Spaces:
Sleeping
Sleeping
File size: 4,943 Bytes
4db4d66 |
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 |
import torch
import torch.nn as nn
import lightning as L
from torchmetrics import Accuracy
from typing import Any
from utils.common import one_cycle_lr
class ResidualBlock(L.LightningModule):
def __init__(self, channels):
super(ResidualBlock, self).__init__()
self.residual_block = nn.Sequential(
nn.Conv2d(
in_channels=channels,
out_channels=channels,
kernel_size=3,
stride=1,
padding=1,
bias=False,
),
nn.BatchNorm2d(channels),
nn.ReLU(),
nn.Conv2d(
in_channels=channels,
out_channels=channels,
kernel_size=3,
stride=1,
padding=1,
bias=False,
),
nn.BatchNorm2d(channels),
nn.ReLU(),
)
def forward(self, x):
return x + self.residual_block(x)
class ResNet(L.LightningModule):
def __init__(
self, batch_size=512, shuffle=True, num_workers=4, learning_rate=0.003, scheduler_steps=None, maxlr=None, epochs=None
):
super(ResNet, self).__init__()
self.data_dir = "./data"
self.batch_size = batch_size
self.shuffle = shuffle
self.num_workers = num_workers
self.learning_rate = learning_rate
self.scheduler_steps = scheduler_steps
self.maxlr = maxlr if maxlr is not None else learning_rate
self.epochs = epochs
self.prep = nn.Sequential(
nn.Conv2d(
in_channels=3,
out_channels=64,
kernel_size=3,
stride=1,
padding=1,
bias=False,
),
nn.BatchNorm2d(64),
nn.ReLU(),
)
self.layer1 = nn.Sequential(
nn.Conv2d(
in_channels=64,
out_channels=128,
kernel_size=3,
padding=1,
stride=1,
bias=False,
),
nn.MaxPool2d(kernel_size=2),
nn.BatchNorm2d(128),
nn.ReLU(),
ResidualBlock(channels=128),
)
self.layer2 = nn.Sequential(
nn.Conv2d(
in_channels=128,
out_channels=256,
kernel_size=3,
padding=1,
stride=1,
bias=False,
),
nn.MaxPool2d(kernel_size=2),
nn.BatchNorm2d(256),
nn.ReLU(),
)
self.layer3 = nn.Sequential(
nn.Conv2d(
in_channels=256,
out_channels=512,
kernel_size=3,
padding=1,
stride=1,
bias=False,
),
nn.MaxPool2d(kernel_size=2),
nn.BatchNorm2d(512),
nn.ReLU(),
ResidualBlock(channels=512),
)
self.pool = nn.MaxPool2d(kernel_size=4)
self.fc = nn.Linear(in_features=512, out_features=10, bias=False)
self.softmax = nn.Softmax(dim=-1)
self.accuracy = Accuracy(task="multiclass", num_classes=10)
def forward(self, x):
x = self.prep(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.pool(x)
x = x.view(-1, 512)
x = self.fc(x)
# x = self.softmax(x)
return x
def configure_optimizers(self) -> Any:
optimizer = torch.optim.Adam(
self.parameters(), lr=self.learning_rate, weight_decay=1e-4
)
scheduler = one_cycle_lr(
optimizer=optimizer, maxlr=self.maxlr, steps=self.scheduler_steps, epochs=self.epochs
)
return {"optimizer": optimizer,
"lr_scheduler": {"scheduler": scheduler,
"interval": "step"}}
def training_step(self, batch, batch_idx):
X, y = batch
y_pred = self(X)
loss = nn.CrossEntropyLoss()(y_pred, y)
preds = torch.argmax(y_pred, dim=1)
accuracy = self.accuracy(preds, y)
self.log_dict({"train_loss": loss, "train_acc": accuracy}, prog_bar=True)
return loss
def validation_step(self, batch, batch_idx):
X, y = batch
y_pred = self(X)
loss = nn.CrossEntropyLoss(reduction="sum")(y_pred, y)
preds = torch.argmax(y_pred, dim=1)
accuracy = self.accuracy(preds, y)
self.log_dict({"val_loss": loss, "val_acc": accuracy}, prog_bar=True)
return loss
def test_step(self, batch, batch_idx):
X, y = batch
y_pred = self(X)
loss = nn.CrossEntropyLoss(reduction="sum")(y_pred, y)
preds = torch.argmax(y_pred, dim=1)
accuracy = self.accuracy(preds, y)
self.log_dict({"test_loss": loss, "test_acc": accuracy}, prog_bar=True) |