deeplift
deeplift copied to clipboard
getting non zero prediction difference
Hi,
When applying deeplift over the dataset of "cats and dogs" with the same architecture as provided in Mnist examples. The difference in predictions is coming to be a non-zero value.
Model
model = Sequential() model.add(Conv2D(filters=32, kernel_size=(4,4), strides=(2,2), input_shape=(1, 150, 150))) model.add(Activation("relu")) model.add(Conv2D(filters=64, kernel_size=(4,4), strides=(2,2))) model.add(Activation("relu")) model.add(Dropout(0.25)) model.add(Flatten()) model.add(Dense(units=128)) model.add(Activation("relu")) model.add(Dropout(0.5)) model.add(Dense(units=2)) model.add(Activation("softmax")) from keras.optimizers import Adam model.compile(optimizer=Adam(lr=0.001), loss='categorical_crossentropy', metrics=['accuracy'])
keras version : 2.2.0 tensorflow version : 1.10.1
I started with some another architecture but it was showing the difference so for a trial, I changed the architecture same as that used in Mnist example but then I am getting the difference again.
How big is the difference you are observing?
On Tue, Jun 4, 2019 at 5:30 AM Muskaan Jain [email protected] wrote:
Hi,
When applying deeplift over the dataset of "cats and dogs" with the same architecture as provided in Mnist examples. The difference in predictions is coming to be a non-zero value.
Model
model = Sequential() model.add(Conv2D(filters=32, kernel_size=(4,4), strides=(2,2), input_shape=(1, 150, 150))) model.add(Activation("relu")) model.add(Conv2D(filters=64, kernel_size=(4,4), strides=(2,2))) model.add(Activation("relu")) model.add(Dropout(0.25)) model.add(Flatten()) model.add(Dense(units=128)) model.add(Activation("relu")) model.add(Dropout(0.5)) model.add(Dense(units=2)) model.add(Activation("softmax")) from keras.optimizers import Adam model.compile(optimizer=Adam(lr=0.001), loss='categorical_crossentropy', metrics=['accuracy'])
keras version : 2.2.0 tensorflow version : 1.10.1
I started with some another architecture but it was showing the difference so for a trial, I changed the architecture same as that used in Mnist example but then I am getting the difference again.
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/kundajelab/deeplift/issues/80?email_source=notifications&email_token=AARSFBUXTTBXHKWBGKSU2B3PYZN53A5CNFSM4HS323KKYY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4GXQPXIQ, or mute the thread https://github.com/notifications/unsubscribe-auth/AARSFBWDGGSV5U342BMW4HTPYZN53ANCNFSM4HS323KA .
-- Sent from my phone, please excuse brevity/typos
difference in predictions: 0.93792415
Can you send me your model? I would need to replicate the error to understand the issue
On Tue, Jun 4, 2019 at 5:34 AM Muskaan Jain [email protected] wrote:
difference in predictions: 0.93792415
— You are receiving this because you commented.
Reply to this email directly, view it on GitHub https://github.com/kundajelab/deeplift/issues/80?email_source=notifications&email_token=AARSFBQYU5YTGLL7XCSWL6LPYZONFA5CNFSM4HS323KKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGODW4NIDY#issuecomment-498652175, or mute the thread https://github.com/notifications/unsubscribe-auth/AARSFBQNUI6IAMM3BTNY5HDPYZONFANCNFSM4HS323KA .
-- Sent from my phone, please excuse brevity/typos
By model, do you mean the architecture which is sent above or the whole code?
I'm specifically thinking of the weights file. If you could point me to the dataset you used, that would also be helpful.
On Tue, 4 Jun 2019 at 05:38, Muskaan Jain [email protected] wrote:
By model, do you mean the architecture which is sent above or the whole code?
— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/kundajelab/deeplift/issues/80?email_source=notifications&email_token=AARSFBUFT3CK2GQLOSJBWRTPYZO45A5CNFSM4HS323KKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGODW4NSTY#issuecomment-498653519, or mute the thread https://github.com/notifications/unsubscribe-auth/AARSFBU7HRIUTGA5TM4F7LTPYZO45ANCNFSM4HS323KA .
https://www.kaggle.com/c/dogs-vs-cats/data - dataset link
I am not able to upload the weights file.