mobilenet_v2_keras

mobilenet_v2_keras copied to clipboard

Dear Sir, Sorry to trouble you. In your mobilenet_v2 python script, which mentions the provided BASE_WEIGHT_PATH (https://github.com/JonathanCMitchell/mobilenet_v2_keras/releases/download/v1.1/) is no longer accessible. Does the website link have changed, or is not...

RoraChen

We can't easily freeze all model weights before certain layer, as this layer can be in the middle of Inverted Residual Block, and it is bad to freeze one half...

achukhrov-ffr-team

Hi, this is more of a question concerning your preferences for preprocess_input

1

Hi, I'm looking at your code and comparing it to the usual way of preprocessing numpy arrays into formats for training with Keras. Is there any particular reason why you...

RadEdje

ValueError: Shapes (3, 3, 3, 32) and (48, 3, 3, 3) are incompatible

1

My tensorflow version is 1.14.0 I have downloaded the "mobilenet_v2_weights_tf_dim_ordering_tf_kernels_1.4_224_no_top.h5" and I am trying to load the model: ``` local_weights_file = '../mobilenet_v2_weights_tf_dim_ordering_tf_kernels_1.4_224_no_top.h5' input_tensor = Input(shape=(224,224, 3)) pre_trained_model = MobileNetV2( input_tensor...

HRKpython

I know that that image is scaled to be in range [-1, 1] when training. But I want to also know whether the images were deformed (resized without caring aspect...

offchan42

License of these weights

1

Hi! Thank you very much for making all these weights available. I have been wondering what license you may want to apply, though? Best,

CaveSven

using the new mobileNet weights.

2

Hello, I'm really new to machine learning, Keras, and tensorflow. I'm currently looking for an efficient way to retrain a mobileNetV2 with imagenetWeights when I saw your github repo. Sorry...

RadEdje

Error in the naming of the h5 model

1

Hi, I notice that there has been an error in labeling the models. It think should be label as '0.25' instead of 0.35?

savageyusuff