deeplift
deeplift copied to clipboard
kundajelab
Public facing deeplift repo
HI Avanti, I used Tensorflow 2.0 to build the model and it was saved in h5 format. But when I used convert_model_from_saved_files method as suggested in the tutorial, I get...
Hello, I am trying to apply deeplift on my image dataset with densenet121 model but I get error: my code is: import deeplift from deeplift.layers import NonlinearMxtsMode from deeplift.conversion import...
Hi, I'm trying to analise a model I built using the Tensorflow.keras implementation of Keras instead of Keras proper. I get this error when I try to call `kc.convert_model_from_saved_files`: ```~/anaconda3/envs/tensorflow_p36/lib/python3.6/site-packages/deeplift/conversion/kerasapi_conversion.py...
Hi, I am using Keras (V 2.2.4) and my model is LRCN (a combination of CNN + LSTM). You can see my code here: https://github.com/AmirHoseinSafari/LRCN-drug-resistance/blob/master/models/Bayesian_optimizer.py I am trying to run...
Hey! While calculating the 'scores', if I use the first row of my test data for input_data_list, as follows: `scores = np.array(deeplift_contribs_func(task_idx=0, input_data_list=[xtest.iloc[[0]]], batch_size=10, progress_update=1000))` Question 1: Can I use...
Hi, is there support for Keras LocallyConnected2D and LocallyConnected1D layers, which are basically CNN filters with different weights for each patch of the image.
Hi Avanti, Thanks for your amazing work on deepLIFT. Currently, I have problem using deepLIFT with a Keras model using a Minimum layer, which pulls computation from K separated paths,...
Hi Avanti and others, Thank you very much for this great package. I would like to use your package to compute the feature contribution for my research problem. I used...
Hi @AvantiShri, i have two questions: i have used deeplift to compute importance scores for my sequences (true positive and true negative predictions). I wanted to get a logo representation...
Hi, My network involves simple residual connection structures that use keras Add layer, it seems this type of structure is supported according to your latest work with "BPnet" paper. Do...
