import torch import torch.utils.data import numpy as np from torch import nn, optim from torch.autograd import Variable import torch.nn.functional as F from torchvision import datasets, transforms import pandas as pd import matplotlib.pyplot as plt import seaborn as sns import torch.nn as nn import math import torch.utils.model_zoo as model_zoo def conv3x3(in_planes, out_planes, stride=1): """3x3 convolution with padding""" return nn.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 = nn.BatchNorm2d(planes) self.relu = nn.ReLU(inplace=True) self.conv2 = conv3x3(planes, planes) self.bn2 = nn.BatchNorm2d(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 Bottleneck(nn.Module): expansion = 4 def __init__(self, inplanes, planes, stride=1, downsample=None): super(Bottleneck, self).__init__() self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False) self.bn1 = nn.BatchNorm2d(planes) self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False) self.bn2 = nn.BatchNorm2d(planes) self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False) self.bn3 = nn.BatchNorm2d(planes * 4) self.relu = nn.ReLU(inplace=True) 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) out = self.relu(out) out = self.conv3(out) out = self.bn3(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, layers, inp_channels= 3, num_classes=1000): self.inplanes = 64 super(ResNet, self).__init__() self.conv1 = nn.Conv2d(inp_channels, 64, kernel_size=2, stride=2, padding=3, bias=False) self.bn1 = nn.BatchNorm2d(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) self.avgpool = nn.AvgPool2d(2, stride=1) self.fc = nn.Linear(512 * block.expansion, num_classes) for m in self.modules(): if isinstance(m, nn.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, nn.BatchNorm2d): 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( nn.Conv2d(self.inplanes, planes * block.expansion, kernel_size=1, stride=stride, bias=False), nn.BatchNorm2d(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) x = self.layer1(x) x = self.layer2(x) x = self.layer3(x) x = self.layer4(x) x = self.avgpool(x) x = x.view(x.size(0), -1) x = self.fc(x) return x net = ResNet(BasicBlock, [2, 2, 2, 2], num_classes=10,inp_channels=1) print(net) use_gpu = torch.cuda.is_available() if use_gpu: net = net.cuda() print ('USE GPU') else: print ('USE CPU') criterion = nn.CrossEntropyLoss() optimizer = optim.SGD(net.parameters(), lr = 0.3, momentum = 0.1) print ("1. Loading data") train = pd.read_csv("../input/train.csv").values test = pd.read_csv("../input/test.csv").values print ("2. Converting data") X_data = train[:, 1:].reshape(train.shape[0], 1, 28, 28) X_data = X_data.astype(float) X_data /= 255.0 X_data = torch.from_numpy(X_data); X_label = train[:,0]; X_label = X_label.astype(int); X_label = torch.from_numpy(X_label); X_label = X_label.view(train.shape[0],-1); print (X_data.size(), X_label.size()) print ("3. Training phase") nb_train = train.shape[0] nb_epoch = 20000 nb_index = 0 nb_batch = 250 for epoch in range(nb_epoch): if nb_index + nb_batch >= nb_train: nb_index = 0 else: nb_index = nb_index + nb_batch mini_data = Variable(X_data[nb_index:(nb_index+nb_batch)].clone()) mini_label = Variable(X_label[nb_index:(nb_index+nb_batch)].clone(), requires_grad = False) mini_data = mini_data.type(torch.FloatTensor) mini_label = mini_label.type(torch.LongTensor) if use_gpu: mini_data = mini_data.cuda() mini_label = mini_label.cuda() optimizer.zero_grad() mini_out = net(mini_data) mini_label = mini_label.view(nb_batch) mini_loss = criterion(mini_out, mini_label) mini_loss.backward() optimizer.step() if (epoch + 1) % 100 == 0: print("Epoch = %d, Loss = %f" %(epoch+1, mini_loss.data[0])) print ("4. Testing phase") Y_data = test.reshape(test.shape[0], 1, 28, 28) Y_data = Y_data.astype(float) Y_data /= 255.0 Y_data = torch.from_numpy(Y_data); print (Y_data.size()) nb_test = test.shape[0] net.eval() final_prediction = np.ndarray(shape = (nb_test, 2), dtype=int) for each_sample in range(nb_test): sample_data = Variable(Y_data[each_sample:each_sample+1].clone()) sample_data = sample_data.type(torch.FloatTensor) if use_gpu: sample_data = sample_data.cuda() sample_out = net(sample_data) pred = torch.max(sample_out, 1) final_prediction[each_sample][0] = 1 + each_sample final_prediction[each_sample][1] = pred[1][0] if (each_sample + 1) % 2000 == 0: print("Total tested = %d" %(each_sample + 1)) print ('5. Generating submission file') submission = pd.DataFrame(final_prediction, dtype=int, columns=['ImageId', 'Label']) submission.to_csv('submission.csv', index=False, header=True)