model.detector.Detector#

class Detector(num_classes: int, loss_ratio: float | None = 0.04, time_window: int = 16, iou_threshold: float = 0.4, learning_rate: float = 0.001, clip_grad: int = -1, dt: float = 0.001, state_storage: bool = False, init_weights: bool = True, in_channels: int = 2, sizes: List[List[int]] = [[20, 30, 40], [60, 90, 120], [150, 200, 250]], aspect_ratios: List[List[float]] = [[0.5, 1.0, 2.0], [0.5, 1.0, 2.0], [0.5, 1.0, 2.0]], load_model: str = '', plotter: Plotter | None = None)[source]#

Bases: LightningModule

Basic object detector class

Implements the basic functions for calculating losses, training the network and generating predictions. The network model is passed as a parameter when initializing.

Warning

This class can only be used as a base class for inheritance.

Parameters:

num_classes (int) – Number of classes.
loss_ratio (int, optional) – The ratio of the loss for non-detection to the loss for false positives. The higher this parameter, the more guesses the network generates. This is necessary to keep the network active. Defaults to 0.04.
time_window (int, optional) – The size of the time window at the beginning of the sequence, which can be truncated to a random length. This ensures randomization of the length of training sequences and the ability of the network to work with streaming information. Defaults to 0.
iou_threshold (float, optional) – Minimum acceptable iou. Defaults to 0.4.
learning_rate (float, optional) – Learning rate. Defaults to 0.001.
clip_grad (int, optional) – Number of frames at the end of the sequence used to take the gradient. If less than zero, the gradient is taken over the entire sequence. Defaults to -1.
dt (float, optional) – Time step to use in integration. Defaults to 0.001.
state_storage (bool, optional) – If true preserves preserves all intermediate states of spiking neurons. Necessary for analyzing the network operation. Defaults to False.
init_weights (bool, optional) – If true, apply the weight initialization function. Defaults to True.
in_channels (int, optional) – Number of input channels
sizes (List[List[int]], optional) – List of anchor box sizes. Must contain three nested lists, each containing any number of sizes. The first list corresponds to the feature map with the highest resolution.
aspect_ratios (List[List[float]], optional) – List of aspect ratios of anchor boxes. ratio = height / width. Same format as sizes.
load_model (str, optional) – The name of the model whose weights will be loaded.
plotter (Plotter, optional) – Class for displaying results. Needed for the prediction step. Expects to receive a utils.Plotter object. Defaults to None.

Methods

`configure_optimizers`	Choose what optimizers and learning-rate schedulers to use in your optimization.
`events_forward`	Processes a single time step of event data
`forward`	Main forward method
`image_forward`	Processes a static image
`load`	Loads model weights from HuggingFace Hub if a path is provided
`on_predict_epoch_start`	Called at the beginning of predicting.
`on_test_epoch_end`	Called in the test loop at the very end of the epoch.
`on_validation_epoch_end`	Called in the validation loop at the very end of the epoch.
`on_validation_epoch_start`	Called in the validation loop at the very beginning of the epoch.
`predict`	Returns processed predictions from storage, applying NMS
`predict_step`	Step function called during `predict()`.
`test_step`	Operates on a single batch of data from the test set.
`training_step`	Here you compute and return the training loss and some additional metrics for e.g. the progress bar or logger.
`validation_step`	Operates on a single batch of data from the validation set.

Attributes

training

configure_optimizers() → Optimizer[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. Optimization with multiple optimizers only works in the manual optimization mode.

Return:

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.
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 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.

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

Note:

Some things to know:

Lightning calls .backward() and .step() automatically in case of automatic optimization.
If a 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 optimizer.
If you use torch.optim.LBFGS, Lightning handles the closure function automatically for you.
If you use multiple optimizers, you will have to switch to ‘manual optimization’ mode and step them yourself.
If you need to control how often the optimizer steps, override the optimizer_step() hook.

events_forward(events: Tensor, state: ListState | None = None) → ListState | None[source]#: Processes a single time step of event data

forward(batch: Dict[str, Any]) → Tuple[Tensor, Tensor, Tensor][source]#

Main forward method

Handles both image and event data, processes the batch, and returns predictions.

image_forward(image: Tensor) → None[source]#: Processes a static image

load()[source]#: Loads model weights from HuggingFace Hub if a path is provided

on_predict_epoch_start()[source]#: Called at the beginning of predicting.

on_test_epoch_end()[source]#: Called in the test loop at the very end of the epoch.

on_validation_epoch_end()[source]#: Called in the validation loop at the very end of the epoch.

on_validation_epoch_start()[source]#: Called in the validation loop at the very beginning of the epoch.

predict() → Tensor[source]#: Returns processed predictions from storage, applying NMS

predict_step(batch: Dict[str, Any], batch_idx: int)[source]#

Step function called during predict(). By default, it calls forward(). Override to add any processing logic.

The predict_step() is used to scale inference on multi-devices.

To prevent an OOM error, it is possible to use BasePredictionWriter callback to write the predictions to disk or database after each batch or on epoch end.

The BasePredictionWriter should be used while using a spawn based accelerator. This happens for Trainer(strategy="ddp_spawn") or training on 8 TPU cores with Trainer(accelerator="tpu", devices=8) as predictions won’t be returned.

Args:: batch: The output of your data iterable, normally a DataLoader. batch_idx: The index of this batch. dataloader_idx: The index of the dataloader that produced this batch.

(only if multiple dataloaders used)
Return:: Predicted output (optional).

Example

class MyModel(LightningModule):

    def predict_step(self, batch, batch_idx, dataloader_idx=0):
        return self(batch)

dm = ...
model = MyModel()
trainer = Trainer(accelerator="gpu", devices=2)
predictions = trainer.predict(model, dm)

test_step(batch: Dict[str, Any], batch_idx: int) → Tensor[source]#

Operates on a single batch of data from the test set. In this step you’d normally generate examples or calculate anything of interest such as accuracy.

Args:

batch: The output of your data iterable, normally a DataLoader. batch_idx: The index of this batch. dataloader_idx: The index of the dataloader that produced this batch.

(only if multiple dataloaders used)

Return:

Tensor - The loss tensor
dict - A dictionary. Can include any keys, but must include the key 'loss'.
None - Skip to the next batch.

# if you have one test dataloader:
def test_step(self, batch, batch_idx): ...


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

Examples:

# CASE 1: A single test dataset
def test_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)
    test_acc = torch.sum(y == labels_hat).item() / (len(y) * 1.0)

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

If you pass in multiple test dataloaders, test_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 test dataloaders
def test_step(self, batch, batch_idx, dataloader_idx=0):
    # dataloader_idx tells you which dataset this is.
    ...

Note:: If you don’t need to test you don’t need to implement this method.
Note:: When the test_step() is called, the model has been put in eval mode and PyTorch gradients have been disabled. At the end of the test epoch, the model goes back to training mode and gradients are enabled.

training_step(batch: Dict[str, Any], batch_idx: int) → Tensor[source]#

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

Args:

batch: The output of your data iterable, normally a DataLoader. batch_idx: The index of this batch. dataloader_idx: The index of the dataloader that produced this batch.

(only if multiple dataloaders used)

Return:

Tensor - The loss tensor
dict - A dictionary which can include any keys, but must include the key 'loss' in the case of automatic optimization.
None - In automatic optimization, this will skip to the next batch (but is not supported for multi-GPU, TPU, or DeepSpeed). For manual optimization, this has no special meaning, as returning the loss is not required.

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

To use multiple optimizers, you can switch to ‘manual optimization’ and control their stepping:

def __init__(self):
    super().__init__()
    self.automatic_optimization = False


# Multiple optimizers (e.g.: GANs)
def training_step(self, batch, batch_idx):
    opt1, opt2 = self.optimizers()

    # do training_step with encoder
    ...
    opt1.step()
    # do training_step with decoder
    ...
    opt2.step()

Note:: When accumulate_grad_batches > 1, the loss returned here will be automatically normalized by accumulate_grad_batches internally.

validation_step(batch: Dict[str, Any], batch_idx: int) → Tensor[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.

Args:

batch: The output of your data iterable, normally a DataLoader. batch_idx: The index of this batch. dataloader_idx: The index of the dataloader that produced this batch.

(only if multiple dataloaders used)

Return:

Tensor - The loss tensor
dict - A dictionary. Can include any keys, but must include the key 'loss'.
None - Skip to the next batch.

# 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.

model.detector.Detector

Contents

model.detector.Detector#