Dear Malka,

for scientific purpose I think PyTorch is much simpler and more straightforward.

Also it's a great replacement for numpy to use the power of GPUs.

http://pytorch.org/

I've noticed that tensorflow is hard to work with.

Dear Malka,

for scientific purpose I think PyTorch is much simpler and more straightforward.

Also it's a great replacement for numpy to use the power of GPUs.

http://pytorch.org/

I've noticed that tensorflow is hard to work with.

Thanks Mohammadreza and Rahman.

Yes first we used Spyder and then noticed the Jupyter Notebook is convenient. Also noticed some programms works well with Spyder without errors.

Malka

Keras is more like a wrapper for Tensorflow/Theano/CNTK which supports most of the commonly used DL algorithms. If you would like to quickly apply and test some existing DL framework, then Keras would be your way to go.

If you would like to delve into research and want a fine-grained control over all of your parameters and network structure, then you could work directly on Tensorflow. (I'd also like to add that Theano's development is frozen as of now due to the popularity of the other deep learning packages such as Tensorflow.)

Thanks, Ebenezer. Yes this is for the research purpose and we want the fine-grained control over all of the parameters. We will explore the Theano development.

I use Keras with Tensorflow backend( in spyder there is a variable explorer that I really like). The model construction is comparatively simpler in keras, you can always fine tune things if you understand the network parameters(You might have to look into the keras documentation for doing so).

For example: if I want to change the learning rate of an 'Adam' optimizer in keras, I import the function and change values accordingly:

from keras.optimizers import adam

opt=adam(lr=0.002, beta_1=0.9, beta_2=0.999, epsilon=1e-08)

model.compile(optimizer =opt, loss = 'categorical_crossentropy', metrics=['accuracy'])

It is also possible to visualise the keras.callbacks using tensorboard. So I would recommend Keras.

Thanks Tahmina for the comprehensive answer. Yes, we used 'Adam' optimizer in Keras.

Personally, I am with Keras and Pycharm/Jupiter when dealing with imaging stuff. For flat data, I would use H2O.

If you’re end user, I recommend keras, developers then tensorflow

tensorgraph debugger is my best friend

It depends on the use-case. As some people have already pointed out, Keras is a wrapper for Tensorflow and Theano in Python. You can either use Tensorflow directly in Python, or you can access Tensorflow using Keras.

If you want to train, test networks without digging in deep, Keras (or PyTorch) should be more than enough. If you want to dig deep, understand and implement DNNs from scratch, Tensorflow should be the better & flexible option.