efficientnet
efficientnet copied to clipboard
qubvel
Implementation of EfficientNet model. Keras and TensorFlow Keras.
How to convert resnet to efficientnet on Mask R-CNN backbone? mask r cnn is too slow.. so i hope to change the backbone. but face the wall... help me..
every time I am getting this error. Please HELP.
I trained efficientnet model (efficientnetB2 to be precised), saved it but getting different accuracy result after loaded and evaluated the model with same test dataset. Only saving it as h5py...
I am trying to use 3 'EfficientNetB7' backbones with different input size in the same model but I get the following error. Is there a way to change the name...
Code: `!pip install -U --pre efficientnet` `import efficientnet.tfkeras as ef` `base_net=ef.EfficientNetL2(weights='noisy-student', include_top=False, input_shape= (224,224,3),pooling='max')` Error: `--------------------------------------------------------------------------- ValueError Traceback (most recent call last) in () ----> 1 base_net=ef.EfficientNetL2(weights='noisy-student', include_top=False, input_shape=(224,224,3),pooling='max') 18...
import efficientnet.keras as efn base_model = efn.EfficientNetB7(weights=None, include_top=False,drop_connect_rate=0.4) model.fit fails for the error "ValueError: rate must be a scalar tensor or a float in the range [0, 1), got 1"...
Dear Author， Thanks for sharing your code. But I didn't find the code about gird search of alpha beta and gamma. Which file is it in？ I am looking forward...
I am getting this error. If I downgrade to version 0.0.2 I don't get this error instead, I get NameError: name 'drop_connect_rate' is not defined
Hello, it seems that the efficientnetL2 is having problem i tried to load model but i got an error for both imagenet and noisy student checkpoint the error message is...
When training efficientnet-b0 on Cifar 100, while the reported results are ~90% accuracy, the model achieves an accuracy of around 7% (Cifar 10 achieves around 40% accuracy). I've explored several...
