keras-applications

keras-applications copied to clipboard

AttributeError: module 'tensorflow.keras.applications' has no attribute 'EfficientNetB0'

4

In the [doc](https://keras.io/api/applications/) has [EfficientNet](https://keras.io/api/applications/efficientnet/#efficientnetb0-function) but cannot use it. When I coding it show me an error `AttributeError: module 'tensorflow.keras.applications' has no attribute 'EfficientNetB0'` . I use TensorFlow 2.2.0 and...

5hyfilm-zz

### Summary ### Environment - Python version: 3.7 - Keras version: 2.4.0 - Keras-applications version: 1.0.8 - Keras backend with version: not installed ### Logs or source codes for reproduction...

RobinV760

### Summary I think that there is a missing layer in the implementation of Inceptionv3. According to the paper C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna,...

LucaUrbinati44

The drop connect rate (aka survival rate) is incorrect

9

I originally posted this as an issue here: https://github.com/qubvel/efficientnet/issues/135 However I noticed the two implementations were the same and the error exists here as well, so I decided to post...

xhluca

cannot import efficientnet implementation in keras_applications AttributeError: module 'keras_applications' has no attribute 'efficientnet'

1

### Summary ### Environment - Python version: 3.7.7 - Keras version:2.3.1 - Keras-applications version:1.0.8 - Keras backend with version: ### Logs or source codes for reproduction

vamshi-vk

Is there any plan to provide shufflenet v2 model and pre-trained weights? Thank you very much for any response!

darcula1993

### Summary It seems like in the case of DenseNet and ResNet, the weights are released on the `keras-applications` repo: https://github.com/keras-team/keras-applications/blob/bc89834ed36935ab4a4994446e34ff81c0d8e1b7/keras_applications/densenet.py#L27-L29 https://github.com/keras-team/keras-applications/blob/bc89834ed36935ab4a4994446e34ff81c0d8e1b7/keras_applications/resnet_common.py#L41-L43 In the case of EfficientNet, the weights come...

xhluca

InceptionResnetV2 summary() seems to be another network as it does not look like the one in the paper.

1

# Summary Importing the model of InceptionResnetV2 seems to be importing another model instead. ### Environment - Python version: 3.8.2 - Keras version: 2.3.1 - Keras-applications version: 1.0.8 ### Logs...

hamddan4

Imagenet pretrained weights not match the current implementation of ResNext, thanks

2

I am using ResNext50 in tensorflow.keras.application.resnet and also the ImageNet pretrained weights downloaded from https://github.com/keras-team/keras-applications/releases/download/resnet/resnext50_weights_tf_dim_ordering_tf_kernels_notop.h5. However, it seems the latest ResNext implementation does not match the weights. For example, if...

junyongyou

Add InceptionV4 pretrianed model

4

According Google's research : https://arxiv.org/abs/1805.08974 Inception-V4 shows best performance on fine-tune, while keras-application still not include inception-v4 pretrained model. Add an official implementation will be very helpful, thank u.

lichuanx