xception65,68.98,31.02,88.32,11.68,39.92,299,0.875,bicubic
|
||||
gluon_resnext101_32x4d,68.96,31.04,88.34,11.66,44.18,224,0.875,bicubic
|
||||
tf_efficientnet_b2_ap,68.93,31.07,88.34,11.66,9.11,260,0.89,bicubic
|
||||
gluon_resnet152_v1b,68.81,31.19,87.71,12.29,60.19,224,0.875,bicubic
|
||||
dpn131,68.76,31.24,87.48,12.52,79.25,224,0.875,bicubic
|
||||
resnext50d_32x4d,68.75,31.25,88.31,11.69,25.05,224,0.875,bicubic
|
||||
tf_efficientnet_b2,68.75,31.25,87.95,12.05,9.11,260,0.89,bicubic
|
||||
dpn131,68.76,31.24,87.48,12.52,79.25,224,0.875,bicubic
|
||||
gluon_resnet152_v1b,68.81,31.19,87.71,12.29,60.19,224,0.875,bicubic
|
||||
gluon_resnext101_32x4d,68.96,31.04,88.34,11.66,44.18,224,0.875,bicubic
|
||||
gluon_xception65,68.98,31.02,88.32,11.68,39.92,299,0.875,bicubic
|
||||
gluon_resnet101_v1d,68.99,31.01,88.08,11.92,44.57,224,0.875,bicubic
|
||||
mixnet_xl,69,31,88.19,11.81,11.9,224,0.875,bicubic
|
||||
gluon_resnet152_v1c,69.13,30.87,87.89,12.11,60.21,224,0.875,bicubic
|
||||
seresnext101_32x4d,69.34,30.66,88.05,11.95,48.96,224,0.875,bilinear
|
||||
inception_v4,69.35,30.65,88.78,11.22,42.68,299,0.875,bicubic
|
||||
ens_adv_inception_resnet_v2,69.52,30.48,88.5,11.5,55.84,299,0.8975,bicubic
|
||||
gluon_resnext101_64x4d,69.69,30.31,88.26,11.74,83.46,224,0.875,bicubic
|
||||
gluon_resnet152_v1d,69.95,30.05,88.47,11.53,60.21,224,0.875,bicubic
|
||||
gluon_seresnext101_32x4d,70.01,29.99,88.91,11.09,48.96,224,0.875,bicubic
|
||||
inception_resnet_v2,70.12,29.88,88.68,11.32,55.84,299,0.8975,bicubic
|
||||
gluon_resnet152_v1s,70.32,29.68,88.87,11.13,60.32,224,0.875,bicubic
|
||||
gluon_seresnext101_64x4d,70.44,29.56,89.35,10.65,88.23,224,0.875,bicubic
|
||||
senet154,70.48,29.52,88.99,11.01,115.09,224,0.875,bilinear
|
||||
gluon_senet154,70.6,29.4,88.92,11.08,115.09,224,0.875,bicubic
|
||||
tf_efficientnet_b3,70.62,29.38,89.44,10.56,12.23,300,0.904,bicubic
|
||||
tf_efficientnet_b4,72.28,27.72,90.6,9.4,19.34,380,0.922,bicubic
|
||||
nasnetalarge,72.31,27.69,90.51,9.49,88.75,331,0.875,bicubic
|
||||
pnasnet5large,72.37,27.63,90.26,9.74,86.06,331,0.875,bicubic
|
||||
tf_efficientnet_b5,73.37,26.63,91.21,8.79,30.39,456,0.934,bicubic
|
||||
ig_resnext101_32x8d,73.66,26.34,92.15,7.85,88.79,224,0.875,bilinear
|
||||
tf_efficientnet_b6,73.9,26.1,91.75,8.25,43.04,528,0.942,bicubic
|
||||
tf_efficientnet_b7,74.04,25.96,91.86,8.14,66.35,600,0.949,bicubic
|
||||
ig_resnext101_32x16d,75.71,24.29,92.9,7.1,194.03,224,0.875,bilinear
|
||||
ig_resnext101_32x32d,76.84,23.16,93.19,6.81,468.53,224,0.875,bilinear
|
||||
ig_resnext101_32x48d,76.87,23.13,93.32,6.68,828.41,224,0.875,bilinear
|
||||
gluon_resnet101_v1s,68.72,31.28,87.9,12.1,44.67,224,0.875,bicubic
|
||||
dpn107,68.71,31.29,88.13,11.87,86.92,224,0.875,bicubic
|
||||
gluon_seresnext50_32x4d,68.67,31.33,88.32,11.68,27.56,224,0.875,bicubic
|
||||
hrnet_w64,68.63,31.37,88.07,11.93,128.06,224,0.875,bilinear
|
||||
dpn98,68.58,31.42,87.66,12.34,61.57,224,0.875,bicubic
|
||||
ssl_resnet50,68.42,31.58,88.58,11.42,25.56,224,0.875,bilinear
|
||||
dla102x2,68.34,31.66,87.87,12.13,41.75,224,0.875,bilinear
|
||||
gluon_resnext50_32x4d,68.28,31.72,87.32,12.68,25.03,224,0.875,bicubic
|
||||
tf_efficientnet_el,68.18,31.82,88.35,11.65,10.59,300,0.904,bicubic
|
||||
dpn92,68.01,31.99,87.59,12.41,37.67,224,0.875,bicubic
|
||||
gluon_resnet50_v1d,67.91,32.09,87.12,12.88,25.58,224,0.875,bicubic
|
||||
seresnext50_32x4d,67.87,32.13,87.62,12.38,27.56,224,0.875,bilinear
|
||||
resnext101_32x8d,67.85,32.15,87.48,12.52,88.79,224,0.875,bilinear
|
||||
efficientnet_b2,67.8,32.2,88.2,11.8,9.11,260,0.89,bicubic
|
||||
hrnet_w44,67.77,32.23,87.53,12.47,67.06,224,0.875,bilinear
|
||||
hrnet_w48,67.77,32.23,87.42,12.58,77.47,224,0.875,bilinear
|
||||
xception,67.67,32.33,87.57,12.43,22.86,299,0.8975,bicubic
|
||||
dla169,67.61,32.39,87.56,12.44,53.99,224,0.875,bilinear
|
||||
gluon_inception_v3,67.59,32.41,87.46,12.54,23.83,299,0.875,bicubic
|
||||
hrnet_w40,67.59,32.41,87.13,12.87,57.56,224,0.875,bilinear
|
||||
gluon_resnet101_v1c,67.56,32.44,87.16,12.84,44.57,224,0.875,bicubic
|
||||
efficientnet_b1,67.55,32.45,87.29,12.71,7.79,240,0.882,bicubic
|
||||
seresnet152,67.55,32.45,87.39,12.61,66.82,224,0.875,bilinear
|
||||
res2net50_26w_8s,67.53,32.47,87.27,12.73,48.4,224,0.875,bilinear
|
||||
tf_efficientnet_b1_ap,67.52,32.48,87.77,12.23,7.79,240,0.882,bicubic
|
||||
tf_efficientnet_cc_b1_8e,67.48,32.52,87.31,12.69,39.72,240,0.882,bicubic
|
||||
gluon_resnet101_v1b,67.45,32.55,87.23,12.77,44.55,224,0.875,bicubic
|
||||
res2net101_26w_4s,67.45,32.55,87.01,12.99,45.21,224,0.875,bilinear
|
||||
seresnet101,67.15,32.85,87.05,12.95,49.33,224,0.875,bilinear
|
||||
gluon_resnet50_v1s,67.1,32.9,86.86,13.14,25.68,224,0.875,bicubic
|
||||
dla60x,67.08,32.92,87.17,12.83,17.65,224,0.875,bilinear
|
||||
dla60_res2net,67.03,32.97,87.14,12.86,21.15,224,0.875,bilinear
|
||||
resnet152,67.02,32.98,87.57,12.43,60.19,224,0.875,bilinear
|
||||
dla102x,67,33,86.77,13.23,26.77,224,0.875,bilinear
|
||||
mixnet_l,66.97,33.03,86.94,13.06,7.33,224,0.875,bicubic
|
||||
res2net50_26w_6s,66.91,33.09,86.9,13.1,37.05,224,0.875,bilinear
|
||||
tf_efficientnet_b1,66.89,33.11,87.04,12.96,7.79,240,0.882,bicubic
|
||||
resnext50_32x4d,66.88,33.12,86.36,13.64,25.03,224,0.875,bicubic
|
||||
tf_efficientnet_em,66.87,33.13,86.98,13.02,6.9,240,0.882,bicubic
|
||||
resnet50,66.81,33.19,87,13,25.56,224,0.875,bicubic
|
||||
hrnet_w32,66.79,33.21,87.29,12.71,41.23,224,0.875,bilinear
|
||||
tf_mixnet_l,66.78,33.22,86.46,13.54,7.33,224,0.875,bicubic
|
||||
hrnet_w30,66.76,33.24,86.79,13.21,37.71,224,0.875,bilinear
|
||||
wide_resnet101_2,66.68,33.32,87.04,12.96,126.89,224,0.875,bilinear
|
||||
wide_resnet50_2,66.65,33.35,86.81,13.19,68.88,224,0.875,bilinear
|
||||
dla60_res2next,66.64,33.36,87.02,12.98,17.33,224,0.875,bilinear
|
||||
adv_inception_v3,66.6,33.4,86.56,13.44,23.83,299,0.875,bicubic
|
||||
dla102,66.55,33.45,86.91,13.09,33.73,224,0.875,bilinear
|
||||
gluon_resnet50_v1c,66.54,33.46,86.16,13.84,25.58,224,0.875,bicubic
|
||||
tf_inception_v3,66.42,33.58,86.68,13.32,23.83,299,0.875,bicubic
|
||||
seresnet50,66.24,33.76,86.33,13.67,28.09,224,0.875,bilinear
|
||||
tf_efficientnet_cc_b0_8e,66.21,33.79,86.22,13.78,24.01,224,0.875,bicubic
|
||||
tv_resnext50_32x4d,66.18,33.82,86.04,13.96,25.03,224,0.875,bilinear
|
||||
res2net50_26w_4s,66.17,33.83,86.6,13.4,25.7,224,0.875,bilinear
|
||||
inception_v3,66.12,33.88,86.34,13.66,27.16,299,0.875,bicubic
|
||||
gluon_resnet50_v1b,66.04,33.96,86.27,13.73,25.56,224,0.875,bicubic
|
||||
res2net50_14w_8s,66.02,33.98,86.24,13.76,25.06,224,0.875,bilinear
|
||||
densenet161,65.85,34.15,86.46,13.54,28.68,224,0.875,bicubic
|
||||
res2next50,65.85,34.15,85.83,14.17,24.67,224,0.875,bilinear
|
||||
resnet101,65.68,34.32,85.98,14.02,44.55,224,0.875,bilinear
|
||||
dpn68b,65.6,34.4,85.94,14.06,12.61,224,0.875,bicubic
|
||||
tf_efficientnet_b0_ap,65.49,34.51,85.55,14.45,5.29,224,0.875,bicubic
|
||||
res2net50_48w_2s,65.32,34.68,85.96,14.04,25.29,224,0.875,bilinear
|
||||
densenet201,65.28,34.72,85.67,14.33,20.01,224,0.875,bicubic
|
||||
tf_efficientnet_es,65.24,34.76,85.54,14.46,5.44,224,0.875,bicubic
|
||||
dla60,65.22,34.78,85.75,14.25,22.33,224,0.875,bilinear
|
||||
tf_efficientnet_cc_b0_4e,65.13,34.87,85.13,14.87,13.31,224,0.875,bicubic
|
||||
seresnext26_32x4d,65.04,34.96,85.65,14.35,16.79,224,0.875,bicubic
|
||||
hrnet_w18,64.91,35.09,85.75,14.25,21.3,224,0.875,bilinear
|
||||
densenet169,64.78,35.22,85.25,14.75,14.15,224,0.875,bicubic
|
||||
mixnet_m,64.69,35.31,85.47,14.53,5.01,224,0.875,bicubic
|
||||
resnet26d,64.63,35.37,85.12,14.88,16.01,224,0.875,bicubic
|
||||
efficientnet_b0,64.58,35.42,85.89,14.11,5.29,224,0.875,bicubic
|
||||
tf_efficientnet_b0,64.29,35.71,85.25,14.75,5.29,224,0.875,bicubic
|
||||
tf_mixnet_m,64.27,35.73,85.09,14.91,5.01,224,0.875,bicubic
|
||||
dpn68,64.22,35.78,85.18,14.82,12.61,224,0.875,bicubic
|
||||
tf_mixnet_s,63.59,36.41,84.27,15.73,4.13,224,0.875,bicubic
|
||||
resnet26,63.45,36.55,84.27,15.73,16,224,0.875,bicubic
|
||||
mixnet_s,63.38,36.62,84.71,15.29,4.13,224,0.875,bicubic
|
||||
tv_resnet50,63.33,36.67,84.65,15.35,25.56,224,0.875,bilinear
|
||||
mobilenetv3_rw,63.23,36.77,84.52,15.48,5.48,224,0.875,bicubic
|
||||
semnasnet_100,63.12,36.88,84.53,15.47,3.89,224,0.875,bicubic
|
||||
densenet121,62.94,37.06,84.26,15.74,7.98,224,0.875,bicubic
|
||||
seresnet34,62.89,37.11,84.22,15.78,21.96,224,0.875,bilinear
|
||||
hrnet_w18_small_v2,62.83,37.17,83.97,16.03,15.6,224,0.875,bilinear
|
||||
resnet34,62.82,37.18,84.12,15.88,21.8,224,0.875,bilinear
|
||||
swsl_resnet18,62.73,37.27,84.3,15.7,11.69,224,0.875,bilinear
|
||||
gluon_resnet34_v1b,62.56,37.44,84,16,21.8,224,0.875,bicubic
|
||||
dla34,62.51,37.49,83.92,16.08,15.78,224,0.875,bilinear
|
||||
tf_mobilenetv3_large_100,62.47,37.53,83.96,16.04,5.48,224,0.875,bilinear
|
||||
fbnetc_100,62.43,37.57,83.39,16.61,5.57,224,0.875,bilinear
|
||||
mnasnet_100,61.91,38.09,83.71,16.29,4.38,224,0.875,bicubic
|
||||
ssl_resnet18,61.49,38.51,83.33,16.67,11.69,224,0.875,bilinear
|
||||
spnasnet_100,61.21,38.79,82.77,17.23,4.42,224,0.875,bilinear
|
||||
tv_resnet34,61.2,38.8,82.72,17.28,21.8,224,0.875,bilinear
|
||||
tf_mobilenetv3_large_075,60.38,39.62,81.96,18.04,3.99,224,0.875,bilinear
|
||||
seresnet18,59.81,40.19,81.68,18.32,11.78,224,0.875,bicubic
|
||||
tf_mobilenetv3_large_minimal_100,59.07,40.93,81.14,18.86,3.92,224,0.875,bilinear
|
||||
hrnet_w18_small,58.97,41.03,81.34,18.66,13.19,224,0.875,bilinear
|
||||
gluon_resnet18_v1b,58.32,41.68,80.96,19.04,11.69,224,0.875,bicubic
|
||||
resnet18,57.18,42.82,80.19,19.81,11.69,224,0.875,bilinear
|
||||
dla60x_c,56.02,43.98,78.96,21.04,1.34,224,0.875,bilinear
|
||||
tf_mobilenetv3_small_100,54.51,45.49,77.08,22.92,2.54,224,0.875,bilinear
|
||||
dla46x_c,53.08,46.92,76.84,23.16,1.08,224,0.875,bilinear
|
||||
dla46_c,52.2,47.8,75.68,24.32,1.31,224,0.875,bilinear
|
||||
tf_mobilenetv3_small_075,52.15,47.85,75.46,24.54,2.04,224,0.875,bilinear
|
||||
tf_mobilenetv3_small_minimal_100,49.53,50.47,73.05,26.95,2.04,224,0.875,bilinear
|
||||
|
||||
|
11
sotabench.py
11
sotabench.py
@ -294,6 +294,17 @@ model_list = [
|
||||
_entry('res2next50', 'Res2NeXt-50', '1904.01169'),
|
||||
_entry('dla60_res2net', 'Res2Net-DLA-60', '1904.01169'),
|
||||
_entry('dla60_res2next', 'Res2NeXt-DLA-60', '1904.01169'),
|
||||
|
||||
## HRNet official impl weights
|
||||
_entry('hrnet_w18_small', 'HRNet-W18-C-Small-V1', '1908.07919'),
|
||||
_entry('hrnet_w18_small_v2', 'HRNet-W18-C-Small-V2', '1908.07919'),
|
||||
_entry('hrnet_w18', 'HRNet-W18-C', '1908.07919'),
|
||||
_entry('hrnet_w30', 'HRNet-W30-C', '1908.07919'),
|
||||
_entry('hrnet_w32', 'HRNet-W32-C', '1908.07919'),
|
||||
_entry('hrnet_w40', 'HRNet-W40-C', '1908.07919'),
|
||||
_entry('hrnet_w44', 'HRNet-W44-C', '1908.07919'),
|
||||
_entry('hrnet_w48', 'HRNet-W48-C', '1908.07919'),
|
||||
_entry('hrnet_w64', 'HRNet-W64-C', '1908.07919'),
|
||||
]
|
||||
|
||||
for m in model_list:
|
||||
|
||||
@ -10,7 +10,7 @@ import torch.nn.functional as F
|
||||
|
||||
from .registry import register_model
|
||||
from .helpers import load_pretrained
|
||||
from .adaptive_avgmax_pool import select_adaptive_pool2d
|
||||
from .adaptive_avgmax_pool import SelectAdaptivePool2d
|
||||
from timm.data import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD
|
||||
import re
|
||||
|
||||
@ -88,8 +88,8 @@ class DenseNet(nn.Module):
|
||||
def __init__(self, growth_rate=32, block_config=(6, 12, 24, 16),
|
||||
num_init_features=64, bn_size=4, drop_rate=0,
|
||||
num_classes=1000, in_chans=3, global_pool='avg'):
|
||||
self.global_pool = global_pool
|
||||
self.num_classes = num_classes
|
||||
self.drop_rate = drop_rate
|
||||
super(DenseNet, self).__init__()
|
||||
|
||||
# First convolution
|
||||
@ -117,32 +117,31 @@ class DenseNet(nn.Module):
|
||||
self.features.add_module('norm5', nn.BatchNorm2d(num_features))
|
||||
|
||||
# Linear layer
|
||||
self.classifier = nn.Linear(num_features, num_classes)
|
||||
|
||||
self.num_features = num_features
|
||||
self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
||||
self.classifier = nn.Linear(self.num_features * self.global_pool.feat_mult(), num_classes)
|
||||
|
||||
def get_classifier(self):
|
||||
return self.classifier
|
||||
|
||||
def reset_classifier(self, num_classes, global_pool='avg'):
|
||||
self.global_pool = global_pool
|
||||
self.num_classes = num_classes
|
||||
del self.classifier
|
||||
if num_classes:
|
||||
self.classifier = nn.Linear(self.num_features, num_classes)
|
||||
else:
|
||||
self.classifier = None
|
||||
self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
||||
self.classifier = nn.Linear(
|
||||
self.num_features * self.global_pool.feat_mult(), num_classes) if num_classes else None
|
||||
|
||||
def forward_features(self, x, pool=True):
|
||||
def forward_features(self, x):
|
||||
x = self.features(x)
|
||||
x = F.relu(x, inplace=True)
|
||||
if pool:
|
||||
x = select_adaptive_pool2d(x, self.global_pool)
|
||||
x = x.view(x.size(0), -1)
|
||||
return x
|
||||
|
||||
def forward(self, x):
|
||||
return self.classifier(self.forward_features(x, pool=True))
|
||||
x = self.forward_features(x)
|
||||
x = self.global_pool(x).flatten(1)
|
||||
if self.drop_rate > 0.:
|
||||
x = F.dropout(x, p=self.drop_rate, training=self.training)
|
||||
x = self.classifier(x)
|
||||
return x
|
||||
|
||||
|
||||
def _filter_pretrained(state_dict):
|
||||
|
||||
@ -276,8 +276,7 @@ class DLA(nn.Module):
|
||||
|
||||
self.num_features = channels[-1]
|
||||
self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
||||
self.fc = nn.Conv2d(self.num_features * self.global_pool.feat_mult(), num_classes,
|
||||
kernel_size=1, stride=1, padding=0, bias=True)
|
||||
self.fc = nn.Conv2d(self.num_features * self.global_pool.feat_mult(), num_classes, 1, bias=True)
|
||||
|
||||
for m in self.modules():
|
||||
if isinstance(m, nn.Conv2d):
|
||||
@ -302,15 +301,14 @@ class DLA(nn.Module):
|
||||
return self.fc
|
||||
|
||||
def reset_classifier(self, num_classes, global_pool='avg'):
|
||||
self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
||||
self.num_classes = num_classes
|
||||
del self.fc
|
||||
self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
||||
if num_classes:
|
||||
self.fc = nn.Linear(self.num_features * self.global_pool.feat_mult(), num_classes)
|
||||
self.fc = nn.Conv2d(self.num_features * self.global_pool.feat_mult(), num_classes, 1, bias=True)
|
||||
else:
|
||||
self.fc = None
|
||||
|
||||
def forward_features(self, x, pool=True):
|
||||
def forward_features(self, x):
|
||||
x = self.base_layer(x)
|
||||
x = self.level0(x)
|
||||
x = self.level1(x)
|
||||
@ -318,17 +316,15 @@ class DLA(nn.Module):
|
||||
x = self.level3(x)
|
||||
x = self.level4(x)
|
||||
x = self.level5(x)
|
||||
if pool:
|
||||
x = self.global_pool(x)
|
||||
return x
|
||||
|
||||
def forward(self, x):
|
||||
x = self.forward_features(x)
|
||||
x = self.global_pool(x)
|
||||
if self.drop_rate > 0.:
|
||||
x = F.dropout(x, p=self.drop_rate, training=self.training)
|
||||
x = self.fc(x)
|
||||
x = x.flatten(1)
|
||||
return x
|
||||
return x.flatten(1)
|
||||
|
||||
|
||||
@register_model
|
||||
|
||||
@ -16,7 +16,7 @@ from collections import OrderedDict
|
||||
|
||||
from .registry import register_model
|
||||
from .helpers import load_pretrained
|
||||
from .adaptive_avgmax_pool import select_adaptive_pool2d
|
||||
from .adaptive_avgmax_pool import SelectAdaptivePool2d
|
||||
from timm.data import IMAGENET_DPN_MEAN, IMAGENET_DPN_STD
|
||||
|
||||
|
||||
@ -160,7 +160,6 @@ class DPN(nn.Module):
|
||||
super(DPN, self).__init__()
|
||||
self.num_classes = num_classes
|
||||
self.drop_rate = drop_rate
|
||||
self.global_pool = global_pool
|
||||
self.b = b
|
||||
bw_factor = 1 if small else 4
|
||||
|
||||
@ -218,32 +217,32 @@ class DPN(nn.Module):
|
||||
self.features = nn.Sequential(blocks)
|
||||
|
||||
# Using 1x1 conv for the FC layer to allow the extra pooling scheme
|
||||
self.classifier = nn.Conv2d(in_chs, num_classes, kernel_size=1, bias=True)
|
||||
self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
||||
self.classifier = nn.Conv2d(
|
||||
self.num_features * self.global_pool.feat_mult(), num_classes, kernel_size=1, bias=True)
|
||||
|
||||
def get_classifier(self):
|
||||
return self.classifier
|
||||
|
||||
def reset_classifier(self, num_classes, global_pool='avg'):
|
||||
self.num_classes = num_classes
|
||||
self.global_pool = global_pool
|
||||
del self.classifier
|
||||
self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
||||
if num_classes:
|
||||
self.classifier = nn.Conv2d(self.num_features, num_classes, kernel_size=1, bias=True)
|
||||
self.classifier = nn.Conv2d(
|
||||
self.num_features * self.global_pool.feat_mult(), num_classes, kernel_size=1, bias=True)
|
||||
else:
|
||||
self.classifier = None
|
||||
|
||||
def forward_features(self, x, pool=True):
|
||||
x = self.features(x)
|
||||
if pool:
|
||||
x = select_adaptive_pool2d(x, pool_type=self.global_pool)
|
||||
return x
|
||||
def forward_features(self, x):
|
||||
return self.features(x)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.forward_features(x)
|
||||
x = self.global_pool(x)
|
||||
if self.drop_rate > 0.:
|
||||
x = F.dropout(x, p=self.drop_rate, training=self.training)
|
||||
out = self.classifier(x)
|
||||
return out.view(out.size(0), -1)
|
||||
return out.flatten(1)
|
||||
|
||||
|
||||
@register_model
|
||||
|
||||
@ -211,8 +211,7 @@ class EfficientNet(nn.Module):
|
||||
def __init__(self, block_args, num_classes=1000, num_features=1280, in_chans=3, stem_size=32,
|
||||
channel_multiplier=1.0, channel_divisor=8, channel_min=None,
|
||||
pad_type='', act_layer=nn.ReLU, drop_rate=0., drop_connect_rate=0.,
|
||||
se_kwargs=None, norm_layer=nn.BatchNorm2d, norm_kwargs=None,
|
||||
global_pool='avg', weight_init='goog'):
|
||||
se_kwargs=None, norm_layer=nn.BatchNorm2d, norm_kwargs=None, global_pool='avg'):
|
||||
super(EfficientNet, self).__init__()
|
||||
norm_kwargs = norm_kwargs or {}
|
||||
|
||||
@ -245,11 +244,7 @@ class EfficientNet(nn.Module):
|
||||
# Classifier
|
||||
self.classifier = nn.Linear(self.num_features * self.global_pool.feat_mult(), self.num_classes)
|
||||
|
||||
for m in self.modules():
|
||||
if weight_init == 'goog':
|
||||
efficientnet_init_goog(m)
|
||||
else:
|
||||
efficientnet_init_default(m)
|
||||
efficientnet_init_weights(self)
|
||||
|
||||
def as_sequential(self):
|
||||
layers = [self.conv_stem, self.bn1, self.act1]
|
||||
@ -262,14 +257,10 @@ class EfficientNet(nn.Module):
|
||||
return self.classifier
|
||||
|
||||
def reset_classifier(self, num_classes, global_pool='avg'):
|
||||
self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
||||
self.num_classes = num_classes
|
||||
del self.classifier
|
||||
if num_classes:
|
||||
self.classifier = nn.Linear(
|
||||
self.num_features * self.global_pool.feat_mult(), num_classes)
|
||||
else:
|
||||
self.classifier = None
|
||||
self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
||||
self.classifier = nn.Linear(
|
||||
self.num_features * self.global_pool.feat_mult(), num_classes) if num_classes else None
|
||||
|
||||
def forward_features(self, x):
|
||||
x = self.conv_stem(x)
|
||||
@ -300,7 +291,7 @@ class EfficientNetFeatures(nn.Module):
|
||||
def __init__(self, block_args, out_indices=(0, 1, 2, 3, 4), feature_location='pre_pwl',
|
||||
in_chans=3, stem_size=32, channel_multiplier=1.0, channel_divisor=8, channel_min=None,
|
||||
output_stride=32, pad_type='', act_layer=nn.ReLU, drop_rate=0., drop_connect_rate=0.,
|
||||
se_kwargs=None, norm_layer=nn.BatchNorm2d, norm_kwargs=None, weight_init='goog'):
|
||||
se_kwargs=None, norm_layer=nn.BatchNorm2d, norm_kwargs=None):
|
||||
super(EfficientNetFeatures, self).__init__()
|
||||
norm_kwargs = norm_kwargs or {}
|
||||
|
||||
@ -326,12 +317,7 @@ class EfficientNetFeatures(nn.Module):
|
||||
self.feature_info = builder.features # builder provides info about feature channels for each block
|
||||
self._in_chs = builder.in_chs
|
||||
|
||||
for m in self.modules():
|
||||
if weight_init == 'goog':
|
||||
efficientnet_init_goog(m)
|
||||
else:
|
||||
efficientnet_init_default(m)
|
||||
|
||||
efficientnet_init_weights(self)
|
||||
if _DEBUG:
|
||||
for k, v in self.feature_info.items():
|
||||
print('Feature idx: {}: Name: {}, Channels: {}'.format(k, v['name'], v['num_chs']))
|
||||
|
||||
@ -358,9 +358,13 @@ class EfficientNetBuilder:
|
||||
return stages
|
||||
|
||||
|
||||
def efficientnet_init_goog(m, n=''):
|
||||
# weight init as per Tensorflow Official impl
|
||||
# https://github.com/tensorflow/tpu/blob/master/models/official/mnasnet/mnasnet_model.py
|
||||
def _init_weight_goog(m, n=''):
|
||||
""" Weight initialization as per Tensorflow official implementations.
|
||||
|
||||
Handles layers in EfficientNet, EfficientNet-CondConv, MixNet, MnasNet, MobileNetV3, etc:
|
||||
* https://github.com/tensorflow/tpu/blob/master/models/official/mnasnet/mnasnet_model.py
|
||||
* https://github.com/tensorflow/tpu/blob/master/models/official/efficientnet/efficientnet_model.py
|
||||
"""
|
||||
if isinstance(m, CondConv2d):
|
||||
fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
|
||||
init_weight_fn = get_condconv_initializer(
|
||||
@ -386,7 +390,8 @@ def efficientnet_init_goog(m, n=''):
|
||||
m.bias.data.zero_()
|
||||
|
||||
|
||||
def efficientnet_init_default(m, n=''):
|
||||
def _init_weight_default(m, n=''):
|
||||
""" Basic ResNet (Kaiming) style weight init"""
|
||||
if isinstance(m, CondConv2d):
|
||||
init_fn = get_condconv_initializer(partial(
|
||||
nn.init.kaiming_normal_, mode='fan_out', nonlinearity='relu'), m.num_experts, m.weight_shape)
|
||||
@ -400,3 +405,8 @@ def efficientnet_init_default(m, n=''):
|
||||
nn.init.kaiming_uniform_(m.weight, mode='fan_in', nonlinearity='linear')
|
||||
|
||||
|
||||
def efficientnet_init_weights(model: nn.Module, init_fn=None):
|
||||
init_fn = init_fn or _init_weight_goog
|
||||
for n, m in model.named_modules():
|
||||
init_fn(m, n)
|
||||
|
||||
|
||||
@ -13,7 +13,7 @@ from collections import OrderedDict
|
||||
|
||||
from .registry import register_model
|
||||
from .helpers import load_pretrained
|
||||
from .adaptive_avgmax_pool import select_adaptive_pool2d
|
||||
from .adaptive_avgmax_pool import SelectAdaptivePool2d
|
||||
from timm.data import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD
|
||||
|
||||
__all__ = ['Xception65', 'Xception71']
|
||||
@ -185,7 +185,6 @@ class Xception65(nn.Module):
|
||||
super(Xception65, self).__init__()
|
||||
self.num_classes = num_classes
|
||||
self.drop_rate = drop_rate
|
||||
self.global_pool = global_pool
|
||||
norm_kwargs = norm_kwargs if norm_kwargs is not None else {}
|
||||
if output_stride == 32:
|
||||
entry_block3_stride = 2
|
||||
@ -249,21 +248,18 @@ class Xception65(nn.Module):
|
||||
1536, self.num_features, 3, stride=1, dilation=exit_block_dilations[1],
|
||||
norm_layer=norm_layer, norm_kwargs=norm_kwargs)
|
||||
self.bn5 = norm_layer(num_features=self.num_features, **norm_kwargs)
|
||||
self.fc = nn.Linear(in_features=self.num_features, out_features=num_classes)
|
||||
self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
||||
self.fc = nn.Linear(self.num_features * self.global_pool.feat_mult(), num_classes)
|
||||
|
||||
def get_classifier(self):
|
||||
return self.fc
|
||||
|
||||
def reset_classifier(self, num_classes, global_pool='avg'):
|
||||
self.num_classes = num_classes
|
||||
self.global_pool = global_pool
|
||||
del self.fc
|
||||
if num_classes:
|
||||
self.fc = nn.Linear(self.num_features, num_classes)
|
||||
else:
|
||||
self.fc = None
|
||||
self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
||||
self.fc = nn.Linear(self.num_features * self.global_pool.feat_mult(), num_classes) if num_classes else None
|
||||
|
||||
def forward_features(self, x, pool=True):
|
||||
def forward_features(self, x):
|
||||
# Entry flow
|
||||
x = self.conv1(x)
|
||||
x = self.bn1(x)
|
||||
@ -299,14 +295,11 @@ class Xception65(nn.Module):
|
||||
x = self.conv5(x)
|
||||
x = self.bn5(x)
|
||||
x = self.relu(x)
|
||||
|
||||
if pool:
|
||||
x = select_adaptive_pool2d(x, pool_type=self.global_pool)
|
||||
x = x.view(x.size(0), -1)
|
||||
return x
|
||||
|
||||
def forward(self, x):
|
||||
x = self.forward_features(x)
|
||||
x = self.global_pool(x).flatten(1)
|
||||
if self.drop_rate:
|
||||
F.dropout(x, self.drop_rate, training=self.training)
|
||||
x = self.fc(x)
|
||||
@ -322,7 +315,6 @@ class Xception71(nn.Module):
|
||||
super(Xception71, self).__init__()
|
||||
self.num_classes = num_classes
|
||||
self.drop_rate = drop_rate
|
||||
self.global_pool = global_pool
|
||||
norm_kwargs = norm_kwargs if norm_kwargs is not None else {}
|
||||
if output_stride == 32:
|
||||
entry_block3_stride = 2
|
||||
@ -393,21 +385,18 @@ class Xception71(nn.Module):
|
||||
1536, self.num_features, 3, stride=1, dilation=exit_block_dilations[1],
|
||||
norm_layer=norm_layer, norm_kwargs=norm_kwargs)
|
||||
self.bn5 = norm_layer(num_features=self.num_features, **norm_kwargs)
|
||||
self.fc = nn.Linear(in_features=self.num_features, out_features=num_classes)
|
||||
self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
||||
self.fc = nn.Linear(self.num_features * self.global_pool.feat_mult(), num_classes)
|
||||
|
||||
def get_classifier(self):
|
||||
return self.fc
|
||||
|
||||
def reset_classifier(self, num_classes, global_pool='avg'):
|
||||
self.num_classes = num_classes
|
||||
self.global_pool = global_pool
|
||||
del self.fc
|
||||
if num_classes:
|
||||
self.fc = nn.Linear(self.num_features, num_classes)
|
||||
else:
|
||||
self.fc = None
|
||||
self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
||||
self.fc = nn.Linear(self.num_features * self.global_pool.feat_mult(), num_classes) if num_classes else None
|
||||
|
||||
def forward_features(self, x, pool=True):
|
||||
def forward_features(self, x):
|
||||
# Entry flow
|
||||
x = self.conv1(x)
|
||||
x = self.bn1(x)
|
||||
@ -443,14 +432,11 @@ class Xception71(nn.Module):
|
||||
x = self.conv5(x)
|
||||
x = self.bn5(x)
|
||||
x = self.relu(x)
|
||||
|
||||
if pool:
|
||||
x = select_adaptive_pool2d(x, pool_type=self.global_pool)
|
||||
x = x.view(x.size(0), -1)
|
||||
return x
|
||||
|
||||
def forward(self, x):
|
||||
x = self.forward_features(x)
|
||||
x = self.global_pool(x).flatten(1)
|
||||
if self.drop_rate:
|
||||
F.dropout(x, self.drop_rate, training=self.training)
|
||||
x = self.fc(x)
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@ -8,7 +8,7 @@ import torch.nn.functional as F
|
||||
|
||||
from .registry import register_model
|
||||
from .helpers import load_pretrained
|
||||
from .adaptive_avgmax_pool import select_adaptive_pool2d
|
||||
from .adaptive_avgmax_pool import SelectAdaptivePool2d
|
||||
from timm.data import IMAGENET_INCEPTION_MEAN, IMAGENET_INCEPTION_STD
|
||||
|
||||
__all__ = ['InceptionResnetV2']
|
||||
@ -226,7 +226,6 @@ class InceptionResnetV2(nn.Module):
|
||||
def __init__(self, num_classes=1001, in_chans=3, drop_rate=0., global_pool='avg'):
|
||||
super(InceptionResnetV2, self).__init__()
|
||||
self.drop_rate = drop_rate
|
||||
self.global_pool = global_pool
|
||||
self.num_classes = num_classes
|
||||
self.num_features = 1536
|
||||
|
||||
@ -287,22 +286,20 @@ class InceptionResnetV2(nn.Module):
|
||||
)
|
||||
self.block8 = Block8(noReLU=True)
|
||||
self.conv2d_7b = BasicConv2d(2080, self.num_features, kernel_size=1, stride=1)
|
||||
self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
||||
# NOTE some variants/checkpoints for this model may have 'last_linear' as the name for the FC
|
||||
self.classif = nn.Linear(self.num_features, num_classes)
|
||||
self.classif = nn.Linear(self.num_features * self.global_pool.feat_mult(), num_classes)
|
||||
|
||||
def get_classifier(self):
|
||||
return self.classif
|
||||
|
||||
def reset_classifier(self, num_classes, global_pool='avg'):
|
||||
self.global_pool = global_pool
|
||||
self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
||||
self.num_classes = num_classes
|
||||
del self.classif
|
||||
if num_classes:
|
||||
self.classif = torch.nn.Linear(self.num_features, num_classes)
|
||||
else:
|
||||
self.classif = None
|
||||
self.classif = nn.Linear(
|
||||
self.num_features * self.global_pool.feat_mult(), num_classes) if num_classes else None
|
||||
|
||||
def forward_features(self, x, pool=True):
|
||||
def forward_features(self, x):
|
||||
x = self.conv2d_1a(x)
|
||||
x = self.conv2d_2a(x)
|
||||
x = self.conv2d_2b(x)
|
||||
@ -318,14 +315,11 @@ class InceptionResnetV2(nn.Module):
|
||||
x = self.repeat_2(x)
|
||||
x = self.block8(x)
|
||||
x = self.conv2d_7b(x)
|
||||
if pool:
|
||||
x = select_adaptive_pool2d(x, self.global_pool)
|
||||
#x = F.avg_pool2d(x, 8, count_include_pad=False)
|
||||
x = x.view(x.size(0), -1)
|
||||
return x
|
||||
|
||||
def forward(self, x):
|
||||
x = self.forward_features(x, pool=True)
|
||||
x = self.forward_features(x)
|
||||
x = self.global_pool(x).flatten(1)
|
||||
if self.drop_rate > 0:
|
||||
x = F.dropout(x, p=self.drop_rate, training=self.training)
|
||||
x = self.classif(x)
|
||||
|
||||
@ -8,7 +8,7 @@ import torch.nn.functional as F
|
||||
|
||||
from .registry import register_model
|
||||
from .helpers import load_pretrained
|
||||
from .adaptive_avgmax_pool import select_adaptive_pool2d
|
||||
from .adaptive_avgmax_pool import SelectAdaptivePool2d
|
||||
from timm.data import IMAGENET_INCEPTION_MEAN, IMAGENET_INCEPTION_STD
|
||||
|
||||
__all__ = ['InceptionV4']
|
||||
@ -244,7 +244,6 @@ class InceptionV4(nn.Module):
|
||||
def __init__(self, num_classes=1001, in_chans=3, drop_rate=0., global_pool='avg'):
|
||||
super(InceptionV4, self).__init__()
|
||||
self.drop_rate = drop_rate
|
||||
self.global_pool = global_pool
|
||||
self.num_classes = num_classes
|
||||
self.num_features = 1536
|
||||
|
||||
@ -272,25 +271,24 @@ class InceptionV4(nn.Module):
|
||||
Inception_C(),
|
||||
Inception_C(),
|
||||
)
|
||||
self.last_linear = nn.Linear(self.num_features, num_classes)
|
||||
self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
||||
self.last_linear = nn.Linear(self.num_features * self.global_pool.feat_mult(), num_classes)
|
||||
|
||||
def get_classifier(self):
|
||||
return self.classif
|
||||
return self.last_linear
|
||||
|
||||
def reset_classifier(self, num_classes, global_pool='avg'):
|
||||
self.global_pool = global_pool
|
||||
self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
||||
self.num_classes = num_classes
|
||||
self.classif = nn.Linear(self.num_features, num_classes)
|
||||
self.last_linear = nn.Linear(
|
||||
self.num_features * self.global_pool.feat_mult(), num_classes) if num_classes else None
|
||||
|
||||
def forward_features(self, x, pool=True):
|
||||
x = self.features(x)
|
||||
if pool:
|
||||
x = select_adaptive_pool2d(x, self.global_pool)
|
||||
x = x.view(x.size(0), -1)
|
||||
return x
|
||||
def forward_features(self, x):
|
||||
return self.features(x)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.forward_features(x)
|
||||
x = self.global_pool(x).flatten(1)
|
||||
if self.drop_rate > 0:
|
||||
x = F.dropout(x, p=self.drop_rate, training=self.training)
|
||||
x = self.last_linear(x)
|
||||
|
||||
@ -75,8 +75,7 @@ class MobileNetV3(nn.Module):
|
||||
|
||||
def __init__(self, block_args, num_classes=1000, in_chans=3, stem_size=16, num_features=1280, head_bias=True,
|
||||
channel_multiplier=1.0, pad_type='', act_layer=nn.ReLU, drop_rate=0., drop_connect_rate=0.,
|
||||
se_kwargs=None, norm_layer=nn.BatchNorm2d, norm_kwargs=None,
|
||||
global_pool='avg', weight_init='goog'):
|
||||
se_kwargs=None, norm_layer=nn.BatchNorm2d, norm_kwargs=None, global_pool='avg'):
|
||||
super(MobileNetV3, self).__init__()
|
||||
|
||||
self.num_classes = num_classes
|
||||
@ -107,11 +106,7 @@ class MobileNetV3(nn.Module):
|
||||
# Classifier
|
||||
self.classifier = nn.Linear(self.num_features * self.global_pool.feat_mult(), self.num_classes)
|
||||
|
||||
for m in self.modules():
|
||||
if weight_init == 'goog':
|
||||
efficientnet_init_goog(m)
|
||||
else:
|
||||
efficientnet_init_default(m)
|
||||
efficientnet_init_weights(self)
|
||||
|
||||
def as_sequential(self):
|
||||
layers = [self.conv_stem, self.bn1, self.act1]
|
||||
@ -126,12 +121,8 @@ class MobileNetV3(nn.Module):
|
||||
def reset_classifier(self, num_classes, global_pool='avg'):
|
||||
self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
||||
self.num_classes = num_classes
|
||||
del self.classifier
|
||||
if num_classes:
|
||||
self.classifier = nn.Linear(
|
||||
self.num_features * self.global_pool.feat_mult(), num_classes)
|
||||
else:
|
||||
self.classifier = None
|
||||
self.classifier = nn.Linear(
|
||||
self.num_features * self.global_pool.feat_mult(), num_classes) if self.num_classes else None
|
||||
|
||||
def forward_features(self, x):
|
||||
x = self.conv_stem(x)
|
||||
@ -161,7 +152,7 @@ class MobileNetV3Features(nn.Module):
|
||||
def __init__(self, block_args, out_indices=(0, 1, 2, 3, 4), feature_location='pre_pwl',
|
||||
in_chans=3, stem_size=16, channel_multiplier=1.0, output_stride=32, pad_type='',
|
||||
act_layer=nn.ReLU, drop_rate=0., drop_connect_rate=0., se_kwargs=None,
|
||||
norm_layer=nn.BatchNorm2d, norm_kwargs=None, weight_init='goog'):
|
||||
norm_layer=nn.BatchNorm2d, norm_kwargs=None):
|
||||
super(MobileNetV3Features, self).__init__()
|
||||
norm_kwargs = norm_kwargs or {}
|
||||
|
||||
@ -187,12 +178,7 @@ class MobileNetV3Features(nn.Module):
|
||||
self.feature_info = builder.features # builder provides info about feature channels for each block
|
||||
self._in_chs = builder.in_chs
|
||||
|
||||
for m in self.modules():
|
||||
if weight_init == 'goog':
|
||||
efficientnet_init_goog(m)
|
||||
else:
|
||||
efficientnet_init_default(m)
|
||||
|
||||
efficientnet_init_weights(self)
|
||||
if _DEBUG:
|
||||
for k, v in self.feature_info.items():
|
||||
print('Feature idx: {}: Name: {}, Channels: {}'.format(k, v['name'], v['num_chs']))
|
||||
|
||||
@ -556,8 +556,18 @@ class NASNetALarge(nn.Module):
|
||||
self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
||||
self.last_linear = nn.Linear(self.num_features * self.global_pool.feat_mult(), num_classes)
|
||||
|
||||
def forward_features(self, input, pool=True):
|
||||
x_conv0 = self.conv0(input)
|
||||
def get_classifier(self):
|
||||
return self.last_linear
|
||||
|
||||
def reset_classifier(self, num_classes, global_pool='avg'):
|
||||
self.num_classes = num_classes
|
||||
self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
||||
del self.last_linear
|
||||
self.last_linear = nn.Linear(
|
||||
self.num_features * self.global_pool.feat_mult(), num_classes) if num_classes else None
|
||||
|
||||
def forward_features(self, x):
|
||||
x_conv0 = self.conv0(x)
|
||||
x_stem_0 = self.cell_stem_0(x_conv0)
|
||||
x_stem_1 = self.cell_stem_1(x_conv0, x_stem_0)
|
||||
|
||||
@ -586,13 +596,11 @@ class NASNetALarge(nn.Module):
|
||||
x_cell_16 = self.cell_16(x_cell_15, x_cell_14)
|
||||
x_cell_17 = self.cell_17(x_cell_16, x_cell_15)
|
||||
x = self.relu(x_cell_17)
|
||||
if pool:
|
||||
x = self.global_pool(x)
|
||||
x = x.view(x.size(0), -1)
|
||||
return x
|
||||
|
||||
def forward(self, input):
|
||||
x = self.forward_features(input)
|
||||
def forward(self, x):
|
||||
x = self.forward_features(x)
|
||||
x = self.global_pool(x).flatten(1)
|
||||
if self.drop_rate > 0:
|
||||
x = F.dropout(x, self.drop_rate, training=self.training)
|
||||
x = self.last_linear(x)
|
||||
|
||||
@ -355,7 +355,7 @@ class PNASNet5Large(nn.Module):
|
||||
else:
|
||||
self.last_linear = None
|
||||
|
||||
def forward_features(self, x, pool=True):
|
||||
def forward_features(self, x):
|
||||
x_conv_0 = self.conv_0(x)
|
||||
x_stem_0 = self.cell_stem_0(x_conv_0)
|
||||
x_stem_1 = self.cell_stem_1(x_conv_0, x_stem_0)
|
||||
@ -372,13 +372,11 @@ class PNASNet5Large(nn.Module):
|
||||
x_cell_10 = self.cell_10(x_cell_8, x_cell_9)
|
||||
x_cell_11 = self.cell_11(x_cell_9, x_cell_10)
|
||||
x = self.relu(x_cell_11)
|
||||
if pool:
|
||||
x = self.global_pool(x)
|
||||
x = x.view(x.size(0), -1)
|
||||
return x
|
||||
|
||||
def forward(self, input):
|
||||
x = self.forward_features(input)
|
||||
def forward(self, x):
|
||||
x = self.forward_features(x)
|
||||
x = self.global_pool(x).flatten(1)
|
||||
if self.drop_rate > 0:
|
||||
x = F.dropout(x, self.drop_rate, training=self.training)
|
||||
x = self.last_linear(x)
|
||||
|
||||
@ -17,7 +17,7 @@ from .adaptive_avgmax_pool import SelectAdaptivePool2d
|
||||
from timm.data import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD
|
||||
|
||||
|
||||
__all__ = ['ResNet'] # model_registry will add each entrypoint fn to this
|
||||
__all__ = ['ResNet', 'BasicBlock', 'Bottleneck'] # model_registry will add each entrypoint fn to this
|
||||
|
||||
|
||||
def _cfg(url='', **kwargs):
|
||||
@ -374,12 +374,9 @@ class ResNet(nn.Module):
|
||||
self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
||||
self.num_classes = num_classes
|
||||
del self.fc
|
||||
if num_classes:
|
||||
self.fc = nn.Linear(self.num_features * self.global_pool.feat_mult(), num_classes)
|
||||
else:
|
||||
self.fc = None
|
||||
self.fc = nn.Linear(self.num_features * self.global_pool.feat_mult(), num_classes) if num_classes else None
|
||||
|
||||
def forward_features(self, x, pool=True):
|
||||
def forward_features(self, x):
|
||||
x = self.conv1(x)
|
||||
x = self.bn1(x)
|
||||
x = self.relu(x)
|
||||
@ -389,14 +386,11 @@ class ResNet(nn.Module):
|
||||
x = self.layer2(x)
|
||||
x = self.layer3(x)
|
||||
x = self.layer4(x)
|
||||
|
||||
if pool:
|
||||
x = self.global_pool(x)
|
||||
x = x.view(x.size(0), -1)
|
||||
return x
|
||||
|
||||
def forward(self, x):
|
||||
x = self.forward_features(x)
|
||||
x = self.global_pool(x).flatten(1)
|
||||
if self.drop_rate > 0.:
|
||||
x = F.dropout(x, p=self.drop_rate, training=self.training)
|
||||
x = self.fc(x)
|
||||
|
||||
@ -274,6 +274,7 @@ class SENet(nn.Module):
|
||||
super(SENet, self).__init__()
|
||||
self.inplanes = inplanes
|
||||
self.num_classes = num_classes
|
||||
self.drop_rate = drop_rate
|
||||
if input_3x3:
|
||||
layer0_modules = [
|
||||
('conv1', nn.Conv2d(in_chans, 64, 3, stride=2, padding=1, bias=False)),
|
||||
@ -337,7 +338,6 @@ class SENet(nn.Module):
|
||||
downsample_padding=downsample_padding
|
||||
)
|
||||
self.avg_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
||||
self.drop_rate = drop_rate
|
||||
self.num_features = 512 * block.expansion
|
||||
self.last_linear = nn.Linear(self.num_features, num_classes)
|
||||
|
||||
@ -366,26 +366,25 @@ class SENet(nn.Module):
|
||||
def get_classifier(self):
|
||||
return self.last_linear
|
||||
|
||||
def reset_classifier(self, num_classes):
|
||||
def reset_classifier(self, num_classes, global_pool='avg'):
|
||||
self.num_classes = num_classes
|
||||
self.avg_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
||||
del self.last_linear
|
||||
if num_classes:
|
||||
self.last_linear = nn.Linear(self.num_features, num_classes)
|
||||
self.last_linear = nn.Linear(self.num_features * self.avg_pool.feat_mult(), num_classes)
|
||||
else:
|
||||
self.last_linear = None
|
||||
|
||||
def forward_features(self, x, pool=True):
|
||||
def forward_features(self, x):
|
||||
x = self.layer0(x)
|
||||
x = self.layer1(x)
|
||||
x = self.layer2(x)
|
||||
x = self.layer3(x)
|
||||
x = self.layer4(x)
|
||||
if pool:
|
||||
x = self.avg_pool(x)
|
||||
x = x.view(x.size(0), -1)
|
||||
return x
|
||||
|
||||
def logits(self, x):
|
||||
x = self.avg_pool(x).flatten(1)
|
||||
if self.drop_rate > 0.:
|
||||
x = F.dropout(x, p=self.drop_rate, training=self.training)
|
||||
x = self.last_linear(x)
|
||||
|
||||
@ -20,7 +20,7 @@ class TestTimePoolHead(nn.Module):
|
||||
self.base.reset_classifier(0) # delete original fc layer
|
||||
|
||||
def forward(self, x):
|
||||
x = self.base.forward_features(x, pool=False)
|
||||
x = self.base.forward_features(x)
|
||||
x = F.avg_pool2d(x, kernel_size=self.original_pool, stride=1)
|
||||
x = self.fc(x)
|
||||
x = adaptive_avgmax_pool2d(x, 1)
|
||||
|
||||
@ -29,7 +29,7 @@ import torch.nn.functional as F
|
||||
|
||||
from .registry import register_model
|
||||
from .helpers import load_pretrained
|
||||
from .adaptive_avgmax_pool import select_adaptive_pool2d
|
||||
from .adaptive_avgmax_pool import SelectAdaptivePool2d
|
||||
|
||||
__all__ = ['Xception']
|
||||
|
||||
@ -163,7 +163,8 @@ class Xception(nn.Module):
|
||||
self.conv4 = SeparableConv2d(1536, self.num_features, 3, 1, 1)
|
||||
self.bn4 = nn.BatchNorm2d(self.num_features)
|
||||
|
||||
self.fc = nn.Linear(self.num_features, num_classes)
|
||||
self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
||||
self.fc = nn.Linear(self.num_features * self.global_pool.feat_mult(), num_classes)
|
||||
|
||||
# #------- init weights --------
|
||||
for m in self.modules():
|
||||
@ -178,15 +179,12 @@ class Xception(nn.Module):
|
||||
|
||||
def reset_classifier(self, num_classes, global_pool='avg'):
|
||||
self.num_classes = num_classes
|
||||
self.global_pool = global_pool
|
||||
self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
||||
del self.fc
|
||||
if num_classes:
|
||||
self.fc = nn.Linear(self.num_features, num_classes)
|
||||
else:
|
||||
self.fc = None
|
||||
self.fc = nn.Linear(self.num_features * self.global_pool.feat_mult(), num_classes) if num_classes else None
|
||||
|
||||
def forward_features(self, input, pool=True):
|
||||
x = self.conv1(input)
|
||||
def forward_features(self, x):
|
||||
x = self.conv1(x)
|
||||
x = self.bn1(x)
|
||||
x = self.relu(x)
|
||||
|
||||
@ -214,14 +212,11 @@ class Xception(nn.Module):
|
||||
x = self.conv4(x)
|
||||
x = self.bn4(x)
|
||||
x = self.relu(x)
|
||||
|
||||
if pool:
|
||||
x = select_adaptive_pool2d(x, pool_type=self.global_pool)
|
||||
x = x.view(x.size(0), -1)
|
||||
return x
|
||||
|
||||
def forward(self, input):
|
||||
x = self.forward_features(input)
|
||||
def forward(self, x):
|
||||
x = self.forward_features(x)
|
||||
x = self.global_pool(x).flatten(1)
|
||||
if self.drop_rate:
|
||||
F.dropout(x, self.drop_rate, training=self.training)
|
||||
x = self.fc(x)
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user