implement simple model

models/notebooks/1.0-hfk-datamodules-exploration.ipynb

@@ -393,7 +393,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 15,
+ "execution_count": 8,
  "metadata": {},
  "outputs": [
  {
@@ -402,7 +402,7 @@
  "64"
  ]
  },
- "execution_count": 15,
+ "execution_count": 8,
  "metadata": {},
  "output_type": "execute_result"
  }
@@ -413,6 +413,53 @@
  "\n",
  "len(data[\"focus_value\"])"
  ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/home/hku/.local/lib/python3.8/site-packages/torch/nn/modules/loss.py:96: UserWarning: Using a target size (torch.Size([64])) that is different to the input size (torch.Size([64, 1])). This will likely lead to incorrect results due to broadcasting. Please ensure they have the same size.\n",
+ " return F.l1_loss(input, target, reduction=self.reduction)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "(tensor(2.5787, grad_fn=<L1LossBackward0>),\n",
+ " tensor([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
+ " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
+ " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]),\n",
+ " tensor([-1.2805, -0.0943, -2.3645, 0.8542, -0.8047, -6.0020, 0.0000, -4.3352,\n",
+ " -1.8066, -2.7189, -6.4697, -3.2557, -4.2778, -5.0264, -3.4891, 0.0000,\n",
+ " -1.7181, -2.7314, 0.3324, -0.0943, -0.8991, 0.0000, -4.4178, 1.9723,\n",
+ " -3.0026, -5.5685, 3.8374, 3.8625, -0.4125, -4.1936, -1.5781, -1.6393,\n",
+ " -2.9583, -5.4933, -1.7807, -3.3135, -5.3423, -0.7978, -5.3971, -4.9412,\n",
+ " 0.0000, -4.4128, -5.7744, -5.2755, -1.0996, -5.7482, 0.0000, -0.1737,\n",
+ " -3.5851, -6.1429, -6.3642, -3.9653, -0.2081, -0.9539, -0.4159, -0.5388,\n",
+ " -1.3643, -4.4441, -1.5161, 0.6395, -5.4710, -2.6482, 0.0000, -2.6257],\n",
+ " dtype=torch.float64))"
+ ]
+ },
+ "execution_count": 9,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "import types\n",
+ "import importlib.machinery\n",
+ "focus_module = SourceFileLoader('focus_module', '../src/models/focus_module.py').load_module()\n",
+ "from focus_module import FocusLitModule\n",
+ "\n",
+ "model = FocusLitModule()\n",
+ "\n",
+ "model.step(data)"
+ ]
  }
  ],
  "metadata": {

models/requirements.txt

@@ -6,6 +6,7 @@ torchmetrics>=0.7.0
 
 # --------- data and model dependencies --------- #
 scikit-image
+pandas
 
 # --------- hydra --------- #
 hydra-core>=1.1.0

models/src/datamodules/focus_datamodule.py

@@ -51,7 +51,7 @@ class FocusDataSet(Dataset):
  sample = {"image": image, "focus_value": focus_value}
 
  if self.transform:
- sample = self.transform(sample)
+ sample["image"] = self.transform(sample["image"])
 
  return sample
 
@@ -76,7 +76,9 @@ class FocusDataModule(LightningDataModule):
  self.save_hyperparameters(logger=False)
 
  # data transformations
- self.transforms = transforms.Compose([])
+ self.transforms = transforms.Compose(
+ [transforms.ToTensor(), transforms.ConvertImageDtype(torch.float)]
+ )
 
  self.data_train: Optional[Dataset] = None
  self.data_val: Optional[Dataset] = None

models/src/models/focus_module.py

@@ -0,0 +1,157 @@
+from typing import Any, List
+
+import torch
+from torch import nn
+from pytorch_lightning import LightningModule
+from torchmetrics import MaxMetric, MeanAbsoluteError, MinMetric
+from torchmetrics.classification.accuracy import Accuracy
+
+
+class SimpleDenseNet(nn.Module):
+ def __init__(self, hparams: dict):
+ super().__init__()
+
+ self.model = nn.Sequential(
+ nn.Linear(hparams["input_size"], hparams["lin1_size"]),
+ nn.BatchNorm1d(hparams["lin1_size"]),
+ nn.ReLU(),
+ nn.Linear(hparams["lin1_size"], hparams["lin2_size"]),
+ nn.BatchNorm1d(hparams["lin2_size"]),
+ nn.ReLU(),
+ nn.Linear(hparams["lin2_size"], hparams["lin3_size"]),
+ nn.BatchNorm1d(hparams["lin3_size"]),
+ nn.ReLU(),
+ nn.Linear(hparams["lin3_size"], hparams["output_size"]),
+ )
+
+ def forward(self, x):
+ batch_size, channels, width, height = x.size()
+
+ # (batch, 1, width, height) -> (batch, 1*width*height)
+ x = x.view(batch_size, -1)
+
+ return self.model(x)
+
+
+class FocusLitModule(LightningModule):
+ """
+ Example of LightningModule for MNIST classification.
+
+ A LightningModule organizes your PyTorch code into 5 sections:
+ - Computations (init).
+ - Train loop (training_step)
+ - Validation loop (validation_step)
+ - Test loop (test_step)
+ - Optimizers (configure_optimizers)
+
+ Read the docs:
+ https://pytorch-lightning.readthedocs.io/en/latest/common/lightning_module.html
+ """
+
+ def __init__(
+ self,
+ input_size: int = 75 * 75 * 3,
+ lin1_size: int = 256,
+ lin2_size: int = 256,
+ lin3_size: int = 256,
+ output_size: int = 1,
+ lr: float = 0.001,
+ weight_decay: float = 0.0005,
+ ):
+ super().__init__()
+
+ # this line allows to access init params with 'self.hparams' attribute
+ # it also ensures init params will be stored in ckpt
+ self.save_hyperparameters(logger=False)
+
+ self.model = SimpleDenseNet(hparams=self.hparams)
+
+ # loss function
+ self.criterion = torch.nn.L1Loss()
+
+ # use separate metric instance for train, val and test step
+ # to ensure a proper reduction over the epoch
+ self.train_acc = MeanAbsoluteError()
+ self.val_acc = MeanAbsoluteError()
+ self.test_acc = MeanAbsoluteError()
+
+ # for logging best so far validation accuracy
+ self.val_acc_best = MinMetric()
+
+ def forward(self, x: torch.Tensor):
+ return self.model(x)
+
+ def step(self, batch: Any):
+ x = batch["image"]
+ y = batch["focus_value"]
+ logits = self.forward(x)
+ loss = self.criterion(logits, y)
+ preds = torch.argmax(logits, dim=1)
+ return loss, preds, y
+
+ def training_step(self, batch: Any, batch_idx: int):
+ loss, preds, targets = self.step(batch)
+
+ # log train metrics
+ acc = self.train_acc(preds, targets)
+ self.log("train/loss", loss, on_step=False, on_epoch=True, prog_bar=False)
+ self.log("train/acc", acc, on_step=False, on_epoch=True, prog_bar=True)
+
+ # we can return here dict with any tensors
+ # and then read it in some callback or in `training_epoch_end()`` below
+ # remember to always return loss from `training_step()` or else backpropagation will fail!
+ return {"loss": loss, "preds": preds, "targets": targets}
+
+ def training_epoch_end(self, outputs: List[Any]):
+ # `outputs` is a list of dicts returned from `training_step()`
+ pass
+
+ def validation_step(self, batch: Any, batch_idx: int):
+ loss, preds, targets = self.step(batch)
+
+ # log val metrics
+ acc = self.val_acc(preds, targets)
+ self.log("val/loss", loss, on_step=False, on_epoch=True, prog_bar=False)
+ self.log("val/acc", acc, on_step=False, on_epoch=True, prog_bar=True)
+
+ return {"loss": loss, "preds": preds, "targets": targets}
+
+ def validation_epoch_end(self, outputs: List[Any]):
+ acc = self.val_acc.compute() # get val accuracy from current epoch
+ self.val_acc_best.update(acc)
+ self.log(
+ "val/acc_best", self.val_acc_best.compute(), on_epoch=True, prog_bar=True
+ )
+
+ def test_step(self, batch: Any, batch_idx: int):
+ loss, preds, targets = self.step(batch)
+
+ # log test metrics
+ acc = self.test_acc(preds, targets)
+ self.log("test/loss", loss, on_step=False, on_epoch=True)
+ self.log("test/acc", acc, on_step=False, on_epoch=True)
+
+ return {"loss": loss, "preds": preds, "targets": targets}
+
+ def test_epoch_end(self, outputs: List[Any]):
+ pass
+
+ def on_epoch_end(self):
+ # reset metrics at the end of every epoch
+ self.train_acc.reset()
+ self.test_acc.reset()
+ self.val_acc.reset()
+
+ def configure_optimizers(self):
+ """Choose what optimizers and learning-rate schedulers.
+
+ Normally you'd need one. But in the case of GANs or similar you might have multiple.
+
+ See examples here:
+ https://pytorch-lightning.readthedocs.io/en/latest/common/lightning_module.html#configure-optimizers
+ """
+ return torch.optim.Adam(
+ params=self.parameters(),
+ lr=self.hparams.lr,
+ weight_decay=self.hparams.weight_decay,
+ )