Open Arash-HR opened 4 years ago
Make sure you have the latest tensorflow version installed, which is 2.3.0
@Bloodrammer
I have installed the latest version of Tensorflow
>>> import tensorflow as tf
>>> print(tf.__version__)
2.3.0
How about this? The different version of Python might be used in running demo.
>>> import tensorflow as tf
>>> print(tf.__version__)
2.3.0
>>> tf.keras.applications.__dict__.keys()
dict_keys(['__name__', '__doc__', '__package__', '__loader__', '__spec__', '__path__', '__file__', '__cached__', '__builtins__', '_sys', 'densenet', 'efficientnet', 'imagenet_utils', 'inception_resnet_v2', 'inception_v3', 'mobilenet', 'mobilenet_v2', 'nasnet', 'resnet', 'resnet50', 'resnet_v2', 'vgg16', 'vgg19', 'xception', 'DenseNet121', 'DenseNet169', 'DenseNet201', 'EfficientNetB0', 'EfficientNetB1', 'EfficientNetB2', 'EfficientNetB3', 'EfficientNetB4', 'EfficientNetB5', 'EfficientNetB6', 'EfficientNetB7', 'InceptionResNetV2', 'InceptionV3', 'MobileNet', 'MobileNetV2', 'NASNetLarge', 'NASNetMobile', 'ResNet101', 'ResNet152', 'ResNet50', 'ResNet101V2', 'ResNet152V2', 'ResNet50V2', 'VGG16', 'VGG19', 'Xception'])
@yu4u
>>> import tensorflow as tf
>>> print(tf.__version__)
2.3.0
>>> tf.keras.applications.__dict__.keys()
dict_keys(['__name__', '__doc__', '__package__', '__loader__', '__spec__', '__path__', '__file__', '__cached__', '__builtins__', '_sys', 'densenet', 'efficientnet', 'imagenet_utils', 'inception_resnet_v2', 'inception_v3', 'mobilenet', 'mobilenet_v2', 'nasnet', 'resnet', 'resnet50', 'resnet_v2', 'vgg16', 'vgg19', 'xception', 'DenseNet121', 'DenseNet169', 'DenseNet201', 'EfficientNetB0', 'EfficientNetB1', 'EfficientNetB2', 'EfficientNetB3', 'EfficientNetB4', 'EfficientNetB5', 'EfficientNetB6', 'EfficientNetB7', 'InceptionResNetV2', 'InceptionV3', 'MobileNet', 'MobileNetV2', 'NASNetLarge', 'NASNetMobile', 'ResNet101', 'ResNet152', 'ResNet50', 'ResNet101V2', 'ResNet152V2', 'ResNet50V2', 'VGG16', 'VGG19', 'Xception'])
It's strange. EfficientNetB3 does exist.
@yu4u , Hello, EfficientNetB3 ' s input size is 300 300, but the age and gender estimate model is 224 224. How can we get the EfficientNetB3 pretrained model?
But another error will occur.
ValueError: You are trying to load a weight file containing 211 layers into a model with 210 layers.
How can I reproduce the error?
My enviroment:
cuda9.0
tensorflow == v1.12.0
keras == 2.2.4
I add EfficientNet to keras.applications. I run demo.py and get the error.
ValueError: You are trying to load a weight file containing 211 layers into a model with 210 layers.
Please use tensorflow>=2.3.0
Sorry, My cuda version doesn‘t support it. It's not easy for me to change the servers' env.
cuda10.1 tensorflow-v2.3.0 is ok.
Hi when run demo.py , get this error ;
I was worked with this repo without any problem before recent commits , but now ... There is someone to help me ?