Skip to content

Commit

Permalink
Major refactor, small fixes
Browse files Browse the repository at this point in the history
  • Loading branch information
@sthalles
sthalles committed Jan 18, 2021
1 parent f78dd0a commit 6cd188e
Show file tree
Hide file tree
Showing 3 changed files with 22 additions and 77 deletions.
81 changes: 15 additions & 66 deletions README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -16,78 +16,27 @@ $ python run.py

## Config file

Before running SimCLR, make sure you choose the correct running configurations on the ```config.yaml``` file.

```yaml

# A batch size of N, produces 2 * (N-1) negative samples. Original implementation uses a batch size of 8192
batch_size: 512

# Number of epochs to train
epochs: 40

# Frequency to eval the similarity score using the validation set
eval_every_n_epochs: 1

# Specify a folder containing a pre-trained model to fine-tune. If training from scratch, pass None.
fine_tune_from: 'resnet-18_80-epochs'

# Frequency to which tensorboard is updated
log_every_n_steps: 50

# l2 Weight decay magnitude, original implementation uses 10e-6
weight_decay: 10e-6

# if True, training is done using mixed precision. Apex needs to be installed in this case.
fp16_precision: False

# Model related parameters
model:
# Output dimensionality of the embedding vector z. Original implementation uses 2048
out_dim: 256

# The ConvNet base model. Choose one of: "resnet18" or "resnet50". Original implementation uses resnet50
base_model: "resnet18"

# Dataset related parameters
dataset:
s: 1

# dataset input shape. For datasets containing images of different size, this defines the final
input_shape: (96,96,3)

# Number of workers for the data loader
num_workers: 0

# Size of the validation set in percentage
valid_size: 0.05

# NTXent loss related parameters
loss:
# Temperature parameter for the contrastive objective
temperature: 0.5

# Distance metric for contrastive loss. If False, uses dot product. Original implementation uses cosine similarity.
use_cosine_similarity: True
Before running SimCLR, make sure you choose the correct running configurations. You can change the running configurations by passing keyword arguments to the ```run.py``` file.

```python

$ python run.py -data ./datasets --dataset-name stl10 --log-every-n-steps 100 --epochs 100

```

If you want to run it on CPU (for debugging purposes) use the ```--disable-cuda``` option.

## Feature Evaluation

Feature evaluation is done using a linear model protocol.

Features are learned using the ```STL10 train+unsupervised``` set and evaluated in the ```test``` set;
First, we learned features using SimCLR on the ```STL10 unsupervised``` set. Then, we train a linear classifier on top of the frozen features from SimCLR. The linera model is trained on features extracted from the ```STL10 train``` set and evaluated on the ```STL10 test``` set.

Check the [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://github.com/sthalles/SimCLR/blob/master/feature_eval/linear_feature_eval.ipynb) notebook for reproducibility.
Check the [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://github.com/sthalles/SimCLR/blob/simclr-refactor/feature_eval/mini_batch_logistic_regression_evaluator.ipynb) notebook for reproducibility.


| Linear Classifier | Feature Extractor | Architecture | Feature dimensionality | Projection Head dimensionality | Epochs | STL10 Top 1 |
|:---------------------------:|:-----------------:|:------------:|:----------------------:|:-------------------------------:|:------:|:-----------:|
| Logistic Regression | PCA Features | - | 256 | - | | 36.0% |
| KNN | PCA Features | - | 256 | - | | 31.8% |
| Logistic Regression (LBFGS) | SimCLR | [ResNet-18](https://drive.google.com/open?id=1c4eVon0sUd-ChVhH6XMpF6nCngNJsAPk) | 512 | 256 | 40 | 70.3% |
| KNN | SimCLR | ResNet-18 | 512 | 256 | 40 | 66.2% |
| Logistic Regression (LBFGS) | SimCLR | [ResNet-18](https://drive.google.com/open?id=1L0yoeY9i2mzDcj69P4slTWb-cfr3PyoT) | 512 | 256 | 80 | 72.9% |
| KNN | SimCLR | ResNet-18 | 512 | 256 | 80 | 69.8% |
| Logistic Regression (Adam) | SimCLR | [ResNet-18](https://drive.google.com/open?id=1aZ12TITXnajZ6QWmS_SDm8Sp8gXNbeCQ) | 512 | 256 | 100 | 75.4% |
| Logistic Regression (Adam) | SimCLR | [ResNet-50](https://drive.google.com/open?id=1TZqBNTFCsO-mxAiR-zJeyupY-J2gA27Q) | 2048 | 128 | 40 | 74.6% |
| Logistic Regression (Adam) | SimCLR | [ResNet-50](https://drive.google.com/open?id=1is1wkBRccHdhSKQnPUTQoaFkVNSaCb35) | 2048 | 128 | 80 | 77.3% |
| Linear Classification | Dataset | Feature Extractor | Architecture | Feature dimensionality | Projection Head dimensionality | Epochs | Top 1 |
|----------------------------|---------|-------------------|---------------------------------------------------------------------------------|------------------------|--------------------------------|--------|--------|
| Logistic Regression (Adam) | STL10 | SimCLR | [ResNet-18](https://drive.google.com/open?id=14_nH2FkyKbt61cieQDiSbBVNP8-gtwgF) | 512 | 128 | 100 | 70.45 |
| Logistic Regression (Adam) | CIFAR10 | SimCLR | [ResNet-18](https://drive.google.com/open?id=1lc2aoVtrAetGn0PnTkOyFzPCIucOJq7C) | 512 | 128 | 100 | 64.82 |
| Logistic Regression (Adam) | STL10 | SimCLR | [ResNet-50](https://drive.google.com/open?id=1ByTKAUsdm_X7tLcii6oAEl5qFRqRMZSu) | 2048 | 128 | 50 | 67.075 |
4 changes: 1 addition & 3 deletions run.py
View file
Original file line number Diff line number Diff line change
@@ -1,10 +1,10 @@
import argparse
import torch
import torch.backends.cudnn as cudnn
from torchvision import models
from data_aug.contrastive_learning_dataset import ContrastiveLearningDataset
from models.resnet_simclr import ResNetSimCLR
from simclr import SimCLR
import torch.backends.cudnn as cudnn

model_names = sorted(name for name in models.__dict__
if name.islower() and not name.startswith("__")
Expand Down Expand Up @@ -34,8 +34,6 @@
parser.add_argument('--wd', '--weight-decay', default=1e-4, type=float,
metavar='W', help='weight decay (default: 1e-4)',
dest='weight_decay')
parser.add_argument('--resume', default='', type=str, metavar='PATH',
help='path to latest checkpoint (default: none)')
parser.add_argument('--seed', default=None, type=int,
help='seed for initializing training. ')
parser.add_argument('--disable-cuda', action='store_true',
Expand Down
14 changes: 6 additions & 8 deletions simclr.py
View file
Original file line number Diff line number Diff line change
@@ -1,11 +1,12 @@
import logging
import os
import shutil
import sys
import yaml

import torch
from torch.utils.tensorboard import SummaryWriter
import torch.nn.functional as F
import logging
import yaml
from torch.utils.tensorboard import SummaryWriter
from tqdm import tqdm

torch.manual_seed(0)
Expand Down Expand Up @@ -84,11 +85,8 @@ def train(self, train_loader):
self.model, self.optimizer = amp.initialize(self.model, self.optimizer,
opt_level='O2',
keep_batchnorm_fp32=True)

model_checkpoints_folder = os.path.join(self.writer.log_dir, 'checkpoints')

# save config file
_save_config_file(model_checkpoints_folder, self.args)
_save_config_file(self.writer.log_dir, self.args)

n_iter = 0
logging.info(f"Start SimCLR training for {self.args.epochs} epochs.")
Expand All @@ -114,7 +112,7 @@ def train(self, train_loader):
self.optimizer.step()

if n_iter % self.args.log_every_n_steps == 0:
top1, top5 = accuracy(logits, labels, topk=(1,5))
top1, top5 = accuracy(logits, labels, topk=(1, 5))
self.writer.add_scalar('loss', loss, global_step=n_iter)
self.writer.add_scalar('acc/top1', top1[0], global_step=n_iter)
self.writer.add_scalar('acc/top5', top5[0], global_step=n_iter)
Expand Down

0 comments on commit 6cd188e

Please sign in to comment.