File size: 8,916 Bytes
40e1762 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 |
import math
from typing import Any, List
import torch
import torch.nn.functional as F
from torch import nn
from pytorch_lightning import LightningModule
from torchmetrics import MaxMetric, MeanAbsoluteError, MinMetric
from torchmetrics.classification.accuracy import Accuracy
import torchvision.models as models
class FocusLiteNN(nn.Module):
"""
https://github.com/icbcbicc/FocusLiteNN
This class is licenced undeer:
# The Prosperity Public License 3.0.0
Contributor: Zhongling Wang, Mahdi S. Hosseini, Adyn Miles
Source Code: https://github.com/icbcbicc/FocusLiteNN
## Purpose:
This license allows you to use and share this software for noncommercial purposes for free and to try this software for commercial purposes for thirty days.
## Agreement
In order to receive this license, you have to agree to its rules. Those rules are both obligations under that agreement and conditions to your license. Don't do anything with this software that triggers a rule you can't or won't follow.
## Notices
Make sure everyone who gets a copy of any part of this software from you, with or without changes, also gets the text of this license and the contributor and source code lines above.
## Commercial Trial
Limit your use of this software for commercial purposes to a thirty-day trial period. If you use this software for work, your company gets one trial period for all personnel, not one trial per person.
## Contributions Back
Developing feedback, changes, or additions that you contribute back to the contributor on the terms of a standardized public software license such as [the Blue Oak Model License 1.0.0](https://blueoakcouncil.org/license/1.0.0), [the Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0.html), [the MIT license](https://spdx.org/licenses/MIT.html), or [the two-clause BSD license](https://spdx.org/licenses/BSD-2-Clause.html) doesn't count as use for a commercial purpose.
## Personal Uses
Personal use for research, experiment, and testing for the benefit of public knowledge, personal study, private entertainment, hobby projects, amateur pursuits, or religious observance, without any anticipated commercial application, doesn't count as use for a commercial purpose.
## Noncommercial Organizations
Use by any charitable organization, educational institution, public research organization, public safety or health organization, environmental protection organization, or government institution doesn't count as use for a commercial purpose regardless of the source of funding or obligations resulting from the funding.
## Defense
Don't make any legal claim against anyone accusing this software, with or without changes, alone or with other technology, of infringing any patent.
## Copyright
The contributor licenses you to do everything with this software that would otherwise infringe their copyright in it.
## Patent
The contributor licenses you to do everything with this software that would otherwise infringe any patents they can license or become able to license.
## Reliability
The contributor can't revoke this license.
## Excuse
You're excused for unknowingly breaking [Notices](#notices) if you take all practical steps to comply within thirty days of learning you broke the rule.
## No Liability
***As far as the law allows, this software comes as is, without any warranty or condition, and the contributor won't be liable to anyone for any damages related to this software or this license, under any kind of legal claim.***
In practice, we found MIN contributes VERY LITTLE to the performance. To achieve
extreme simplicity, different from Equation 1 in the paper, we only use MAX as the
nonlinear function. All experimental results in the paper are reported based on the
model using only MAX.
The model (class FocusLiteNNMinMax) using weighted MAX and MIN as the nonlinear function
(Equation 1 in paper) has indistinguishable (slightly better) performance compared to the
model using only MAX (class FocusLiteNN).
"""
def __init__(self, num_channel=3):
super(FocusLiteNN, self).__init__()
self.num_channel = num_channel
self.conv = nn.Conv2d(3, self.num_channel, 7, stride=5, padding=1) # 47x47
self.maxpool = nn.MaxPool2d(kernel_size=47)
if self.num_channel > 1:
self.fc = nn.Conv2d(self.num_channel, 1, 1, stride=1, padding=0)
for m in self.modules():
if isinstance(m, nn.Conv2d):
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
m.weight.data.normal_(0, math.sqrt(2.0 / n))
def forward(self, x):
batch_size = x.size()[0]
x = self.conv(x)
x = -self.maxpool(-x) # minpooling
if self.num_channel > 1:
x = self.fc(x)
x = x.view(batch_size, -1)
return x
"""
All code below is licenced under the licence of the whole repository
"""
class FocusLiteNNLitModule(LightningModule):
def __init__(
self,
lr: float = 0.001,
num_channel: int = 3,
pre_trained: bool = False,
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)
# loss function
self.criterion = torch.nn.MSELoss()
# use separate metric instance for train, val and test step
# to ensure a proper reduction over the epoch
self.train_mae = MeanAbsoluteError()
self.val_mae = MeanAbsoluteError()
self.test_mae = MeanAbsoluteError()
# for logging best so far validation accuracy
self.val_mae_best = MinMetric()
self.num_channel = num_channel
self.model = FocusLiteNN(num_channel)
self.model.maxpool = nn.AdaptiveMaxPool2d(1)
def forward(self, x):
x = self.model(x)
return x
def step(self, batch: Any):
x = batch["image"]
y = batch["focus_height"]
logits = self.forward(x)
loss = self.criterion(logits, y.unsqueeze(1))
preds = torch.squeeze(logits)
return loss, preds, y
def training_step(self, batch: Any, batch_idx: int):
loss, preds, targets = self.step(batch)
# log train metrics
mae = self.train_mae(preds, targets)
self.log("train/loss", loss, on_step=False, on_epoch=True, prog_bar=False)
self.log("train/mae", mae, 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
mae = self.val_mae(preds, targets)
self.log("val/loss", loss, on_step=False, on_epoch=True, prog_bar=False)
self.log("val/mae", mae, on_step=False, on_epoch=True, prog_bar=True)
return {"loss": loss, "preds": preds, "targets": targets}
def validation_epoch_end(self, outputs: List[Any]):
mae = self.val_mae.compute() # get val accuracy from current epoch
self.val_mae_best.update(mae)
self.log(
"val/mae_best", self.val_mae_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
mae = self.test_mae(preds, targets)
self.log("test/loss", loss, on_step=False, on_epoch=True)
self.log("test/mae", mae, on_step=False, on_epoch=True)
def test_epoch_end(self, outputs: List[Any]):
print(outputs)
pass
def on_epoch_end(self):
# reset metrics at the end of every epoch
self.train_mae.reset()
self.test_mae.reset()
self.val_mae.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,
)
|