[tune] Fix up examples (#9201)

python/ray/tune/tests/tutorial.py

@@ -6,29 +6,106 @@
 import numpy as np
 import torch
 import torch.optim as optim
-from torchvision import datasets
+import torch.nn as nn
+from torchvision import datasets, transforms
+from torch.utils.data import DataLoader
+import torch.nn.functional as F
 
 from ray import tune
 from ray.tune.schedulers import ASHAScheduler
-from ray.tune.examples.mnist_pytorch import get_data_loaders, ConvNet, train, test
 # __tutorial_imports_end__
 # yapf: enable
 
 
 # yapf: disable
+# __model_def_begin__
+class ConvNet(nn.Module):
+    def __init__(self):
+        super(ConvNet, self).__init__()
+        # In this example, we don't change the model architecture
+        # due to simplicity.
+        self.conv1 = nn.Conv2d(1, 3, kernel_size=3)
+        self.fc = nn.Linear(192, 10)
+
+    def forward(self, x):
+        x = F.relu(F.max_pool2d(self.conv1(x), 3))
+        x = x.view(-1, 192)
+        x = self.fc(x)
+        return F.log_softmax(x, dim=1)
+# __model_def_end__
+# yapf: enable
+
+# yapf: disable
+# __train_def_begin__
+
+# Change these values if you want the training to run quicker or slower.
+EPOCH_SIZE = 512
+TEST_SIZE = 256
+
+def train(model, optimizer, train_loader):
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    model.train()
+    for batch_idx, (data, target) in enumerate(train_loader):
+        # We set this just for the example to run quickly.
+        if batch_idx * len(data) > EPOCH_SIZE:
+            return
+        data, target = data.to(device), target.to(device)
+        optimizer.zero_grad()
+        output = model(data)
+        loss = F.nll_loss(output, target)
+        loss.backward()
+        optimizer.step()
+
+
+def test(model, data_loader):
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    model.eval()
+    correct = 0
+    total = 0
+    with torch.no_grad():
+        for batch_idx, (data, target) in enumerate(data_loader):
+            # We set this just for the example to run quickly.
+            if batch_idx * len(data) > TEST_SIZE:
+                break
+            data, target = data.to(device), target.to(device)
+            outputs = model(data)
+            _, predicted = torch.max(outputs.data, 1)
+            total += target.size(0)
+            correct += (predicted == target).sum().item()
+
+    return correct / total
+# __train_def_end__
+
+
 # __train_func_begin__
 def train_mnist(config):
+    # Data Setup
+    mnist_transforms = transforms.Compose(
+        [transforms.ToTensor(),
+         transforms.Normalize((0.1307, ), (0.3081, ))])
+
+    train_loader = DataLoader(
+        datasets.MNIST("~/data", train=True, download=True, transform=mnist_transforms),
+        batch_size=64,
+        shuffle=True)
+    test_loader = DataLoader(
+        datasets.MNIST("~/data", train=False, transform=mnist_transforms),
+        batch_size=64,
+        shuffle=True)
+
     model = ConvNet()
-    train_loader, test_loader = get_data_loaders()
     optimizer = optim.SGD(
         model.parameters(), lr=config["lr"], momentum=config["momentum"])
     for i in range(10):
         train(model, optimizer, train_loader)
         acc = test(model, test_loader)
+
+        # Send the current training result back to Tune
         tune.report(mean_accuracy=acc)
+
         if i % 5 == 0:
             # This saves the model to the trial directory
-            torch.save(model, "./model.pth")
+            torch.save(model.state_dict(), "./model.pth")
 # __train_func_end__
 # yapf: enable
 
@@ -39,7 +116,10 @@ search_space = {
 }
 
 # Uncomment this to enable distributed execution
-# `ray.init(address=...)`
+# `ray.init(address="auto")`
+
+# Download the dataset first
+datasets.MNIST("~/data", train=True, download=True)
 
 analysis = tune.run(train_mnist, config=search_space)
 # __eval_func_end__
@@ -52,7 +132,7 @@ dfs = analysis.trial_dataframes
 # __run_scheduler_begin__
 analysis = tune.run(
     train_mnist,
-    num_samples=30,
+    num_samples=20,
     scheduler=ASHAScheduler(metric="mean_accuracy", mode="max"),
     config=search_space)
 
@@ -88,7 +168,10 @@ import os
 
 df = analysis.dataframe()
 logdir = analysis.get_best_logdir("mean_accuracy", mode="max")
-model = torch.load(os.path.join(logdir, "model.pth"))
+state_dict = torch.load(os.path.join(logdir, "model.pth"))
+
+model = ConvNet()
+model.load_state_dict(state_dict)
 # __run_analysis_end__
 
 from ray.tune.examples.mnist_pytorch_trainable import TrainMNIST