refactor: add disconnected mnist training script

Author: dimakis

Diff for: demo-notebooks/guided-demos/mnist_disconnected.py

@@ -0,0 +1,162 @@
+# Copyright 2022 IBM, Red Hat
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# In[]
+import os
+
+import torch
+from pytorch_lightning import LightningModule, Trainer
+from pytorch_lightning.callbacks.progress import TQDMProgressBar
+from pytorch_lightning.loggers import CSVLogger
+from torch import nn
+from torch.nn import functional as F
+from torch.utils.data import DataLoader, random_split
+from torchmetrics import Accuracy
+from torchvision import transforms
+from torchvision.datasets import MNIST
+
+PATH_DATASETS = os.environ.get("PATH_DATASETS", ".")
+BATCH_SIZE = 256 if torch.cuda.is_available() else 64
+# %%
+
+local_minst_path = os.path.join(PATH_DATASETS, "mnist")
+
+print("prior to running the trainer")
+print("MASTER_ADDR: is ", os.getenv("MASTER_ADDR"))
+print("MASTER_PORT: is ", os.getenv("MASTER_PORT"))
+
+
+class LitMNIST(LightningModule):
+    def __init__(self, data_dir=PATH_DATASETS, hidden_size=64, learning_rate=2e-4):
+        super().__init__()
+
+        # Set our init args as class attributes
+        self.data_dir = data_dir
+        self.hidden_size = hidden_size
+        self.learning_rate = learning_rate
+
+        # Hardcode some dataset specific attributes
+        self.num_classes = 10
+        self.dims = (1, 28, 28)
+        channels, width, height = self.dims
+        self.transform = transforms.Compose(
+            [
+                transforms.ToTensor(),
+                transforms.Normalize((0.1307,), (0.3081,)),
+            ]
+        )
+
+        # Define PyTorch model
+        self.model = nn.Sequential(
+            nn.Flatten(),
+            nn.Linear(channels * width * height, hidden_size),
+            nn.ReLU(),
+            nn.Dropout(0.1),
+            nn.Linear(hidden_size, hidden_size),
+            nn.ReLU(),
+            nn.Dropout(0.1),
+            nn.Linear(hidden_size, self.num_classes),
+        )
+
+        self.val_accuracy = Accuracy()
+        self.test_accuracy = Accuracy()
+
+    def forward(self, x):
+        x = self.model(x)
+        return F.log_softmax(x, dim=1)
+
+    def training_step(self, batch, batch_idx):
+        x, y = batch
+        logits = self(x)
+        loss = F.nll_loss(logits, y)
+        return loss
+
+    def validation_step(self, batch, batch_idx):
+        x, y = batch
+        logits = self(x)
+        loss = F.nll_loss(logits, y)
+        preds = torch.argmax(logits, dim=1)
+        self.val_accuracy.update(preds, y)
+
+        # Calling self.log will surface up scalars for you in TensorBoard
+        self.log("val_loss", loss, prog_bar=True)
+        self.log("val_acc", self.val_accuracy, prog_bar=True)
+
+    def test_step(self, batch, batch_idx):
+        x, y = batch
+        logits = self(x)
+        loss = F.nll_loss(logits, y)
+        preds = torch.argmax(logits, dim=1)
+        self.test_accuracy.update(preds, y)
+
+        # Calling self.log will surface up scalars for you in TensorBoard
+        self.log("test_loss", loss, prog_bar=True)
+        self.log("test_acc", self.test_accuracy, prog_bar=True)
+
+    def configure_optimizers(self):
+        optimizer = torch.optim.Adam(self.parameters(), lr=self.learning_rate)
+        return optimizer
+
+    ####################
+    # DATA RELATED HOOKS
+    ####################
+
+    def prepare_data(self):
+        # download
+        print("Downloading MNIST dataset...")
+        MNIST(self.data_dir, train=True, download=False)
+        MNIST(self.data_dir, train=False, download=False)
+
+    def setup(self, stage=None):
+        # Assign train/val datasets for use in dataloaders
+        if stage == "fit" or stage is None:
+            mnist_full = MNIST(self.data_dir, train=True, transform=self.transform, download=False)
+            self.mnist_train, self.mnist_val = random_split(mnist_full, [55000, 5000])
+
+        # Assign test dataset for use in dataloader(s)
+        if stage == "test" or stage is None:
+            self.mnist_test = MNIST(
+                self.data_dir, train=False, transform=self.transform, download=False
+            )
+
+    def train_dataloader(self):
+        return DataLoader(self.mnist_train, batch_size=BATCH_SIZE)
+
+    def val_dataloader(self):
+        return DataLoader(self.mnist_val, batch_size=BATCH_SIZE)
+
+    def test_dataloader(self):
+        return DataLoader(self.mnist_test, batch_size=BATCH_SIZE)
+
+
+# Init DataLoader from MNIST Dataset
+
+model = LitMNIST(data_dir=local_minst_path)
+
+print("GROUP: ", int(os.environ.get("GROUP_WORLD_SIZE", 1)))
+print("LOCAL: ", int(os.environ.get("LOCAL_WORLD_SIZE", 1)))
+
+# Initialize a trainer
+trainer = Trainer(
+    accelerator="auto",
+    # devices=1 if torch.cuda.is_available() else None,  # limiting got iPython runs
+    max_epochs=5,
+    callbacks=[TQDMProgressBar(refresh_rate=20)],
+    num_nodes=int(os.environ.get("GROUP_WORLD_SIZE", 1)),
+    devices=int(os.environ.get("LOCAL_WORLD_SIZE", 1)),
+    strategy="ddp",
+)
+
+# Train the model ⚡
+trainer.fit(model)