clip

LightningModule used to train a Clip model.

class mfai.pytorch.lightning_modules.clip.CLIPAccuracySkillScore(top_k, batch_size)

Bases: Metric

CLIP Accuracy Skill Score. The accuracy is computed from the probabilities matrix returned by CLIP. Then we use a uniformly random model as a reference for the skill score. * 0 or negative = worse than random model * 1 = perfect model.

Parameters:

• top_k (int)

• batch_size (int)

compute()

Override this method to compute the final metric value.

This method will automatically synchronize state variables when running in distributed backend.

Return type:

Tensor

update(similarity)

Update the metric state with stats from the cosine similarity matrix.

Return type:

None

Parameters:

similarity (Tensor)

class mfai.pytorch.lightning_modules.clip.CLIPLightningModule(settings, learning_rate=0.0005, min_learning_rate=0.0001, lr_scheduler_interval='step')

Bases: LightningModule

Parameters:

• settings (ClipSettings)

• learning_rate (float)

• min_learning_rate (float)

• lr_scheduler_interval (Literal['step', 'epoch', None])

configure_optimizers()

Lightning method to define optimizers and learning-rate schedulers used for optimization. For more details about this method, please see: https://lightning.ai/docs/pytorch/stable/api/lightning.pytorch.core.LightningModule.html#lightning.pytorch.core.LightningModule.configure_optimizers.

Return type:

Union[Optimizer, Sequence[Optimizer], tuple[Sequence[Optimizer], Sequence[Union[LRScheduler, ReduceLROnPlateau, LRSchedulerConfig]]], OptimizerConfig, OptimizerLRSchedulerConfig, Sequence[OptimizerConfig], Sequence[OptimizerLRSchedulerConfig], None]

forward(images, texts)

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

Parameters:

• *args – Whatever you decide to pass into the forward method.

• **kwargs – Keyword arguments are also possible.

• images (NamedTensor)

• texts (Tensor)

Return type:

Tuple[Tensor, Tensor]

Returns:

Your model’s output

get_hparams()

Return the hparams we want to save in tensorboard logger.

Return type:

dict[str, Any]

plot_probabilities_matrix(sim_matrix)

Plot the clip pair probabilities matrix.

Return type:

Figure

Parameters:

sim_matrix (Tensor)

setup(stage)

Setup metrics and loggers after the trainer and datamodule are defined.

Return type:

None

Parameters:

stage (str)

training_step(batch, batch_idx)

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

Parameters:

• batch (Tuple[NamedTensor, Tensor, Tensor]) – The output of your data iterable, normally a DataLoader.

• batch_idx (int) – The index of this batch.

• dataloader_idx – The index of the dataloader that produced this batch. (only if multiple dataloaders used)

Return type:

Tensor

Returns:

• 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, batch_idx)

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.

Parameters:

• batch (Tuple[NamedTensor, Tensor, Tensor]) – The output of your data iterable, normally a DataLoader.

• batch_idx (int) – The index of this batch.

• dataloader_idx – The index of the dataloader that produced this batch. (only if multiple dataloaders used)

Return type:

Tensor

Returns:

• 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.
    x, y = batch

    # implement your own
    out = self(x)

    if dataloader_idx == 0:
        loss = self.loss0(out, y)
    else:
        loss = self.loss1(out, y)

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

    # log the outputs separately for each dataloader
    self.log_dict({f"val_loss_{dataloader_idx}": loss, f"val_acc_{dataloader_idx}": acc})

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.

class mfai.pytorch.lightning_modules.clip.SaveCLIPVisualEncoderWeights

Bases: Callback

Callback to save the weights of the visual encoder during training.

on_validation_epoch_end(trainer, pl_module)

Called at the end of the validation epoch. Saves the visual encoder weights of CLIP if the validation loss has improved.

Return type:

None

Parameters:

• trainer (Trainer)

• pl_module (LightningModule)