Ahmed Osama

my first thoughts that it's related to this part of the code ``` if is_grayscale: gray_bias = deprocessing_args.get('gray_bias', 0.0) W = np.array([image_scale]) b = np.array([gray_bias]) else: W = np.array([image_scale, image_scale,...

here is the torch model [Model Link](https://drive.google.com/open?id=0B3sn-iPgMRP7ZWgwOVhuTjZmQU0)

i have tried the same model but different result can you please try the same model but with batch normalization , it works with coreml in batch normalization [Batch Model](https://drive.google.com/open?id=0B3sn-iPgMRP7UWhwcnFFRWljTjg)

can you suggest a solution for this case @opedge seems to be working with batch norm and instance norm getting reddish

this might help , this is the model layers and the main problem is with **evaluate()** method nn.Sequential { [input -> (0) -> (1) -> (2) -> (3) -> (4)...

@opedge do you have any example for that

Hi @abinpaul1 , I am willing to implement the changes but the network tab is not helping me to get the logout endpoint and request

@abinpaul1 I have tried it, it returns the login page of Linkedin in HTML Format but the session is active First I used `takeovers `then `logout` 

Thanks @abinpaul1 for your reply the new route returns : ` {"memberEligible":true}` but the session is still active . I will add my code here for reference maybe something is...

Hi @abinpaul1 . I have done some investigation, and found a new route `https://www.linkedin.com/psettings/sessions/delete`. It can be used to log-out from a specific session.   Now, I am getting...