Tushar-N

import torch
import torch.nn as nn
import torch.nn.functional as F

import torchvision.models as tmodels
from functools import partial
import collections

# dummy data: 10 batches of images with batch size 16
dataset = [torch.rand(16,3,224,224).cuda() for _ in range(10)]

thomwolf

##+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
## Created by: Hang Zhang, Rutgers University, Email: zhang.hang@rutgers.edu
## Modified by Thomas Wolf, HuggingFace Inc., Email: thomas@huggingface.co
## Copyright (c) 2017-2018
##
## This source code is licensed under the MIT-style license found in the
## LICENSE file in the root directory of this source tree
##+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

"""Encoding Data Parallel"""

rxwei

See the official Differentiable Programming Manifesto instead.

dvdhfnr

import torch
import torch.nn as nn


def compute_scale_and_shift(prediction, target, mask):
    # system matrix: A = [[a_00, a_01], [a_10, a_11]]
    a_00 = torch.sum(mask * prediction * prediction, (1, 2))
    a_01 = torch.sum(mask * prediction, (1, 2))
    a_11 = torch.sum(mask, (1, 2))

andreyryabtsev