From 51e2e13e114a14a1d2ca2bc2822ed2b085367a2e Mon Sep 17 00:00:00 2001
From: Andre Anjos <andre.dos.anjos@gmail.com>
Date: Wed, 2 Aug 2023 12:25:22 +0200
Subject: [PATCH] [models.densenet_rs] Remove outdated module (functionality is
now incorporated at stock densenet model)
---
pyproject.toml | 1 -
src/ptbench/models/densenet_rs.py | 107 ------------------------------
2 files changed, 108 deletions(-)
delete mode 100644 src/ptbench/models/densenet_rs.py
diff --git a/pyproject.toml b/pyproject.toml
index 30531b7c..ded50f8f 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -72,7 +72,6 @@ ptbench = "ptbench.scripts.cli:cli"
pasa = "ptbench.configs.models.pasa"
signs-to-tb = "ptbench.configs.models.signs_to_tb"
logistic-regression = "ptbench.configs.models.logistic_regression"
-densenet-rs = "ptbench.configs.models_datasets.densenet_rs"
alexnet = "ptbench.configs.models.alexnet"
alexnet-pretrained = "ptbench.configs.models.alexnet_pretrained"
densenet = "ptbench.configs.models.densenet"
diff --git a/src/ptbench/models/densenet_rs.py b/src/ptbench/models/densenet_rs.py
deleted file mode 100644
index 0fbf2b25..00000000
--- a/src/ptbench/models/densenet_rs.py
+++ /dev/null
@@ -1,107 +0,0 @@
-# SPDX-FileCopyrightText: Copyright © 2023 Idiap Research Institute <contact@idiap.ch>
-#
-# SPDX-License-Identifier: GPL-3.0-or-later
-
-import lightning.pytorch as pl
-import torch
-import torch.nn as nn
-import torchvision.models as models
-
-from .normalizer import TorchVisionNormalizer
-
-
-class DensenetRS(pl.LightningModule):
- """Densenet121 module for radiological extraction."""
-
- def __init__(
- self,
- criterion,
- criterion_valid,
- optimizer,
- optimizer_configs,
- ):
- super().__init__()
-
- self.save_hyperparameters(ignore=["criterion", "criterion_valid"])
-
- self.name = "DensenetRS"
-
- self.normalizer = TorchVisionNormalizer()
-
- # Load pretrained model
- self.model_ft = models.densenet121(
- weights=models.DenseNet121_Weights.DEFAULT
- )
-
- # Adapt output features
- num_ftrs = self.model_ft.classifier.in_features
- self.model_ft.classifier = nn.Linear(num_ftrs, 14)
-
- def forward(self, x):
- x = self.normalizer(x)
- x = self.model_ft(x)
- return x
-
- def training_step(self, batch, batch_idx):
- images = batch[1]
- labels = batch[2]
-
- # Increase label dimension if too low
- # Allows single and multiclass usage
- if labels.ndim == 1:
- labels = torch.reshape(labels, (labels.shape[0], 1))
-
- # Forward pass on the network
- outputs = self(images)
-
- # Manually move criterion to selected device, since not part of the model.
- self.hparams.criterion = self.hparams.criterion.to(self.device)
- training_loss = self.hparams.criterion(outputs, labels.float())
-
- return {"loss": training_loss}
-
- def validation_step(self, batch, batch_idx, dataloader_idx=0):
- images = batch[1]
- labels = batch[2]
-
- # Increase label dimension if too low
- # Allows single and multiclass usage
- if labels.ndim == 1:
- labels = torch.reshape(labels, (labels.shape[0], 1))
-
- # data forwarding on the existing network
- outputs = self(images)
-
- # Manually move criterion to selected device, since not part of the model.
- self.hparams.criterion_valid = self.hparams.criterion_valid.to(
- self.device
- )
- validation_loss = self.hparams.criterion_valid(outputs, labels.float())
-
- if dataloader_idx == 0:
- return {"validation_loss": validation_loss}
- else:
- return {f"extra_validation_loss_{dataloader_idx}": validation_loss}
-
- def predict_step(self, batch, batch_idx, dataloader_idx=0, grad_cams=False):
- names = batch[0]
- images = batch[1]
-
- outputs = self(images)
- probabilities = torch.sigmoid(outputs)
-
- # necessary check for HED architecture that uses several outputs
- # for loss calculation instead of just the last concatfuse block
- if isinstance(outputs, list):
- outputs = outputs[-1]
-
- return names[0], torch.flatten(probabilities), torch.flatten(batch[2])
-
- def configure_optimizers(self):
- # Dynamically instantiates the optimizer given the configs
- optimizer = getattr(torch.optim, self.hparams.optimizer)(
- filter(lambda p: p.requires_grad, self.model_ft.parameters()),
- **self.hparams.optimizer_configs,
- )
-
- return optimizer
--
GitLab