Object Detection¶

This package lists contributed object detection models.

Note

We rely on the community to keep these updated and working. If something doesn’t work, we’d really appreciate a contribution to fix!

Faster R-CNN¶

class pl_bolts.models.detection.faster_rcnn.faster_rcnn_module.FasterRCNN(learning_rate=0.0001, num_classes=91, backbone=None, fpn=True, pretrained=False, pretrained_backbone=True, trainable_backbone_layers=3, **kwargs)[source]

Bases: pytorch_lightning.core.module.LightningModule

Warning

The feature FasterRCNN is currently marked under review. The compatibility with other Lightning projects is not guaranteed and API may change at any time. The API and functionality may change without warning in future releases. More details: https://lightning-bolts.readthedocs.io/en/latest/stability.html

PyTorch Lightning implementation of Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.

Paper authors: Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun

Model implemented by:

Teddy Koker <https://github.com/teddykoker>

During training, the model expects both the input tensors, as well as targets (list of dictionary), containing:

boxes (FloatTensor[N, 4]): the ground truth boxes in [x1, y1, x2, y2] format.
labels (Int64Tensor[N]): the class label for each ground truh box

CLI command:

# PascalVOC
python faster_rcnn_module.py --gpus 1 --pretrained True

Parameters

learning_rate¶ (float) – the learning rate
num_classes¶ (int) – number of detection classes (including background)
backbone¶ (Union[str, Module, None]) – Pretained backbone CNN architecture or torch.nn.Module instance.
fpn¶ (bool) – If True, creates a Feature Pyramind Network on top of Resnet based CNNs.
pretrained¶ (bool) – if true, returns a model pre-trained on COCO train2017
pretrained_backbone¶ (bool) – if true, returns a model with backbone pre-trained on Imagenet
trainable_backbone_layers¶ (int) – number of trainable resnet layers starting from final block

configure_optimizers()[source]

Choose what optimizers and learning-rate schedulers to use in your optimization. Normally you’d need one. But in the case of GANs or similar you might have multiple.

Returns

Any of these 6 options.

Single optimizer.
List or Tuple of optimizers.
Two lists - The first list has multiple optimizers, and the second has multiple LR schedulers (or multiple lr_scheduler_config).
Dictionary, with an "optimizer" key, and (optionally) a "lr_scheduler" key whose value is a single LR scheduler or lr_scheduler_config.
Tuple of dictionaries as described above, with an optional "frequency" key.
None - Fit will run without any optimizer.

The lr_scheduler_config is a dictionary which contains the scheduler and its associated configuration. The default configuration is shown below.

lr_scheduler_config = {
    # REQUIRED: The scheduler instance
    "scheduler": lr_scheduler,
    # The unit of the scheduler's step size, could also be 'step'.
    # 'epoch' updates the scheduler on epoch end whereas 'step'
    # updates it after a optimizer update.
    "interval": "epoch",
    # How many epochs/steps should pass between calls to
    # `scheduler.step()`. 1 corresponds to updating the learning
    # rate after every epoch/step.
    "frequency": 1,
    # Metric to to monitor for schedulers like `ReduceLROnPlateau`
    "monitor": "val_loss",
    # If set to `True`, will enforce that the value specified 'monitor'
    # is available when the scheduler is updated, thus stopping
    # training if not found. If set to `False`, it will only produce a warning
    "strict": True,
    # If using the `LearningRateMonitor` callback to monitor the
    # learning rate progress, this keyword can be used to specify
    # a custom logged name
    "name": None,
}

When there are schedulers in which the .step() method is conditioned on a value, such as the torch.optim.lr_scheduler.ReduceLROnPlateau scheduler, Lightning requires that the lr_scheduler_config contains the keyword "monitor" set to the metric name that the scheduler should be conditioned on.

# The ReduceLROnPlateau scheduler requires a monitor
def configure_optimizers(self):
    optimizer = Adam(...)
    return {
        "optimizer": optimizer,
        "lr_scheduler": {
            "scheduler": ReduceLROnPlateau(optimizer, ...),
            "monitor": "metric_to_track",
            "frequency": "indicates how often the metric is updated"
            # If "monitor" references validation metrics, then "frequency" should be set to a
            # multiple of "trainer.check_val_every_n_epoch".
        },
    }


# In the case of two optimizers, only one using the ReduceLROnPlateau scheduler
def configure_optimizers(self):
    optimizer1 = Adam(...)
    optimizer2 = SGD(...)
    scheduler1 = ReduceLROnPlateau(optimizer1, ...)
    scheduler2 = LambdaLR(optimizer2, ...)
    return (
        {
            "optimizer": optimizer1,
            "lr_scheduler": {
                "scheduler": scheduler1,
                "monitor": "metric_to_track",
            },
        },
        {"optimizer": optimizer2, "lr_scheduler": scheduler2},
    )

Metrics can be made available to monitor by simply logging it using self.log('metric_to_track', metric_val) in your LightningModule.

Note

The frequency value specified in a dict along with the optimizer key is an int corresponding to the number of sequential batches optimized with the specific optimizer. It should be given to none or to all of the optimizers. There is a difference between passing multiple optimizers in a list, and passing multiple optimizers in dictionaries with a frequency of 1:

In the former case, all optimizers will operate on the given batch in each optimization step.

In the latter, only one optimizer will operate on the given batch at every step.

This is different from the frequency value specified in the lr_scheduler_config mentioned above.

def configure_optimizers(self):
    optimizer_one = torch.optim.SGD(self.model.parameters(), lr=0.01)
    optimizer_two = torch.optim.SGD(self.model.parameters(), lr=0.01)
    return [
        {"optimizer": optimizer_one, "frequency": 5},
        {"optimizer": optimizer_two, "frequency": 10},
    ]

In this example, the first optimizer will be used for the first 5 steps, the second optimizer for the next 10 steps and that cycle will continue. If an LR scheduler is specified for an optimizer using the lr_scheduler key in the above dict, the scheduler will only be updated when its optimizer is being used.

Examples:

# most cases. no learning rate scheduler
def configure_optimizers(self):
    return Adam(self.parameters(), lr=1e-3)

# multiple optimizer case (e.g.: GAN)
def configure_optimizers(self):
    gen_opt = Adam(self.model_gen.parameters(), lr=0.01)
    dis_opt = Adam(self.model_dis.parameters(), lr=0.02)
    return gen_opt, dis_opt

# example with learning rate schedulers
def configure_optimizers(self):
    gen_opt = Adam(self.model_gen.parameters(), lr=0.01)
    dis_opt = Adam(self.model_dis.parameters(), lr=0.02)
    dis_sch = CosineAnnealing(dis_opt, T_max=10)
    return [gen_opt, dis_opt], [dis_sch]

# example with step-based learning rate schedulers
# each optimizer has its own scheduler
def configure_optimizers(self):
    gen_opt = Adam(self.model_gen.parameters(), lr=0.01)
    dis_opt = Adam(self.model_dis.parameters(), lr=0.02)
    gen_sch = {
        'scheduler': ExponentialLR(gen_opt, 0.99),
        'interval': 'step'  # called after each training step
    }
    dis_sch = CosineAnnealing(dis_opt, T_max=10) # called every epoch
    return [gen_opt, dis_opt], [gen_sch, dis_sch]

# example with optimizer frequencies
# see training procedure in `Improved Training of Wasserstein GANs`, Algorithm 1
# https://arxiv.org/abs/1704.00028
def configure_optimizers(self):
    gen_opt = Adam(self.model_gen.parameters(), lr=0.01)
    dis_opt = Adam(self.model_dis.parameters(), lr=0.02)
    n_critic = 5
    return (
        {'optimizer': dis_opt, 'frequency': n_critic},
        {'optimizer': gen_opt, 'frequency': 1}
    )

Note

Some things to know:

Lightning calls .backward() and .step() on each optimizer as needed.
If learning rate scheduler is specified in configure_optimizers() with key "interval" (default “epoch”) in the scheduler configuration, Lightning will call the scheduler’s .step() method automatically in case of automatic optimization.
If you use 16-bit precision (precision=16), Lightning will automatically handle the optimizers.
If you use multiple optimizers, training_step() will have an additional optimizer_idx parameter.
If you use torch.optim.LBFGS, Lightning handles the closure function automatically for you.
If you use multiple optimizers, gradients will be calculated only for the parameters of current optimizer at each training step.
If you need to control how often those optimizers step or override the default .step() schedule, override the optimizer_step() hook.

forward(x)[source]

Same as torch.nn.Module.forward().

Parameters

*args¶ – Whatever you decide to pass into the forward method.
**kwargs¶ – Keyword arguments are also possible.

Returns

Your model’s output

training_step(batch, batch_idx)[source]

Here you compute and return the training loss and some additional metrics for e.g. the progress bar or logger.

Parameters

batch¶ (Tensor | (Tensor, …) | [Tensor, …]) – The output of your DataLoader. A tensor, tuple or list.
batch_idx¶ (int) – Integer displaying index of this batch
optimizer_idx¶ (int) – When using multiple optimizers, this argument will also be present.
hiddens¶ (Any) – Passed in if truncated_bptt_steps > 0.

Returns

Any of.

Tensor - The loss tensor
dict - A dictionary. Can include any keys, but must include the key 'loss'
None - Training will skip to the next batch. This is only for automatic optimization.
This is not supported for multi-GPU, TPU, IPU, or DeepSpeed.

In this step you’d normally do the forward pass and calculate the loss for a batch. You can also do fancier things like multiple forward passes or something model specific.

Example:

def training_step(self, batch, batch_idx):
    x, y, z = batch
    out = self.encoder(x)
    loss = self.loss(out, x)
    return loss

If you define multiple optimizers, this step will be called with an additional optimizer_idx parameter.

# Multiple optimizers (e.g.: GANs)
def training_step(self, batch, batch_idx, optimizer_idx):
    if optimizer_idx == 0:
        # do training_step with encoder
        ...
    if optimizer_idx == 1:
        # do training_step with decoder
        ...

If you add truncated back propagation through time you will also get an additional argument with the hidden states of the previous step.

# Truncated back-propagation through time
def training_step(self, batch, batch_idx, hiddens):
    # hiddens are the hidden states from the previous truncated backprop step
    out, hiddens = self.lstm(data, hiddens)
    loss = ...
    return {"loss": loss, "hiddens": hiddens}

Note

The loss value shown in the progress bar is smoothed (averaged) over the last values, so it differs from the actual loss returned in train/validation step.

validation_epoch_end(outs)[source]

Called at the end of the validation epoch with the outputs of all validation steps.

# the pseudocode for these calls
val_outs = []
for val_batch in val_data:
    out = validation_step(val_batch)
    val_outs.append(out)
validation_epoch_end(val_outs)

Parameters: outputs¶ – List of outputs you defined in validation_step(), or if there are multiple dataloaders, a list containing a list of outputs for each dataloader.
Returns: None

Note

If you didn’t define a validation_step(), this won’t be called.

Examples

With a single dataloader:

def validation_epoch_end(self, val_step_outputs):
    for out in val_step_outputs:
        ...

With multiple dataloaders, outputs will be a list of lists. The outer list contains one entry per dataloader, while the inner list contains the individual outputs of each validation step for that dataloader.

def validation_epoch_end(self, outputs):
    for dataloader_output_result in outputs:
        dataloader_outs = dataloader_output_result.dataloader_i_outputs

    self.log("final_metric", final_value)

validation_step(batch, batch_idx)[source]

Operates on a single batch of data from the validation set. In this step you’d might generate examples or calculate anything of interest like accuracy.

# the pseudocode for these calls
val_outs = []
for val_batch in val_data:
    out = validation_step(val_batch)
    val_outs.append(out)
validation_epoch_end(val_outs)

Parameters

batch¶ – The output of your DataLoader.
batch_idx¶ – The index of this batch.
dataloader_idx¶ – The index of the dataloader that produced this batch. (only if multiple val dataloaders used)

Returns

Any object or value
None - Validation will skip to the next batch

# pseudocode of order
val_outs = []
for val_batch in val_data:
    out = validation_step(val_batch)
    if defined("validation_step_end"):
        out = validation_step_end(out)
    val_outs.append(out)
val_outs = validation_epoch_end(val_outs)

# if you have one val dataloader:
def validation_step(self, batch, batch_idx):
    ...


# if you have multiple val dataloaders:
def validation_step(self, batch, batch_idx, dataloader_idx=0):
    ...

Examples:

# CASE 1: A single validation dataset
def validation_step(self, batch, batch_idx):
    x, y = batch

    # implement your own
    out = self(x)
    loss = self.loss(out, y)

    # log 6 example images
    # or generated text... or whatever
    sample_imgs = x[:6]
    grid = torchvision.utils.make_grid(sample_imgs)
    self.logger.experiment.add_image('example_images', grid, 0)

    # calculate acc
    labels_hat = torch.argmax(out, dim=1)
    val_acc = torch.sum(y == labels_hat).item() / (len(y) * 1.0)

    # log the outputs!
    self.log_dict({'val_loss': loss, 'val_acc': val_acc})

If you pass in multiple val dataloaders, validation_step() will have an additional argument. We recommend setting the default value of 0 so that you can quickly switch between single and multiple dataloaders.

# CASE 2: multiple validation dataloaders
def validation_step(self, batch, batch_idx, dataloader_idx=0):
    # dataloader_idx tells you which dataset this is.
    ...

Note

If you don’t need to validate you don’t need to implement this method.

Note

When the validation_step() is called, the model has been put in eval mode and PyTorch gradients have been disabled. At the end of validation, the model goes back to training mode and gradients are enabled.

RetinaNet¶

class pl_bolts.models.detection.retinanet.retinanet_module.RetinaNet(learning_rate=0.0001, num_classes=91, backbone=None, fpn=True, pretrained=False, pretrained_backbone=True, trainable_backbone_layers=3, **kwargs)[source]

Bases: pytorch_lightning.core.module.LightningModule

Warning

The feature RetinaNet is currently marked under review. The compatibility with other Lightning projects is not guaranteed and API may change at any time. The API and functionality may change without warning in future releases. More details: https://lightning-bolts.readthedocs.io/en/latest/stability.html

PyTorch Lightning implementation of RetinaNet.

Paper: Focal Loss for Dense Object Detection.

Paper authors: Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, Piotr Dollár

Model implemented by:

Aditya Oke <https://github.com/oke-aditya>

During training, the model expects both the input tensors, as well as targets (list of dictionary), containing:

boxes (FloatTensor[N, 4]): the ground truth boxes in [x1, y1, x2, y2] format.
labels (Int64Tensor[N]): the class label for each ground truh box

CLI command:

# PascalVOC using LightningCLI
python retinanet_module.py --trainer.gpus 1 --model.pretrained True

Parameters

learning_rate¶ (float) – the learning rate
num_classes¶ (int) – number of detection classes (including background)
backbone¶ (Optional[str]) – Pretained backbone CNN architecture.
fpn¶ (bool) – If True, creates a Feature Pyramind Network on top of Resnet based CNNs.
pretrained¶ (bool) – if true, returns a model pre-trained on COCO train2017
pretrained_backbone¶ (bool) – if true, returns a model with backbone pre-trained on Imagenet
trainable_backbone_layers¶ (int) – number of trainable resnet layers starting from final block

configure_optimizers()[source]

Choose what optimizers and learning-rate schedulers to use in your optimization. Normally you’d need one. But in the case of GANs or similar you might have multiple.

Returns

Any of these 6 options.

Single optimizer.
List or Tuple of optimizers.
Two lists - The first list has multiple optimizers, and the second has multiple LR schedulers (or multiple lr_scheduler_config).
Dictionary, with an "optimizer" key, and (optionally) a "lr_scheduler" key whose value is a single LR scheduler or lr_scheduler_config.
Tuple of dictionaries as described above, with an optional "frequency" key.
None - Fit will run without any optimizer.

The lr_scheduler_config is a dictionary which contains the scheduler and its associated configuration. The default configuration is shown below.

lr_scheduler_config = {
    # REQUIRED: The scheduler instance
    "scheduler": lr_scheduler,
    # The unit of the scheduler's step size, could also be 'step'.
    # 'epoch' updates the scheduler on epoch end whereas 'step'
    # updates it after a optimizer update.
    "interval": "epoch",
    # How many epochs/steps should pass between calls to
    # `scheduler.step()`. 1 corresponds to updating the learning
    # rate after every epoch/step.
    "frequency": 1,
    # Metric to to monitor for schedulers like `ReduceLROnPlateau`
    "monitor": "val_loss",
    # If set to `True`, will enforce that the value specified 'monitor'
    # is available when the scheduler is updated, thus stopping
    # training if not found. If set to `False`, it will only produce a warning
    "strict": True,
    # If using the `LearningRateMonitor` callback to monitor the
    # learning rate progress, this keyword can be used to specify
    # a custom logged name
    "name": None,
}

When there are schedulers in which the .step() method is conditioned on a value, such as the torch.optim.lr_scheduler.ReduceLROnPlateau scheduler, Lightning requires that the lr_scheduler_config contains the keyword "monitor" set to the metric name that the scheduler should be conditioned on.

# The ReduceLROnPlateau scheduler requires a monitor
def configure_optimizers(self):
    optimizer = Adam(...)
    return {
        "optimizer": optimizer,
        "lr_scheduler": {
            "scheduler": ReduceLROnPlateau(optimizer, ...),
            "monitor": "metric_to_track",
            "frequency": "indicates how often the metric is updated"
            # If "monitor" references validation metrics, then "frequency" should be set to a
            # multiple of "trainer.check_val_every_n_epoch".
        },
    }


# In the case of two optimizers, only one using the ReduceLROnPlateau scheduler
def configure_optimizers(self):
    optimizer1 = Adam(...)
    optimizer2 = SGD(...)
    scheduler1 = ReduceLROnPlateau(optimizer1, ...)
    scheduler2 = LambdaLR(optimizer2, ...)
    return (
        {
            "optimizer": optimizer1,
            "lr_scheduler": {
                "scheduler": scheduler1,
                "monitor": "metric_to_track",
            },
        },
        {"optimizer": optimizer2, "lr_scheduler": scheduler2},
    )

Metrics can be made available to monitor by simply logging it using self.log('metric_to_track', metric_val) in your LightningModule.

Note

The frequency value specified in a dict along with the optimizer key is an int corresponding to the number of sequential batches optimized with the specific optimizer. It should be given to none or to all of the optimizers. There is a difference between passing multiple optimizers in a list, and passing multiple optimizers in dictionaries with a frequency of 1:

In the former case, all optimizers will operate on the given batch in each optimization step.

In the latter, only one optimizer will operate on the given batch at every step.

This is different from the frequency value specified in the lr_scheduler_config mentioned above.

def configure_optimizers(self):
    optimizer_one = torch.optim.SGD(self.model.parameters(), lr=0.01)
    optimizer_two = torch.optim.SGD(self.model.parameters(), lr=0.01)
    return [
        {"optimizer": optimizer_one, "frequency": 5},
        {"optimizer": optimizer_two, "frequency": 10},
    ]

In this example, the first optimizer will be used for the first 5 steps, the second optimizer for the next 10 steps and that cycle will continue. If an LR scheduler is specified for an optimizer using the lr_scheduler key in the above dict, the scheduler will only be updated when its optimizer is being used.

Examples:

# most cases. no learning rate scheduler
def configure_optimizers(self):
    return Adam(self.parameters(), lr=1e-3)

# multiple optimizer case (e.g.: GAN)
def configure_optimizers(self):
    gen_opt = Adam(self.model_gen.parameters(), lr=0.01)
    dis_opt = Adam(self.model_dis.parameters(), lr=0.02)
    return gen_opt, dis_opt

# example with learning rate schedulers
def configure_optimizers(self):
    gen_opt = Adam(self.model_gen.parameters(), lr=0.01)
    dis_opt = Adam(self.model_dis.parameters(), lr=0.02)
    dis_sch = CosineAnnealing(dis_opt, T_max=10)
    return [gen_opt, dis_opt], [dis_sch]

# example with step-based learning rate schedulers
# each optimizer has its own scheduler
def configure_optimizers(self):
    gen_opt = Adam(self.model_gen.parameters(), lr=0.01)
    dis_opt = Adam(self.model_dis.parameters(), lr=0.02)
    gen_sch = {
        'scheduler': ExponentialLR(gen_opt, 0.99),
        'interval': 'step'  # called after each training step
    }
    dis_sch = CosineAnnealing(dis_opt, T_max=10) # called every epoch
    return [gen_opt, dis_opt], [gen_sch, dis_sch]

# example with optimizer frequencies
# see training procedure in `Improved Training of Wasserstein GANs`, Algorithm 1
# https://arxiv.org/abs/1704.00028
def configure_optimizers(self):
    gen_opt = Adam(self.model_gen.parameters(), lr=0.01)
    dis_opt = Adam(self.model_dis.parameters(), lr=0.02)
    n_critic = 5
    return (
        {'optimizer': dis_opt, 'frequency': n_critic},
        {'optimizer': gen_opt, 'frequency': 1}
    )

Note

Some things to know:

Lightning calls .backward() and .step() on each optimizer as needed.
If learning rate scheduler is specified in configure_optimizers() with key "interval" (default “epoch”) in the scheduler configuration, Lightning will call the scheduler’s .step() method automatically in case of automatic optimization.
If you use 16-bit precision (precision=16), Lightning will automatically handle the optimizers.
If you use multiple optimizers, training_step() will have an additional optimizer_idx parameter.
If you use torch.optim.LBFGS, Lightning handles the closure function automatically for you.
If you use multiple optimizers, gradients will be calculated only for the parameters of current optimizer at each training step.
If you need to control how often those optimizers step or override the default .step() schedule, override the optimizer_step() hook.

forward(x)[source]

Same as torch.nn.Module.forward().

Parameters

*args¶ – Whatever you decide to pass into the forward method.
**kwargs¶ – Keyword arguments are also possible.

Returns

Your model’s output

training_step(batch, batch_idx)[source]

Here you compute and return the training loss and some additional metrics for e.g. the progress bar or logger.

Parameters

batch¶ (Tensor | (Tensor, …) | [Tensor, …]) – The output of your DataLoader. A tensor, tuple or list.
batch_idx¶ (int) – Integer displaying index of this batch
optimizer_idx¶ (int) – When using multiple optimizers, this argument will also be present.
hiddens¶ (Any) – Passed in if truncated_bptt_steps > 0.

Returns

Any of.

Tensor - The loss tensor
dict - A dictionary. Can include any keys, but must include the key 'loss'
None - Training will skip to the next batch. This is only for automatic optimization.
This is not supported for multi-GPU, TPU, IPU, or DeepSpeed.

In this step you’d normally do the forward pass and calculate the loss for a batch. You can also do fancier things like multiple forward passes or something model specific.

Example:

def training_step(self, batch, batch_idx):
    x, y, z = batch
    out = self.encoder(x)
    loss = self.loss(out, x)
    return loss

If you define multiple optimizers, this step will be called with an additional optimizer_idx parameter.

# Multiple optimizers (e.g.: GANs)
def training_step(self, batch, batch_idx, optimizer_idx):
    if optimizer_idx == 0:
        # do training_step with encoder
        ...
    if optimizer_idx == 1:
        # do training_step with decoder
        ...

If you add truncated back propagation through time you will also get an additional argument with the hidden states of the previous step.

# Truncated back-propagation through time
def training_step(self, batch, batch_idx, hiddens):
    # hiddens are the hidden states from the previous truncated backprop step
    out, hiddens = self.lstm(data, hiddens)
    loss = ...
    return {"loss": loss, "hiddens": hiddens}

Note

The loss value shown in the progress bar is smoothed (averaged) over the last values, so it differs from the actual loss returned in train/validation step.

validation_epoch_end(outs)[source]

Called at the end of the validation epoch with the outputs of all validation steps.

# the pseudocode for these calls
val_outs = []
for val_batch in val_data:
    out = validation_step(val_batch)
    val_outs.append(out)
validation_epoch_end(val_outs)

Parameters: outputs¶ – List of outputs you defined in validation_step(), or if there are multiple dataloaders, a list containing a list of outputs for each dataloader.
Returns: None

Note

If you didn’t define a validation_step(), this won’t be called.

Examples

With a single dataloader:

def validation_epoch_end(self, val_step_outputs):
    for out in val_step_outputs:
        ...

With multiple dataloaders, outputs will be a list of lists. The outer list contains one entry per dataloader, while the inner list contains the individual outputs of each validation step for that dataloader.

def validation_epoch_end(self, outputs):
    for dataloader_output_result in outputs:
        dataloader_outs = dataloader_output_result.dataloader_i_outputs

    self.log("final_metric", final_value)

validation_step(batch, batch_idx)[source]

Operates on a single batch of data from the validation set. In this step you’d might generate examples or calculate anything of interest like accuracy.

# the pseudocode for these calls
val_outs = []
for val_batch in val_data:
    out = validation_step(val_batch)
    val_outs.append(out)
validation_epoch_end(val_outs)

Parameters

batch¶ – The output of your DataLoader.
batch_idx¶ – The index of this batch.
dataloader_idx¶ – The index of the dataloader that produced this batch. (only if multiple val dataloaders used)

Returns

Any object or value
None - Validation will skip to the next batch

# pseudocode of order
val_outs = []
for val_batch in val_data:
    out = validation_step(val_batch)
    if defined("validation_step_end"):
        out = validation_step_end(out)
    val_outs.append(out)
val_outs = validation_epoch_end(val_outs)

# if you have one val dataloader:
def validation_step(self, batch, batch_idx):
    ...


# if you have multiple val dataloaders:
def validation_step(self, batch, batch_idx, dataloader_idx=0):
    ...

Examples:

# CASE 1: A single validation dataset
def validation_step(self, batch, batch_idx):
    x, y = batch

    # implement your own
    out = self(x)
    loss = self.loss(out, y)

    # log 6 example images
    # or generated text... or whatever
    sample_imgs = x[:6]
    grid = torchvision.utils.make_grid(sample_imgs)
    self.logger.experiment.add_image('example_images', grid, 0)

    # calculate acc
    labels_hat = torch.argmax(out, dim=1)
    val_acc = torch.sum(y == labels_hat).item() / (len(y) * 1.0)

    # log the outputs!
    self.log_dict({'val_loss': loss, 'val_acc': val_acc})

If you pass in multiple val dataloaders, validation_step() will have an additional argument. We recommend setting the default value of 0 so that you can quickly switch between single and multiple dataloaders.

# CASE 2: multiple validation dataloaders
def validation_step(self, batch, batch_idx, dataloader_idx=0):
    # dataloader_idx tells you which dataset this is.
    ...

Note

If you don’t need to validate you don’t need to implement this method.

Note

When the validation_step() is called, the model has been put in eval mode and PyTorch gradients have been disabled. At the end of validation, the model goes back to training mode and gradients are enabled.

YOLO¶

class pl_bolts.models.detection.yolo.yolo_module.YOLO(network, optimizer=<class 'torch.optim.sgd.SGD'>, optimizer_params={'lr': 0.001, 'momentum': 0.9, 'weight_decay': 0.0005}, lr_scheduler=<class 'pl_bolts.optimizers.lr_scheduler.LinearWarmupCosineAnnealingLR'>, lr_scheduler_params={'max_epochs': 300, 'warmup_epochs': 1, 'warmup_start_lr': 0.0}, confidence_threshold=0.2, nms_threshold=0.45, max_predictions_per_image=-1)[source]

Bases: pytorch_lightning.core.module.LightningModule

Warning

The feature YOLO is currently marked under review. The compatibility with other Lightning projects is not guaranteed and API may change at any time. The API and functionality may change without warning in future releases. More details: https://lightning-bolts.readthedocs.io/en/latest/stability.html

PyTorch Lightning implementation of YOLOv3 and YOLOv4.

YOLOv3 paper: Joseph Redmon and Ali Farhadi

YOLOv4 paper: Alexey Bochkovskiy, Chien-Yao Wang, and Hong-Yuan Mark Liao

Implementation: Seppo Enarvi

The network architecture can be read from a Darknet configuration file using the YOLOConfiguration class, or created by some other means, and provided as a list of PyTorch modules.

The input from the data loader is expected to be a list of images. Each image is a tensor with shape [channels, height, width]. The images from a single batch will be stacked into a single tensor, so the sizes have to match. Different batches can have different image sizes, as long as the size is divisible by the ratio in which the network downsamples the input.

During training, the model expects both the input tensors and a list of targets. Each target is a dictionary containing:

boxes (FloatTensor[N, 4]): the ground-truth boxes in (x1, y1, x2, y2) format
labels (Int64Tensor[N]): the class label for each ground-truth box

forward() method returns all predictions from all detection layers in all images in one tensor with shape [images, predictors, classes + 5]. The coordinates are scaled to the input image size. During training it also returns a dictionary containing the classification, box overlap, and confidence losses.

During inference, the model requires only the input tensors. infer() method filters and processes the predictions. The processed output includes the following tensors:

boxes (FloatTensor[N, 4]): predicted bounding box (x1, y1, x2, y2) coordinates in image space
scores (FloatTensor[N]): detection confidences
labels (Int64Tensor[N]): the predicted labels for each image

Weights can be loaded from a Darknet model file using load_darknet_weights().

CLI command:

# PascalVOC
wget https://raw.githubusercontent.com/AlexeyAB/darknet/master/cfg/yolov4-tiny-3l.cfg
python yolo_module.py --config yolov4-tiny-3l.cfg --data_dir . --gpus 8 --batch_size 8

Parameters

network¶ (ModuleList) – A list of network modules. This can be obtained from a Darknet configuration using the get_network() method.
optimizer¶ (Type[Optimizer]) – Which optimizer class to use for training.
optimizer_params¶ (Dict[str, Any]) – Parameters to pass to the optimizer constructor.
lr_scheduler¶ (Type[_LRScheduler]) – Which learning rate scheduler class to use for training.
lr_scheduler_params¶ (Dict[str, Any]) – Parameters to pass to the learning rate scheduler constructor.
confidence_threshold¶ (float) – Postprocessing will remove bounding boxes whose confidence score is not higher than this threshold.
nms_threshold¶ (float) – Non-maximum suppression will remove bounding boxes whose IoU with a higher confidence box is higher than this threshold, if the predicted categories are equal.
max_predictions_per_image¶ (int) – If non-negative, keep at most this number of highest-confidence predictions per image.

configure_optimizers()[source]

Constructs the optimizer and learning rate scheduler.

Return type: Tuple[List, List]

forward(images, targets=None)[source]

Runs a forward pass through the network (all layers listed in self.network), and if training targets are provided, computes the losses from the detection layers.

Detections are concatenated from the detection layers. Each image will produce N * num_anchors * grid_height * grid_width detections, where N depends on the number of detection layers. For one detection layer N = 1, and each detection layer increases it by a number that depends on the size of the feature map on that layer. For example, if the feature map is twice as wide and high as the grid, the layer will add four times more features.

Parameters

images¶ (Tensor) – Images to be processed. Tensor of size [batch_size, num_channels, height, width].
targets¶ (Optional[List[Dict[str, Tensor]]]) – If set, computes losses from detection layers against these targets. A list of dictionaries, one for each image.

Returns

Detections, and if targets were provided, a dictionary of losses. Detections are shaped [batch_size, num_predictors, num_classes + 5], where num_predictors is the total number of cells in all detection layers times the number of boxes predicted by one cell. The predicted box coordinates are in (x1, y1, x2, y2) format and scaled to the input image size.

Return type

detections (Tensor), losses (Dict[str, Tensor])

infer(image)[source]

Feeds an image to the network and returns the detected bounding boxes, confidence scores, and class labels.

Parameters: image¶ (Tensor) – An input image, a tensor of uint8 values sized [channels, height, width].
Returns: A matrix of detected bounding box (x1, y1, x2, y2) coordinates, a vector of confidences for the bounding box detections, and a vector of predicted class labels.
Return type: boxes (Tensor), confidences (Tensor), labels (Tensor)

load_darknet_weights(weight_file)[source]

Loads weights to layer modules from a pretrained Darknet model.

One may want to continue training from the pretrained weights, on a dataset with a different number of object categories. The number of kernels in the convolutional layers just before each detection layer depends on the number of output classes. The Darknet solution is to truncate the weight file and stop reading weights at the first incompatible layer. For this reason the function silently leaves the rest of the layers unchanged, when the weight file ends.

Parameters: weight_file¶ – A file object containing model weights in the Darknet binary format.

test_step(batch, batch_idx)[source]

Evaluates a batch of data from the test set.

Parameters

batch¶ (Tuple[List[Tensor], List[Dict[str, Tensor]]]) – A tuple of images and targets. Images is a list of 3-dimensional tensors. Targets is a list of dictionaries that contain ground-truth boxes, labels, etc.
batch_idx¶ (int) – The index of this batch.

training_step(batch, batch_idx)[source]

Computes the training loss.

Parameters

batch¶ (Tuple[List[Tensor], List[Dict[str, Tensor]]]) – A tuple of images and targets. Images is a list of 3-dimensional tensors. Targets is a list of dictionaries that contain ground-truth boxes, labels, etc.
batch_idx¶ (int) – The index of this batch.

Return type

Dict[str, Tensor]

Returns

A dictionary that includes the training loss in ‘loss’.

validation_step(batch, batch_idx)[source]

Evaluates a batch of data from the validation set.

Parameters

batch¶ (Tuple[List[Tensor], List[Dict[str, Tensor]]]) – A tuple of images and targets. Images is a list of 3-dimensional tensors. Targets is a list of dictionaries that contain ground-truth boxes, labels, etc.
batch_idx¶ (int) – The index of this batch