Open moonsh opened 1 year ago
Thank you for sharing this work. It helps me a lot.
I am trying to use mobilenetv3 backbone but I got some weight size mismatching problems. I used the below additional script for mobilenetv3. Is there something I didn't include ?
elif model_name.startswith('mobilenet'): from options import FLAGS FLAGS.centered_stride = True bn = keras.layers.BatchNormalization
import backbones.mobilenet_v3 class MyLayers(backbones.mobilenet_v3.VersionAwareLayers): def __getattr__(self, name): if name == 'BatchNormalization': return bn return super().__getattr__(name) arch = model_name arch = arch[:-4] if arch.endswith('mini') else arch classname = f'MobileNet{arch[len("mobilenet"):]} mod = getattr(backbones.mobilenet_v3, classname)( include_top=False, weights=None, minimalistic=False, input_shape=(None, None, 3), layers=MyLayers(), centered_stride=FLAGS.centered_stride, pooling=None)
I am also trying to do it with mobilenet. Any luck?
Thank you for sharing this work. It helps me a lot.
I am trying to use mobilenetv3 backbone but I got some weight size mismatching problems. I used the below additional script for mobilenetv3. Is there something I didn't include ?
elif model_name.startswith('mobilenet'): from options import FLAGS FLAGS.centered_stride = True bn = keras.layers.BatchNormalization