-
different batch size
```
NASNetMobile_1: 56.6741931512655
NASNetMobile_4: 70.56445293510752
NASNetMobile_8: 81.44838344875278
```
different models
```
NASNetMobile_1: 56.89726058517501
Effi…
-
All Keras Applications work correctly with the torch backend except NASNetMobile. It runs, but its predictions are incorrect. To investigate.
-
Add the following Keras applications backbones:
* `MobileNetV2`
* `NASNetMobile`
* `DenseNet121`
* `DenseNet169`
* `DenseNet201`
* `Xception`
* `InceptionV3`
* `ResNetXt50`
-
As it stands there 6 pre-trained models availible for fine tuning:
- MobileNetV2
- InceptionV3
- VGG16
- VGG19
- NASNetMobile
- SimpleCnnModel
It is not however from that which I can see comm…
-
-
#### Feature Request
I've converted a bunch of Keras models into the Dl4j .zip format for WekaDeeplearning4j, a Weka wrapper for Dl4j. I was wondering whether the Dl4j maintainers would be interest…
-
Getting
```
Internal error occurred (please report it at https://github.com/itislab/alpheus/issues): Failed to compute the artefacts:
Newtonsoft.Json.JsonWriterException: Token PropertyName…
-
Hi, I found a pre-trained model named
seresnext50_imagenet_1000_no_top_v2.h5
in your release,
however, I cound not load it，so please tell me how to use it？
Thx.
-
Hi
when run demo.py , get this error ;
```
File "demo.py", line 92, in main
model = get_model(cfg)
File "/home/arash/Desktop/age-gender-estimation/src/factory.py", line 8, in get_model
…
-
**System information**
- Have I written custom code (as opposed to using example directory): yes
- OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Linux Ubuntu 16.04
- TensorFlow backe…