import torch
import torch.nn.functional as F
from torch import nn
import math
from maskrcnn_benchmark.layers import FrozenBatchNorm2d
from maskrcnn_benchmark.layers import Conv2d


def conv3x3(in_planes, out_planes, stride=1):
	"""3x3 convolution with padding"""
	return Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
	              padding=1, bias=False)


class BasicBlock(nn.Module):
	expansion = 1

	def __init__(self, inplanes, planes, stride=1, downsample=None):
		super(BasicBlock, self).__init__()
		self.conv1 = conv3x3(inplanes, planes, stride)
		self.bn1 = FrozenBatchNorm2d(planes)
		self.relu = nn.ReLU(inplace=True)
		self.conv2 = conv3x3(planes, planes)
		self.bn2 = FrozenBatchNorm2d(planes)
		self.downsample = downsample
		self.stride = stride

	def forward(self, x):
		residual = x

		out = self.conv1(x)
		out = self.bn1(out)
		out = self.relu(out)

		out = self.conv2(out)
		out = self.bn2(out)

		if self.downsample is not None:
			residual = self.downsample(x)

		out += residual
		out = self.relu(out)

		return out


class ResNet(nn.Module):

	def __init__(self, block=BasicBlock, layers=[3, 4, 6, 3]):
		self.inplanes = 64
		super(ResNet, self).__init__()
		self.conv1 = Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
		                    bias=False)
		self.bn1 = FrozenBatchNorm2d(64)
		self.relu = nn.ReLU(inplace=True)
		self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
		self.layer1 = self._make_layer(block, 64, layers[0])
		self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
		self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
		self.layer4 = self._make_layer(block, 512, layers[3], stride=2)

		for m in self.modules():
			if isinstance(m, Conv2d):
				n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
				m.weight.data.normal_(0, math.sqrt(2. / n))
			elif isinstance(m, FrozenBatchNorm2d):
				m.weight.data.fill_(1)
				m.bias.data.zero_()

	def _make_layer(self, block, planes, blocks, stride=1):
		downsample = None
		if stride != 1 or self.inplanes != planes * block.expansion:
			downsample = nn.Sequential(
				Conv2d(self.inplanes, planes * block.expansion,
				       kernel_size=1, stride=stride, bias=False),
				FrozenBatchNorm2d(planes * block.expansion),
			)

		layers = []
		layers.append(block(self.inplanes, planes, stride, downsample))
		self.inplanes = planes * block.expansion
		for i in range(1, blocks):
			layers.append(block(self.inplanes, planes))

		return nn.Sequential(*layers)

	def forward(self, x):
		x = self.conv1(x)
		x = self.bn1(x)
		x = self.relu(x)
		x = self.maxpool(x)

		x2 = self.layer1(x)
		x3 = self.layer2(x2)
		x4 = self.layer3(x3)
		x5 = self.layer4(x4)
		return [x2, x3, x4, x5]