Deep Learning Editor
J'aime 1
Compare Deep Learning Studio vs. Neural Network Console vs. Neural
Network Modeler vs. NVIDIA Digit
Nom | DEEP COGNITION - Deep Learning Studio | SONY - Neural Network Console | IBM - Neural Network Modeler | NVIDIA - Digit | Comment |
---|---|---|---|---|---|
Version of the software | 2.0 | Current | 1.1 | 6.0 | For NNC and NNM it is the version currently available on their Cloud. |
Underlaying Framework | Apache MXNet | SONY Neural Netwok Libraries | Theano Tensorflow/Keras Caffe (v1) | Tensorflow | |
Development Activity | Important (2 enhanced versions have been release recently) | Unknown NNL - github is here : github.com/..." | Unkown | Important | NNC - Activity on the underlaying framework (NNL) is weak. |
GPUs | CUDA compatible | ??? | Depends on the target Framework | CUDA compatible | |
DL MODEL EDITOR | |||||
Graphical editor provided | Oui | Oui | Oui | Non Changing the model is possible by editing the network graph" | |
DL models supported | |||||
- CNN | Oui | Oui | Oui | Oui | |
- LSTM | Oui | Oui | Oui | ||
- MLP / Auto-encoders | Oui | Oui | Oui | ||
- RNN | Oui | Oui | |||
Pretained Networks | Oui (Resnet50, InceptionV3, SqueezeNet, VGG16, VGG19, WideResNet) | Non | Non | Oui | |
Use Keras API | Oui | Non | Non | ||
Save Keras HDFS file (.h5) | Oui | Non | |||
Save Keras model .yaml file | Non | Non | |||
Save Keras model file | Non | Non | |||
Load Keras model .yaml file | Oui | Non | |||
Load Keras HDFS file (.h5) | Oui | Non | |||
Code generation | Non | Non | Oui | ||
- Theano | Non | Non | Oui | ||
- Tensorflow/Keras | Non | Non | Oui | ||
- Caffe (v1) | Non | Non | Oui | ||
Custom cost function | Oui | Non | Non | ||
Load Keras Models + Weights | Oui | Non | |||
Load Caffe Models + Weights | Non | Non | Oui | ||
Load Keras Code | ??? | ||||
Model checker | Oui | Oui | Oui | Non | |
Datasets Management | Oui | Oui | Non | Oui | |
Experiments Mangement | Oui | Non | |||
- Exp comparison | Oui | ||||
- Prev. Exp loader | Yes | ??? | N/A | ||
TRAINING | |||||
DL model training | Oui | Oui | Non | Oui | |
Tune learning parameter | Oui | Oui | |||
Live performance monitoring | Oui | Non | |||
INFERENCE | |||||
Inference available | Oui | Oui | Non | Oui | |
Results browser | Oui | Non | |||
View Valid/test set inference | Oui | Oui | |||
Confusion matrix | Non | Oui | |||
Visualize intermediate layer activation | Oui | Non | |||
User test int | Oui | Non | |||
DEPLOIEMENT | |||||
- Rest API | Oui | Oui On DC server | |||
PLATFORM | |||||
- Cloud | Oui | Oui | |||
but no computing environnement" | Oui | ||||
- Cloud Trial period | Oui | Oui | Oui | ||
- Desktop | Oui (any platform with python) | Non | Oui | ||
OTHER | |||||
AutoML | Oui | Non | Non | Non | |
Browser | Oui | Non | |||
Environment management | Oui | Non | Non | ||
Python shell | Oui | Non | Non | ||
Jupyter notebook | Oui | Non | Non | ||
Documentation | "Minimal | ||||
(Keras API)" | "Minimal | ||||
(SONY Neural Network Library)" | ??? | ||||
Tutorials | Oui | Oui | Oui | ||
Web Site | deepcognition.ai | sony.com/... | mybluemix.net/... | nvidia.com/... |
Avis utilisateurs et commentaires