catalyst

pip install catalyst[ml]         # installs ML-based Catalyst
pip install catalyst[cv]         # installs CV-based Catalyst
# master version installation
pip install git+https://github.com/catalyst-team/catalyst@master --upgrade
# all available extensions are listed here:
# https://github.com/catalyst-team/catalyst/blob/master/setup.py

import os
from torch import nn, optim
from torch.nn import functional as F
from torch.utils.data import DataLoader
from catalyst import dl, metrics
from catalyst.contrib.datasets import MNIST

model = nn.Sequential(nn.Flatten(), nn.Linear(28 * 28, 10))
optimizer = optim.Adam(model.parameters(), lr=0.02)

train_data = MNIST(os.getcwd(), train=True)
valid_data = MNIST(os.getcwd(), train=False)
loaders = {
    "train": DataLoader(train_data, batch_size=32),
    "valid": DataLoader(valid_data, batch_size=32),
}

class CustomRunner(dl.Runner):
    def predict_batch(self, batch):
        # model inference step
        return self.model(batch[0].to(self.engine.device))

    def on_loader_start(self, runner):
        super().on_loader_start(runner)
        self.meters = {
            key: metrics.AdditiveMetric(compute_on_call=False)
            for key in ["loss", "accuracy01", "accuracy03"]
        }

    def handle_batch(self, batch):
        # model train/valid step
        # unpack the batch
        x, y = batch
        # run model forward pass
        logits = self.model(x)
        # compute the loss
        loss = F.cross_entropy(logits, y)
        # compute the metrics
        accuracy01, accuracy03 = metrics.accuracy(logits, y, topk=(1, 3))
        # log metrics
        self.batch_metrics.update(
            {"loss": loss, "accuracy01": accuracy01, "accuracy03": accuracy03}
        )
        for key in ["loss", "accuracy01", "accuracy03"]:
            self.meters[key].update(self.batch_metrics[key].item(), self.batch_size)
        # run model backward pass
        if self.is_train_loader:
            self.engine.backward(loss)
            self.optimizer.step()
            self.optimizer.zero_grad()

    def on_loader_end(self, runner):
        for key in ["loss", "accuracy01", "accuracy03"]:
            self.loader_metrics[key] = self.meters[key].compute()[0]
        super().on_loader_end(runner)

runner = CustomRunner()
# model training
runner.train(
    model=model,
    optimizer=optimizer,
    loaders=loaders,
    logdir="./logs",
    num_epochs=5,
    verbose=True,
    valid_loader="valid",
    valid_metric="loss",
    minimize_valid_metric=True,
)
# model inference
for logits in runner.predict_loader(loader=loaders["valid"]):
    assert logits.detach().cpu().numpy().shape[-1] == 10

import torch
from torch.utils.data import DataLoader, TensorDataset
from catalyst import dl

# data
num_samples, num_features = int(1e4), int(1e1)
X, y = torch.rand(num_samples, num_features), torch.rand(num_samples)
dataset = TensorDataset(X, y)
loader = DataLoader(dataset, batch_size=32, num_workers=1)
loaders = {"train": loader, "valid": loader}

# model, criterion, optimizer, scheduler
model = torch.nn.Linear(num_features, 1)
criterion = torch.nn.MSELoss()
optimizer = torch.optim.Adam(model.parameters())
scheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer, [3, 6])

# model training
runner = dl.SupervisedRunner()
runner.train(
    model=model,
    criterion=criterion,
    optimizer=optimizer,
    scheduler=scheduler,
    loaders=loaders,
    logdir="./logdir",
    valid_loader="valid",
    valid_metric="loss",
    minimize_valid_metric=True,
    num_epochs=8,
    verbose=True,
)

import torch
from torch.utils.data import DataLoader, TensorDataset
from catalyst import dl

# sample data
num_samples, num_features, num_classes = int(1e4), int(1e1), 4
X = torch.rand(num_samples, num_features)
y = (torch.rand(num_samples,) * num_classes).to(torch.int64)

# pytorch loaders
dataset = TensorDataset(X, y)
loader = DataLoader(dataset, batch_size=32, num_workers=1)
loaders = {"train": loader, "valid": loader}

# model, criterion, optimizer, scheduler
model = torch.nn.Linear(num_features, num_classes)
criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters())
scheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer, [2])

# model training
runner = dl.SupervisedRunner(
    input_key="features", output_key="logits", target_key="targets", loss_key="loss"
)
runner.train(
    model=model,
    criterion=criterion,
    optimizer=optimizer,
    scheduler=scheduler,
    loaders=loaders,
    logdir="./logdir",
    num_epochs=3,
    valid_loader="valid",
    valid_metric="accuracy03",
    minimize_valid_metric=False,
    verbose=True,
    callbacks=[
        dl.AccuracyCallback(input_key="logits", target_key="targets", num_classes=num_classes),
        # uncomment for extra metrics:
        # dl.PrecisionRecallF1SupportCallback(
        #     input_key="logits", target_key="targets", num_classes=num_classes
        # ),
        # dl.AUCCallback(input_key="logits", target_key="targets"),
        # catalyst[ml] required ``pip install catalyst[ml]``
        # dl.ConfusionMatrixCallback(
        #     input_key="logits", target_key="targets", num_classes=num_classes
        # ),
    ],
)

import torch
from torch.utils.data import DataLoader, TensorDataset
from catalyst import dl

# sample data
num_samples, num_features, num_classes = int(1e4), int(1e1), 4
X = torch.rand(num_samples, num_features)
y = (torch.rand(num_samples, num_classes) > 0.5).to(torch.float32)

# pytorch loaders
dataset = TensorDataset(X, y)
loader = DataLoader(dataset, batch_size=32, num_workers=1)
loaders = {"train": loader, "valid": loader}

# model, criterion, optimizer, scheduler
model = torch.nn.Linear(num_features, num_classes)
criterion = torch.nn.BCEWithLogitsLoss()
optimizer = torch.optim.Adam(model.parameters())
scheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer, [2])

# model training
runner = dl.SupervisedRunner(
    input_key="features", output_key="logits", target_key="targets", loss_key="loss"
)
runner.train(
    model=model,
    criterion=criterion,
    optimizer=optimizer,
    scheduler=scheduler,
    loaders=loaders,
    logdir="./logdir",
    num_epochs=3,
    valid_loader="valid",
    valid_metric="accuracy01",
    minimize_valid_metric=False,
    verbose=True,
    callbacks=[
        dl.BatchTransformCallback(
            transform=torch.sigmoid,
            scope="on_batch_end",
            input_key="logits",
            output_key="scores"
        ),
        dl.AUCCallback(input_key="scores", target_key="targets"),
        # uncomment for extra metrics:
        # dl.MultilabelAccuracyCallback(input_key="scores", target_key="targets", threshold=0.5),
        # dl.MultilabelPrecisionRecallF1SupportCallback(
        #     input_key="scores", target_key="targets", threshold=0.5
        # ),
    ]
)

import torch
from torch import nn, optim
from torch.utils.data import DataLoader, TensorDataset
from catalyst import dl

# sample data
num_samples, num_features, num_classes1, num_classes2 = int(1e4), int(1e1), 4, 10
X = torch.rand(num_samples, num_features)
y1 = (torch.rand(num_samples,) * num_classes1).to(torch.int64)
y2 = (torch.rand(num_samples,) * num_classes2).to(torch.int64)

# pytorch loaders
dataset = TensorDataset(X, y1, y2)
loader = DataLoader(dataset, batch_size=32, num_workers=1)
loaders = {"train": loader, "valid": loader}

class CustomModule(nn.Module):
    def __init__(self, in_features: int, out_features1: int, out_features2: int):
        super().__init__()
        self.shared = nn.Linear(in_features, 128)
        self.head1 = nn.Linear(128, out_features1)
        self.head2 = nn.Linear(128, out_features2)

    def forward(self, x):
        x = self.shared(x)
        y1 = self.head1(x)
        y2 = self.head2(x)
        return y1, y2

# model, criterion, optimizer, scheduler
model = CustomModule(num_features, num_classes1, num_classes2)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters())
scheduler = optim.lr_scheduler.MultiStepLR(optimizer, [2])

class CustomRunner(dl.Runner):
    def handle_batch(self, batch):
        x, y1, y2 = batch
        y1_hat, y2_hat = self.model(x)
        self.batch = {
            "features": x,
            "logits1": y1_hat,
            "logits2": y2_hat,
            "targets1": y1,
            "targets2": y2,
        }

# model training
runner = CustomRunner()
runner.train(
    model=model,
    criterion=criterion,
    optimizer=optimizer,
    scheduler=scheduler,
    loaders=loaders,
    num_epochs=3,
    verbose=True,
    callbacks=[
        dl.CriterionCallback(metric_key="loss1", input_key="logits1", target_key="targets1"),
        dl.CriterionCallback(metric_key="loss2", input_key="logits2", target_key="targets2"),
        dl.MetricAggregationCallback(metric_key="loss", metrics=["loss1", "loss2"], mode="mean"),
        dl.BackwardCallback(metric_key="loss"),
        dl.OptimizerCallback(metric_key="loss"),
        dl.SchedulerCallback(),
        dl.AccuracyCallback(
            input_key="logits1", target_key="targets1", num_classes=num_classes1, prefix="one_"
        ),
        dl.AccuracyCallback(
            input_key="logits2", target_key="targets2", num_classes=num_classes2, prefix="two_"
        ),
        # catalyst[ml] required ``pip install catalyst[ml]``
        # dl.ConfusionMatrixCallback(
        #     input_key="logits1", target_key="targets1", num_classes=num_classes1, prefix="one_cm"
        # ),
        # dl.ConfusionMatrixCallback(
        #     input_key="logits2", target_key="targets2", num_classes=num_classes2, prefix="two_cm"
        # ),
        dl.CheckpointCallback(
            logdir="./logs/one",
            loader_key="valid", metric_key="one_accuracy01", minimize=False, topk=1
        ),
        dl.CheckpointCallback(
            logdir="./logs/two",
            loader_key="valid", metric_key="two_accuracy03", minimize=False, topk=3
        ),
    ],
    loggers={"console": dl.ConsoleLogger(), "tb": dl.TensorboardLogger("./logs/tb")},
)

import torch
from torch.utils.data import DataLoader, TensorDataset
from catalyst import dl

# sample data
num_users, num_features, num_items = int(1e4), int(1e1), 10
X = torch.rand(num_users, num_features)
y = (torch.rand(num_users, num_items) > 0.5).to(torch.float32)

# pytorch loaders
dataset = TensorDataset(X, y)
loader = DataLoader(dataset, batch_size=32, num_workers=1)
loaders = {"train": loader, "valid": loader}

# model, criterion, optimizer, scheduler
model = torch.nn.Linear(num_features, num_items)
criterion = torch.nn.BCEWithLogitsLoss()
optimizer = torch.optim.Adam(model.parameters())
scheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer, [2])

# model training
runner = dl.SupervisedRunner(
    input_key="features", output_key="logits", target_key="targets", loss_key="loss"
)
runner.train(
    model=model,
    criterion=criterion,
    optimizer=optimizer,
    scheduler=scheduler,
    loaders=loaders,
    num_epochs=3,
    verbose=True,
    callbacks=[
        dl.BatchTransformCallback(
            transform=torch.sigmoid,
            scope="on_batch_end",
            input_key="logits",
            output_key="scores"
        ),
        dl.CriterionCallback(input_key="logits", target_key="targets", metric_key="loss"),
        # uncomment for extra metrics:
        # dl.AUCCallback(input_key="scores", target_key="targets"),
        # dl.HitrateCallback(input_key="scores", target_key="targets", topk=(1, 3, 5)),
        # dl.MRRCallback(input_key="scores", target_key="targets", topk=(1, 3, 5)),
        # dl.MAPCallback(input_key="scores", target_key="targets", topk=(1, 3, 5)),
        # dl.NDCGCallback(input_key="scores", target_key="targets", topk=(1, 3, 5)),
        dl.BackwardCallback(metric_key="loss"),
        dl.OptimizerCallback(metric_key="loss"),
        dl.SchedulerCallback(),
        dl.CheckpointCallback(
            logdir="./logs", loader_key="valid", metric_key="loss", minimize=True
        ),
    ]
)

import os
from torch import nn, optim
from torch.utils.data import DataLoader
from catalyst import dl
from catalyst.contrib.datasets import MNIST

model = nn.Sequential(nn.Flatten(), nn.Linear(28 * 28, 10))
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.02)

train_data = MNIST(os.getcwd(), train=True)
valid_data = MNIST(os.getcwd(), train=False)
loaders = {
    "train": DataLoader(train_data, batch_size=32),
    "valid": DataLoader(valid_data, batch_size=32),
}

runner = dl.SupervisedRunner()
# model training
runner.train(
    model=model,
    criterion=criterion,
    optimizer=optimizer,
    loaders=loaders,
    num_epochs=1,
    logdir="./logs",
    valid_loader="valid",
    valid_metric="loss",
    minimize_valid_metric=True,
    verbose=True,
# uncomment for extra metrics:
#     callbacks=[
#         dl.AccuracyCallback(input_key="logits", target_key="targets", num_classes=10),
#         dl.PrecisionRecallF1SupportCallback(
#             input_key="logits", target_key="targets", num_classes=10
#         ),
#         dl.AUCCallback(input_key="logits", target_key="targets"),
#         # catalyst[ml] required ``pip install catalyst[ml]``
#         dl.ConfusionMatrixCallback(
#             input_key="logits", target_key="targets", num_classes=num_classes
#         ),
#     ]
)

import os
import torch
from torch import nn
from torch.utils.data import DataLoader
from catalyst import dl
from catalyst.contrib.datasets import MNIST
from catalyst.contrib.losses import IoULoss


model = nn.Sequential(
    nn.Conv2d(1, 1, 3, 1, 1), nn.ReLU(),
    nn.Conv2d(1, 1, 3, 1, 1), nn.Sigmoid(),
)
criterion = IoULoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.02)

train_data = MNIST(os.getcwd(), train=True)
valid_data = MNIST(os.getcwd(), train=False)
loaders = {
    "train": DataLoader(train_data, batch_size=32),
    "valid": DataLoader(valid_data, batch_size=32),
}

class CustomRunner(dl.SupervisedRunner):
    def handle_batch(self, batch):
        x = batch[self._input_key]
        x_noise = (x + torch.rand_like(x)).clamp_(0, 1)
        x_ = self.model(x_noise)
        self.batch = {self._input_key: x, self._output_key: x_, self._target_key: x}

runner = CustomRunner(
    input_key="features", output_key="scores", target_key="targets", loss_key="loss"
)
# model training
runner.train(
    model=model,
    criterion=criterion,
    optimizer=optimizer,
    loaders=loaders,
    num_epochs=1,
    callbacks=[
        dl.IOUCallback(input_key="scores", target_key="targets"),
        dl.DiceCallback(input_key="scores", target_key="targets"),
        dl.TrevskyCallback(input_key="scores", target_key="targets", alpha=0.2),
    ],
    logdir="./logdir",
    valid_loader="valid",
    valid_metric="loss",
    minimize_valid_metric=True,
    verbose=True,
)

import os
from torch.optim import Adam
from torch.utils.data import DataLoader
from catalyst import dl
from catalyst.contrib.data import HardTripletsSampler
from catalyst.contrib.datasets import MnistMLDataset, MnistQGDataset
from catalyst.contrib.losses import TripletMarginLossWithSampler
from catalyst.contrib.models import MnistSimpleNet
from catalyst.data.sampler import BatchBalanceClassSampler


# 1. train and valid loaders
train_dataset = MnistMLDataset(root=os.getcwd())
sampler = BatchBalanceClassSampler(
    labels=train_dataset.get_labels(), num_classes=5, num_samples=10, num_batches=10
)
train_loader = DataLoader(dataset=train_dataset, batch_sampler=sampler)

valid_dataset = MnistQGDataset(root=os.getcwd(), gallery_fraq=0.2)
valid_loader = DataLoader(dataset=valid_dataset, batch_size=1024)

# 2. model and optimizer
model = MnistSimpleNet(out_features=16)
optimizer = Adam(model.parameters(), lr=0.001)

# 3. criterion with triplets sampling
sampler_inbatch = HardTripletsSampler(norm_required=False)
criterion = TripletMarginLossWithSampler(margin=0.5, sampler_inbatch=sampler_inbatch)

# 4. training with catalyst Runner
class CustomRunner(dl.SupervisedRunner):
    def handle_batch(self, batch) -> None:
        if self.is_train_loader:
            images, targets = batch["features"].float(), batch["targets"].long()
            features = self.model(images)
            self.batch = {"embeddings": features, "targets": targets,}
        else:
            images, targets, is_query = \
                batch["features"].float(), batch["targets"].long(), batch["is_query"].bool()
            features = self.model(images)
            self.batch = {"embeddings": features, "targets": targets, "is_query": is_query}

callbacks = [
    dl.ControlFlowCallbackWrapper(
        dl.CriterionCallback(input_key="embeddings", target_key="targets", metric_key="loss"),
        loaders="train",
    ),
    dl.ControlFlowCallbackWrapper(
        dl.CMCScoreCallback(
            embeddings_key="embeddings",
            labels_key="targets",
            is_query_key="is_query",
            topk=[1],
        ),
        loaders="valid",
    ),
    dl.PeriodicLoaderCallback(
        valid_loader_key="valid", valid_metric_key="cmc01", minimize=False, valid=2
    ),
]

runner = CustomRunner(input_key="features", output_key="embeddings")
runner.train(
    model=model,
    criterion=criterion,
    optimizer=optimizer,
    callbacks=callbacks,
    loaders={"train": train_loader, "valid": valid_loader},
    verbose=False,
    logdir="./logs",
    valid_loader="valid",
    valid_metric="cmc01",
    minimize_valid_metric=False,
    num_epochs=10,
)

import os
import torch
from torch import nn
from torch.utils.data import DataLoader
from catalyst import dl
from catalyst.contrib.datasets import MNIST
from catalyst.contrib.layers import GlobalMaxPool2d, Lambda

latent_dim = 128
generator = nn.Sequential(
    # We want to generate 128 coefficients to reshape into a 7x7x128 map
    nn.Linear(128, 128 * 7 * 7),
    nn.LeakyReLU(0.2, inplace=True),
    Lambda(lambda x: x.view(x.size(0), 128, 7, 7)),
    nn.ConvTranspose2d(128, 128, (4, 4), stride=(2, 2), padding=1),
    nn.LeakyReLU(0.2, inplace=True),
    nn.ConvTranspose2d(128, 128, (4, 4), stride=(2, 2), padding=1),
    nn.LeakyReLU(0.2, inplace=True),
    nn.Conv2d(128, 1, (7, 7), padding=3),
    nn.Sigmoid(),
)
discriminator = nn.Sequential(
    nn.Conv2d(1, 64, (3, 3), stride=(2, 2), padding=1),
    nn.LeakyReLU(0.2, inplace=True),
    nn.Conv2d(64, 128, (3, 3), stride=(2, 2), padding=1),
    nn.LeakyReLU(0.2, inplace=True),
    GlobalMaxPool2d(),
    nn.Flatten(),
    nn.Linear(128, 1),
)

model = nn.ModuleDict({"generator": generator, "discriminator": discriminator})
criterion = {"generator": nn.BCEWithLogitsLoss(), "discriminator": nn.BCEWithLogitsLoss()}
optimizer = {
    "generator": torch.optim.Adam(generator.parameters(), lr=0.0003, betas=(0.5, 0.999)),
    "discriminator": torch.optim.Adam(discriminator.parameters(), lr=0.0003, betas=(0.5, 0.999)),
}
train_data = MNIST(os.getcwd(), train=False)
loaders = {"train": DataLoader(train_data, batch_size=32)}

class CustomRunner(dl.Runner):
    def predict_batch(self, batch):
        batch_size = 1
        # Sample random points in the latent space
        random_latent_vectors = torch.randn(batch_size, latent_dim).to(self.engine.device)
        # Decode them to fake images
        generated_images = self.model["generator"](random_latent_vectors).detach()
        return generated_images

    def handle_batch(self, batch):
        real_images, _ = batch
        batch_size = real_images.shape[0]

        # Sample random points in the latent space
        random_latent_vectors = torch.randn(batch_size, latent_dim).to(self.engine.device)

        # Decode them to fake images
        generated_images = self.model["generator"](random_latent_vectors).detach()
        # Combine them with real images
        combined_images = torch.cat([generated_images, real_images])

        # Assemble labels discriminating real from fake images
        labels = \
            torch.cat([torch.ones((batch_size, 1)), torch.zeros((batch_size, 1))]).to(self.engine.device)
        # Add random noise to the labels - important trick!
        labels += 0.05 * torch.rand(labels.shape).to(self.engine.device)

        # Discriminator forward
        combined_predictions = self.model["discriminator"](combined_images)

        # Sample random points in the latent space
        random_latent_vectors = torch.randn(batch_size, latent_dim).to(self.engine.device)
        # Assemble labels that say "all real images"
        misleading_labels = torch.zeros((batch_size, 1)).to(self.engine.device)

        # Generator forward
        generated_images = self.model["generator"](random_latent_vectors)
        generated_predictions = self.model["discriminator"](generated_images)

        self.batch = {
            "combined_predictions": combined_predictions,
            "labels": labels,
            "generated_predictions": generated_predictions,
            "misleading_labels": misleading_labels,
        }


runner = CustomRunner()
runner.train(
    model=model,
    criterion=criterion,
    optimizer=optimizer,
    loaders=loaders,
    callbacks=[
        dl.CriterionCallback(
            input_key="combined_predictions",
            target_key="labels",
            metric_key="loss_discriminator",
            criterion_key="discriminator",
        ),
        dl.BackwardCallback(metric_key="loss_discriminator"),
        dl.OptimizerCallback(
            optimizer_key="discriminator",
            metric_key="loss_discriminator",
        ),
        dl.CriterionCallback(
            input_key="generated_predictions",
            target_key="misleading_labels",
            metric_key="loss_generator",
            criterion_key="generator",
        ),
        dl.BackwardCallback(metric_key="loss_generator"),
        dl.OptimizerCallback(
            optimizer_key="generator",
            metric_key="loss_generator",
        ),
    ],
    valid_loader="train",
    valid_metric="loss_generator",
    minimize_valid_metric=True,
    num_epochs=20,
    verbose=True,
    logdir="./logs_gan",
)

# visualization (matplotlib required):
# import matplotlib.pyplot as plt
# %matplotlib inline
# plt.imshow(runner.predict_batch(None)[0, 0].cpu().numpy())

import os
import torch
from torch import nn, optim
from torch.nn import functional as F
from torch.utils.data import DataLoader
from catalyst import dl, metrics
from catalyst.contrib.datasets import MNIST

LOG_SCALE_MAX = 2
LOG_SCALE_MIN = -10

def normal_sample(loc, log_scale):
    scale = torch.exp(0.5 * log_scale)
    return loc + scale * torch.randn_like(scale)

class VAE(nn.Module):
    def __init__(self, in_features, hid_features):
        super().__init__()
        self.hid_features = hid_features
        self.encoder = nn.Linear(in_features, hid_features * 2)
        self.decoder = nn.Sequential(nn.Linear(hid_features, in_features), nn.Sigmoid())

    def forward(self, x, deterministic=False):
        z = self.encoder(x)
        bs, z_dim = z.shape

        loc, log_scale = z[:, : z_dim // 2], z[:, z_dim // 2 :]
        log_scale = torch.clamp(log_scale, LOG_SCALE_MIN, LOG_SCALE_MAX)

        z_ = loc if deterministic else normal_sample(loc, log_scale)
        z_ = z_.view(bs, -1)
        x_ = self.decoder(z_)

        return x_, loc, log_scale

class CustomRunner(dl.IRunner):
    def __init__(self, hid_features, logdir, engine):
        super().__init__()
        self.hid_features = hid_features
        self._logdir = logdir
        self._engine = engine

    def get_engine(self):
        return self._engine

    def get_loggers(self):
        return {
            "console": dl.ConsoleLogger(),
            "csv": dl.CSVLogger(logdir=self._logdir),
            "tensorboard": dl.TensorboardLogger(logdir=self._logdir),
        }

    @property
    def num_epochs(self) -> int:
        return 1

    def get_loaders(self):
        loaders = {
            "train": DataLoader(MNIST(os.getcwd(), train=False), batch_size=32),
            "valid": DataLoader(MNIST(os.getcwd(), train=False), batch_size=32),
        }
        return loaders

    def get_model(self):
        model = self.model if self.model is not None else VAE(28 * 28, self.hid_features)
        return model

    def get_optimizer(self, model):
        return optim.Adam(model.parameters(), lr=0.02)

    def get_callbacks(self):
        return {
            "backward": dl.BackwardCallback(metric_key="loss"),
            "optimizer": dl.OptimizerCallback(metric_key="loss"),
            "checkpoint": dl.CheckpointCallback(
                self._logdir,
                loader_key="valid",
                metric_key="loss",
                minimize=True,
                topk=3,
            ),
        }

    def on_loader_start(self, runner):
        super().on_loader_start(runner)
        self.meters = {
            key: metrics.AdditiveMetric(compute_on_call=False)
            for key in ["loss_ae", "loss_kld", "loss"]
        }

    def handle_batch(self, batch):
        x, _ = batch
        x = x.view(x.size(0), -1)
        x_, loc, log_scale = self.model(x, deterministic=not self.is_train_loader)

        loss_ae = F.mse_loss(x_, x)
        loss_kld = (
            -0.5 * torch.sum(1 + log_scale - loc.pow(2) - log_scale.exp(), dim=1)
        ).mean()
        loss = loss_ae + loss_kld * 0.01

        self.batch_metrics = {"loss_ae": loss_ae, "loss_kld": loss_kld, "loss": loss}
        for key in ["loss_ae", "loss_kld", "loss"]:
            self.meters[key].update(self.batch_metrics[key].item(), self.batch_size)

    def on_loader_end(self, runner):
        for key in ["loss_ae", "loss_kld", "loss"]:
            self.loader_metrics[key] = self.meters[key].compute()[0]
        super().on_loader_end(runner)

    def predict_batch(self, batch):
        random_latent_vectors = torch.randn(1, self.hid_features).to(self.engine.device)
        generated_images = self.model.decoder(random_latent_vectors).detach()
        return generated_images

runner = CustomRunner(128, "./logs", dl.CPUEngine())
runner.run()
# visualization (matplotlib required):
# import matplotlib.pyplot as plt
# %matplotlib inline
# plt.imshow(runner.predict_batch(None)[0].cpu().numpy().reshape(28, 28))

import os
import optuna
import torch
from torch import nn
from torch.utils.data import DataLoader
from catalyst import dl
from catalyst.contrib.datasets import MNIST


def objective(trial):
    lr = trial.suggest_loguniform("lr", 1e-3, 1e-1)
    num_hidden = int(trial.suggest_loguniform("num_hidden", 32, 128))

    train_data = MNIST(os.getcwd(), train=True)
    valid_data = MNIST(os.getcwd(), train=False)
    loaders = {
        "train": DataLoader(train_data, batch_size=32),
        "valid": DataLoader(valid_data, batch_size=32),
    }
    model = nn.Sequential(
        nn.Flatten(), nn.Linear(784, num_hidden), nn.ReLU(), nn.Linear(num_hidden, 10)
    )
    optimizer = torch.optim.Adam(model.parameters(), lr=lr)
    criterion = nn.CrossEntropyLoss()

    runner = dl.SupervisedRunner(input_key="features", output_key="logits", target_key="targets")
    runner.train(
        model=model,
        criterion=criterion,
        optimizer=optimizer,
        loaders=loaders,
        callbacks={
            "accuracy": dl.AccuracyCallback(
                input_key="logits", target_key="targets", num_classes=10
            ),
            # catalyst[optuna] required ``pip install catalyst[optuna]``
            "optuna": dl.OptunaPruningCallback(
                loader_key="valid", metric_key="accuracy01", minimize=False, trial=trial
            ),
        },
        num_epochs=3,
    )
    score = trial.best_score
    return score

study = optuna.create_study(
    direction="maximize",
    pruner=optuna.pruners.MedianPruner(
        n_startup_trials=1, n_warmup_steps=0, interval_steps=1
    ),
)
study.optimize(objective, n_trials=3, timeout=300)
print(study.best_value, study.best_params)

runner:
  _target_: catalyst.runners.SupervisedRunner
  model:
    _var_: model
    _target_: torch.nn.Sequential
    args:
      - _target_: torch.nn.Flatten
      - _target_: torch.nn.Linear
        in_features: 784  # 28 * 28
        out_features: 10
  input_key: features
  output_key: &output_key logits
  target_key: &target_key targets
  loss_key: &loss_key loss

run:
  # ≈ stage 1
  - _call_: train  # runner.train(...)

    criterion:
      _target_: torch.nn.CrossEntropyLoss

    optimizer:
      _target_: torch.optim.Adam
      params:  # model.parameters()
        _var_: model.parameters
      lr: 0.02

    loaders:
      train:
        _target_: torch.utils.data.DataLoader
        dataset:
          _target_: catalyst.contrib.datasets.MNIST
          root: data
          train: y
        batch_size: 32

      &valid_loader_key valid:
        &valid_loader
        _target_: torch.utils.data.DataLoader
        dataset:
          _target_: catalyst.contrib.datasets.MNIST
          root: data
          train: n
        batch_size: 32

    callbacks:
      - &accuracy_metric
        _target_: catalyst.callbacks.AccuracyCallback
        input_key: *output_key
        target_key: *target_key
        topk: [1,3,5]
      - _target_: catalyst.callbacks.PrecisionRecallF1SupportCallback
        input_key: *output_key
        target_key: *target_key

    num_epochs: 1
    logdir: logs
    valid_loader: *valid_loader_key
    valid_metric: *loss_key
    minimize_valid_metric: y
    verbose: y

  # ≈ stage 2
  - _call_: evaluate_loader  # runner.evaluate_loader(...)
    loader: *valid_loader
    callbacks:
      - *accuracy_metric

catalyst-run --config example.yaml

• Hierarchical Attention for Sentiment Classification with Visualization
• Pediatric Bone Age Assessment
• Implementation of the paper “Tell Me Where to Look: Guided Attention Inference Network”
• Implementation of the paper “Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural Networks”
• Implementation of the paper “Utterance-level Aggregation For Speaker Recognition In The Wild”
• Implementation of the paper “Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation”
• Implementation of the paper “ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks”

• Solving the Cocktail Party Problem using PyTorch
• Beyond fashion: Deep Learning with Catalyst (Config API)
• Tutorial from Notebook API to Config API (RU)

• Kaggle Quick, Draw! Doodle Recognition Challenge - 11th place
• Catalyst.RL - NeurIPS 2018: AI for Prosthetics Challenge – 3rd place
• Kaggle Google Landmark 2019 - 30th place
• iMet Collection 2019 - FGVC6 - 24th place
• ID R&D Anti-spoofing Challenge - 14th place
• NeurIPS 2019: Recursion Cellular Image Classification - 4th place
• MICCAI 2019: Automatic Structure Segmentation for Radiotherapy Planning Challenge 2019
  • 3rd place solution for Task 3: Organ-at-risk segmentation from chest CT scans
  • and 4th place solution for Task 4: Gross Target Volume segmentation of lung cancer
• Kaggle Seversteal steel detection - 5th place
• RSNA Intracranial Hemorrhage Detection - 5th place
• APTOS 2019 Blindness Detection – 7th place
• Catalyst.RL - NeurIPS 2019: Learn to Move - Walk Around – 2nd place
• xView2 Damage Assessment Challenge - 3rd place

• Catalyst.RL – A Distributed Framework for Reproducible RL Research by Scitator
• Catalyst.Classification - Comprehensive classification pipeline with Pseudo-Labeling by Bagxi and Pdanilov
• Catalyst.Segmentation - Segmentation pipelines - binary, semantic and instance, by Bagxi
• Catalyst.Detection - Anchor-free detection pipeline by Avi2011class and TezRomacH
• Catalyst.GAN - Reproducible GANs pipelines by Asmekal
• Catalyst.Neuro - Brain image analysis project, in collaboration with TReNDS Center
• MLComp – Distributed DAG framework for machine learning with UI by Lightforever
• Pytorch toolbelt - PyTorch extensions for fast R&D prototyping and Kaggle farming by BloodAxe
• Helper functions - An assorted collection of helper functions by Ternaus
• BERT Distillation with Catalyst by elephantmipt

• CamVid Segmentation Example - Example of semantic segmentation for CamVid dataset
• Notebook API tutorial for segmentation in Understanding Clouds from Satellite Images Competition
• Catalyst.RL - NeurIPS 2019: Learn to Move - Walk Around – starter kit
• Catalyst.RL - NeurIPS 2019: Animal-AI Olympics - starter kit
• Inria Segmentation Example - An example of training segmentation model for Inria Sattelite Segmentation Challenge
• iglovikov_segmentation - Semantic segmentation pipeline using Catalyst
• Logging Catalyst Runs to Comet - An example of how to log metrics, hyperparameters and more from Catalyst runs to Comet