From: Parichay Kapoor <pk.kapoor@samsung.com>
Date: Tue, 8 Dec 2020 04:34:11 +0000 (+0900)
Subject: [vgg] Added pytorch model for vgg16
X-Git-Tag: accepted/tizen/unified/20201217.124219~16
X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=e54b4f0903152d14c6261370fd43ca22be150f05;p=platform%2Fcore%2Fml%2Fnntrainer.git

[vgg] Added pytorch model for vgg16

Added pytorch model for vgg16
This is to benchmark against tf and nntrainer

**Self evaluation:**
1. Build test: [x]Passed [ ]Failed [ ]Skipped
2. Run test: [x]Passed [ ]Failed [ ]Skipped

Signed-off-by: Parichay Kapoor <pk.kapoor@samsung.com>
---

diff --git a/Applications/VGG/PyTorch/main.py b/Applications/VGG/PyTorch/main.py
new file mode 100644
index 0000000..3051393
--- /dev/null
+++ b/Applications/VGG/PyTorch/main.py
@@ -0,0 +1,146 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: Apache-2.0
+#
+# @file	main.py
+# @date	08 Dec 2020
+# @brief	This is VGG16 Example using PyTorch
+# @see		https://github.com/nnstreamer/nntrainer
+# @author	Parichay Kapoor <pk.kapoor@samsung.com>
+# @bug		No known bugs except for NYI items
+#
+# This is based on official pytorch examples
+
+'''Train CIFAR100 with PyTorch.'''
+import torch
+import torch.nn as nn
+import torch.optim as optim
+import torch.nn.functional as F
+import torch.backends.cudnn as cudnn
+
+import torchvision
+import torchvision.transforms as transforms
+
+import os
+import argparse
+import sys
+
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+
+# Data
+print('==> Preparing data..')
+transform_train = transforms.Compose([
+    transforms.RandomCrop(32, padding=4),
+    transforms.RandomHorizontalFlip(),
+    transforms.ToTensor(),
+    transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
+])
+
+transform_test = transforms.Compose([
+    transforms.ToTensor(),
+    transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
+])
+
+trainset = torchvision.datasets.CIFAR100(
+        root='./data', train=True, download=True, transform=transform_train)
+trainloader = torch.utils.data.DataLoader(
+        trainset, batch_size=128, shuffle=True, num_workers=4)
+
+testset = torchvision.datasets.CIFAR100(
+        root='./data', train=False, download=True, transform=transform_test)
+testloader = torch.utils.data.DataLoader(
+        testset, batch_size=128, shuffle=False, num_workers=4)
+
+# Model
+
+cfg = {'VGG16': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M']}
+class VGG(nn.Module):
+    def __init__(self, vgg_name):
+        super(VGG, self).__init__()
+        self.features = self._make_layers(cfg[vgg_name])
+        self.classifier = nn.Sequential(nn.Linear(512, 256), nn.BatchNorm1d(256),
+            nn.ReLU(inplace=True), nn.Linear(256, 100))
+
+    def forward(self, x):
+        out = self.features(x)
+        out = out.view(out.size(0), -1)
+        out = self.classifier(out)
+        return out
+
+    def _make_layers(self, cfg):
+        layers = []
+        in_channels = 3
+        for x in cfg:
+            if x == 'M':
+                layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
+            else:
+                layers += [nn.Conv2d(in_channels, x, kernel_size=3, padding=1),
+                        nn.ReLU(inplace=True)]
+                in_channels = x
+        layers += [nn.AvgPool2d(kernel_size=1, stride=1)]
+        return nn.Sequential(*layers)
+
+print('Building model..')
+net = VGG('VGG16')
+net = net.to(device)
+if device == 'cuda':
+    net = torch.nn.DataParallel(net)
+    cudnn.benchmark = True
+
+criterion = nn.CrossEntropyLoss()
+optimizer = optim.Adam(net.parameters(), lr=1e-3, weight_decay=5e-4)
+
+# Training
+def train(epoch):
+    print('\nEpoch: %d' % epoch)
+    net.train()
+    train_loss = 0
+    correct = 0
+    total = 0
+    for batch_idx, (inputs, targets) in enumerate(trainloader):
+        inputs, targets = inputs.to(device), targets.to(device)
+        optimizer.zero_grad()
+        outputs = net(inputs)
+        loss = criterion(outputs, targets)
+        loss.backward()
+        optimizer.step()
+
+        train_loss += loss.item()
+        _, predicted = outputs.max(1)
+        total += targets.size(0)
+        correct += predicted.eq(targets).sum().item()
+
+    print('Loss: %.3f | Acc: %.3f%% (%d/%d)'
+            % (train_loss/(batch_idx+1), 100.*correct/total, correct, total))
+
+def test(epoch):
+    net.eval()
+    test_loss = 0
+    correct = 0
+    total = 0
+    with torch.no_grad():
+        for batch_idx, (inputs, targets) in enumerate(testloader):
+            inputs, targets = inputs.to(device), targets.to(device)
+            outputs = net(inputs)
+            loss = criterion(outputs, targets)
+
+            test_loss += loss.item()
+            _, predicted = outputs.max(1)
+            total += targets.size(0)
+            correct += predicted.eq(targets).sum().item()
+
+        print('Loss: %.3f | Acc: %.3f%% (%d/%d)'
+                % (test_loss/(batch_idx+1), 100.*correct/total, correct, total))
+
+    # Save checkpoint.
+    state = {'net': net.state_dict(),
+            'acc': acc,
+            'epoch': epoch,
+    }
+    if not os.path.isdir('checkpoint'):
+        os.mkdir('checkpoint')
+    torch.save(state, './checkpoint/ckpt.pth')
+
+if __name__ == '__main__':
+    for epoch in range(1):
+        train(epoch)
+    # test(epoch)