Shortcuts

Vision Callbacks

Useful callbacks for vision models


Confused Logit

Shows how the input would have to change to move the prediction from one logit to the other

Example outputs:

Example of prediction confused between 5 and 8
class pl_bolts.callbacks.vision.confused_logit.ConfusedLogitCallback(top_k, projection_factor=3, min_logit_value=5.0, logging_batch_interval=20, max_logit_difference=0.1)[source]

Bases: pytorch_lightning.Callback

Takes the logit predictions of a model and when the probabilities of two classes are very close, the model doesn’t have high certainty that it should pick one vs the other class.

This callback shows how the input would have to change to swing the model from one label prediction to the other.

In this case, the network predicts a 5… but gives almost equal probability to an 8. The images show what about the original 5 would have to change to make it more like a 5 or more like an 8.

For each confused logit the confused images are generated by taking the gradient from a logit wrt an input for the top two closest logits.

Example:

from pl_bolts.callbacks.vision import ConfusedLogitCallback
trainer = Trainer(callbacks=[ConfusedLogitCallback()])

Note

Whenever called, this model will look for self.last_batch and self.last_logits in the LightningModule.

Note

This callback supports tensorboard only right now.

Authored by:

  • Alfredo Canziani

Parameters
  • top_k (int) – How many “offending” images we should plot

  • projection_factor (int) – How much to multiply the input image to make it look more like this logit label

  • min_logit_value (float) – Only consider logit values above this threshold

  • logging_batch_interval (int) – How frequently to inspect/potentially plot something

  • max_logit_difference (float) – When the top 2 logits are within this threshold we consider them confused


Tensorboard Image Generator

Generates images from a generative model and plots to tensorboard

class pl_bolts.callbacks.vision.image_generation.TensorboardGenerativeModelImageSampler(num_samples=3, nrow=8, padding=2, normalize=False, norm_range=None, scale_each=False, pad_value=0)[source]

Bases: pytorch_lightning.Callback

Generates images and logs to tensorboard. Your model must implement the forward function for generation

Requirements:

# model must have img_dim arg
model.img_dim = (1, 28, 28)

# model forward must work for sampling
z = torch.rand(batch_size, latent_dim)
img_samples = your_model(z)

Example:

from pl_bolts.callbacks import TensorboardGenerativeModelImageSampler

trainer = Trainer(callbacks=[TensorboardGenerativeModelImageSampler()])
Parameters
  • num_samples (int) – Number of images displayed in the grid. Default: 3.

  • nrow (int) – Number of images displayed in each row of the grid. The final grid size is (B / nrow, nrow). Default: 8.

  • padding (int) – Amount of padding. Default: 2.

  • normalize (bool) – If True, shift the image to the range (0, 1), by the min and max values specified by range. Default: False.

  • norm_range (Optional[Tuple[int, int]]) – Tuple (min, max) where min and max are numbers, then these numbers are used to normalize the image. By default, min and max are computed from the tensor.

  • scale_each (bool) – If True, scale each image in the batch of images separately rather than the (min, max) over all images. Default: False.

  • pad_value (int) – Value for the padded pixels. Default: 0.

Read the Docs v: 0.3.1
Versions
latest
stable
0.3.1
0.3.0
0.2.5
0.2.4
0.2.3
0.2.2
0.2.1
0.2.0
0.1.1
0.1.0
Downloads
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.