deep-learning-models
deep-learning-models copied to clipboard
fchollet
Keras code and weights files for popular deep learning models.
The original paper states that "The training was regularised by weight decay (the L2 penalty multiplier set to 5 · 10−4) and **dropout regularisation** for the first two fully-connected layers...
Dear all, My module is : model = Sequential() model.add(InputLayer(input_shape=(img_size_flat,))) #784->(28,28,1) model.add(Reshape(img_shape_full)) model.add(Conv2D(kernel_size=5, strides=1, filters=16, padding='same', activation='relu', name='layer_conv1')) model.add(MaxPooling2D(pool_size=2, strides=2)) model.add(Conv2D(kernel_size=5, strides=1, filters=36, padding='same', activation='relu', name='layer_conv2')) model.add(MaxPooling2D(pool_size=2, strides=2)) model.add(Flatten()) model.add(Dense(128,...
Function "_obtain_input_shape" in latest keras must have "require_flatten=include_top" instead of "include_top=include_top"
For the function "_obtain_input_shape", include_top=include_top does not work in new keras version and had to be changed to require_flatten= include_top.
Hi guys, I have a question regarding to the speed of prediction when using pre-trained Xception Model. It takes around 1.4 s to predict a single picture. I assume it...
In your paper https://arxiv.org/pdf/1610.02357.pdf , the Xception model performs exceptionally well on a large dataset (the JFT one). Would it be possible to share the pre-trained weights for the model...
I used the following code following example in Readme.md ``` base_model = InceptionV3(include_top=False, weights='imagenet') model = Model(input=base_model.input, output=base_model.get_layer('pool_3').output) img_path = 'elephant.jpg' img = image.load_img(img_path, target_size=(224, 224)) x = image.img_to_array(img) x...
where I can download the weigths for API version 2?
Hi, I want to train my [WR-Inception Networks](https://arxiv.org/abs/1702.01243) from scratch by using Keras. Could you give me some advices ? Thanks in advance.
