Skip to content

Optimized vis classification to give ~82% Accuracy #315

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 3 commits into
base: main
Choose a base branch
from
Draft

Optimized vis classification to give ~82% Accuracy #315

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1a0152d
Optimized vis classification to give ~82% Accuracy
theory-in-progress Sep 5, 2023
8e726ad
Merge branch 'pytorch-ignite:main' into improve-vis-accuracy
theory-in-progress Sep 5, 2023
1ede4d6
Updated trainers.py
theory-in-progress Sep 5, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 6 additions & 3 deletions src/templates/template-vision-classification/trainers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
import ignite.distributed as idist
import torch
from ignite.engine import DeterministicEngine, Engine, Events
from torch.cuda.amp import autocast
from torch.cuda.amp import autocast, GradScaler
from torch.nn import Module
from torch.optim import Optimizer
from torch.utils.data import DistributedSampler, Sampler
Expand All @@ -27,9 +27,10 @@ def train_function(engine: Union[Engine, DeterministicEngine], batch: Any):
outputs = model(samples)
loss = loss_fn(outputs, targets)

loss.backward()
optimizer.step()
optimizer.zero_grad()
scaler.scale(loss).backward()
scaler.step(optimizer)
scaler.update()

train_loss = loss.item()
engine.state.metrics = {
Expand All @@ -45,6 +46,8 @@ def train_function(engine: Union[Engine, DeterministicEngine], batch: Any):

trainer = Engine(train_function)
#::: } :::#

scaler = GradScaler(enabled=config.use_amp)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Let's define the scaler before train_function for clarity


# set epoch for distributed sampler
@trainer.on(Events.EPOCH_STARTED)
Expand Down