Full Code of bkong999/COVNet for AI

master 932c1cf7e4a0 cached
11 files
35.1 KB
8.2k tokens
19 symbols
1 requests
Download .txt
Repository: bkong999/COVNet
Branch: master
Commit: 932c1cf7e4a0
Files: 11
Total size: 35.1 KB

Directory structure:
gitextract_17ft28df/

├── .gitignore
├── LICENSE
├── README.md
├── config.py
├── data/
│   ├── train.csv
│   └── val.csv
├── dataset.py
├── main.py
├── model.py
├── test.py
└── utils.py

================================================
FILE CONTENTS
================================================

================================================
FILE: .gitignore
================================================
#cmake related files
CMakeCache.txt
CMakeFiles
CMakeScripts
Makefile
cmake_install.cmake
install_manifest.txt
CTestTestfile.cmake
#ignore all bin dirs
bin/
.DS_Store
*.vtp
*.pathlinesinfo
*.pyc
*.pyo
*~
*.bak
*.swp
*.o
*.nii.gz
*.mha
*.raw
*.mhd
*.a
*.orig # git merge conflict file
# model file
*.pth
*.p

### following copied from https://gist.github.com/octocat/9257657
# Compiled source #
###################
*.com
*.class
*.dll
*.exe
*.o
*.so

# Packages #
############
# it's better to unpack these files and commit the raw source
# git has its own built in compression methods
*.7z
*.dmg
*.gz
*.iso
*.jar
*.rar
*.tar
*.zip

# Logs and databases #
######################
*.log
*.sql
*.sqlite

# OS generated files #
######################
.DS_Store
.DS_Store?
._*
.Spotlight-V100
.Trashes
ehthumbs.db
Thumbs.db

# Ignore data and experiments dirs, but keep folder organizations#
######################
experiments


================================================
FILE: LICENSE
================================================
“Commons Clause” License Condition v1.0

The Software is provided to you by the Licensor under the
License, as defined below, subject to the following condition.

Without limiting other conditions in the License, the grant
of rights under the License will not include, and the License
does not grant to you, the right to Sell the Software.

For purposes of the foregoing, “Sell” means practicing any or
all of the rights granted to you under the License to provide
to third parties, for a fee or other consideration (including
without limitation fees for hosting or consulting/ support
services related to the Software), a product or service whose
value derives, entirely or substantially, from the functionality
of the Software. Any license notice or attribution required by
the License must also include this Commons Clause License
Condition notice.

Software: COVNet

License: Apache 2.0

Licensor: CuraCloud Corporation


---------------------------------------------------------------------


                                 Apache License
                           Version 2.0, January 2004
                        http://www.apache.org/licenses/

   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION

   1. Definitions.

      "License" shall mean the terms and conditions for use, reproduction,
      and distribution as defined by Sections 1 through 9 of this document.

      "Licensor" shall mean the copyright owner or entity authorized by
      the copyright owner that is granting the License.

      "Legal Entity" shall mean the union of the acting entity and all
      other entities that control, are controlled by, or are under common
      control with that entity. For the purposes of this definition,
      "control" means (i) the power, direct or indirect, to cause the
      direction or management of such entity, whether by contract or
      otherwise, or (ii) ownership of fifty percent (50%) or more of the
      outstanding shares, or (iii) beneficial ownership of such entity.

      "You" (or "Your") shall mean an individual or Legal Entity
      exercising permissions granted by this License.

      "Source" form shall mean the preferred form for making modifications,
      including but not limited to software source code, documentation
      source, and configuration files.

      "Object" form shall mean any form resulting from mechanical
      transformation or translation of a Source form, including but
      not limited to compiled object code, generated documentation,
      and conversions to other media types.

      "Work" shall mean the work of authorship, whether in Source or
      Object form, made available under the License, as indicated by a
      copyright notice that is included in or attached to the work
      (an example is provided in the Appendix below).

      "Derivative Works" shall mean any work, whether in Source or Object
      form, that is based on (or derived from) the Work and for which the
      editorial revisions, annotations, elaborations, or other modifications
      represent, as a whole, an original work of authorship. For the purposes
      of this License, Derivative Works shall not include works that remain
      separable from, or merely link (or bind by name) to the interfaces of,
      the Work and Derivative Works thereof.

      "Contribution" shall mean any work of authorship, including
      the original version of the Work and any modifications or additions
      to that Work or Derivative Works thereof, that is intentionally
      submitted to Licensor for inclusion in the Work by the copyright owner
      or by an individual or Legal Entity authorized to submit on behalf of
      the copyright owner. For the purposes of this definition, "submitted"
      means any form of electronic, verbal, or written communication sent
      to the Licensor or its representatives, including but not limited to
      communication on electronic mailing lists, source code control systems,
      and issue tracking systems that are managed by, or on behalf of, the
      Licensor for the purpose of discussing and improving the Work, but
      excluding communication that is conspicuously marked or otherwise
      designated in writing by the copyright owner as "Not a Contribution."

      "Contributor" shall mean Licensor and any individual or Legal Entity
      on behalf of whom a Contribution has been received by Licensor and
      subsequently incorporated within the Work.

   2. Grant of Copyright License. Subject to the terms and conditions of
      this License, each Contributor hereby grants to You a perpetual,
      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
      copyright license to reproduce, prepare Derivative Works of,
      publicly display, publicly perform, sublicense, and distribute the
      Work and such Derivative Works in Source or Object form.

   3. Grant of Patent License. Subject to the terms and conditions of
      this License, each Contributor hereby grants to You a perpetual,
      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
      (except as stated in this section) patent license to make, have made,
      use, offer to sell, sell, import, and otherwise transfer the Work,
      where such license applies only to those patent claims licensable
      by such Contributor that are necessarily infringed by their
      Contribution(s) alone or by combination of their Contribution(s)
      with the Work to which such Contribution(s) was submitted. If You
      institute patent litigation against any entity (including a
      cross-claim or counterclaim in a lawsuit) alleging that the Work
      or a Contribution incorporated within the Work constitutes direct
      or contributory patent infringement, then any patent licenses
      granted to You under this License for that Work shall terminate
      as of the date such litigation is filed.

   4. Redistribution. You may reproduce and distribute copies of the
      Work or Derivative Works thereof in any medium, with or without
      modifications, and in Source or Object form, provided that You
      meet the following conditions:

      (a) You must give any other recipients of the Work or
          Derivative Works a copy of this License; and

      (b) You must cause any modified files to carry prominent notices
          stating that You changed the files; and

      (c) You must retain, in the Source form of any Derivative Works
          that You distribute, all copyright, patent, trademark, and
          attribution notices from the Source form of the Work,
          excluding those notices that do not pertain to any part of
          the Derivative Works; and

      (d) If the Work includes a "NOTICE" text file as part of its
          distribution, then any Derivative Works that You distribute must
          include a readable copy of the attribution notices contained
          within such NOTICE file, excluding those notices that do not
          pertain to any part of the Derivative Works, in at least one
          of the following places: within a NOTICE text file distributed
          as part of the Derivative Works; within the Source form or
          documentation, if provided along with the Derivative Works; or,
          within a display generated by the Derivative Works, if and
          wherever such third-party notices normally appear. The contents
          of the NOTICE file are for informational purposes only and
          do not modify the License. You may add Your own attribution
          notices within Derivative Works that You distribute, alongside
          or as an addendum to the NOTICE text from the Work, provided
          that such additional attribution notices cannot be construed
          as modifying the License.

      You may add Your own copyright statement to Your modifications and
      may provide additional or different license terms and conditions
      for use, reproduction, or distribution of Your modifications, or
      for any such Derivative Works as a whole, provided Your use,
      reproduction, and distribution of the Work otherwise complies with
      the conditions stated in this License.

   5. Submission of Contributions. Unless You explicitly state otherwise,
      any Contribution intentionally submitted for inclusion in the Work
      by You to the Licensor shall be under the terms and conditions of
      this License, without any additional terms or conditions.
      Notwithstanding the above, nothing herein shall supersede or modify
      the terms of any separate license agreement you may have executed
      with Licensor regarding such Contributions.

   6. Trademarks. This License does not grant permission to use the trade
      names, trademarks, service marks, or product names of the Licensor,
      except as required for reasonable and customary use in describing the
      origin of the Work and reproducing the content of the NOTICE file.

   7. Disclaimer of Warranty. Unless required by applicable law or
      agreed to in writing, Licensor provides the Work (and each
      Contributor provides its Contributions) on an "AS IS" BASIS,
      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
      implied, including, without limitation, any warranties or conditions
      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
      PARTICULAR PURPOSE. You are solely responsible for determining the
      appropriateness of using or redistributing the Work and assume any
      risks associated with Your exercise of permissions under this License.

   8. Limitation of Liability. In no event and under no legal theory,
      whether in tort (including negligence), contract, or otherwise,
      unless required by applicable law (such as deliberate and grossly
      negligent acts) or agreed to in writing, shall any Contributor be
      liable to You for damages, including any direct, indirect, special,
      incidental, or consequential damages of any character arising as a
      result of this License or out of the use or inability to use the
      Work (including but not limited to damages for loss of goodwill,
      work stoppage, computer failure or malfunction, or any and all
      other commercial damages or losses), even if such Contributor
      has been advised of the possibility of such damages.

   9. Accepting Warranty or Additional Liability. While redistributing
      the Work or Derivative Works thereof, You may choose to offer,
      and charge a fee for, acceptance of support, warranty, indemnity,
      or other liability obligations and/or rights consistent with this
      License. However, in accepting such obligations, You may act only
      on Your own behalf and on Your sole responsibility, not on behalf
      of any other Contributor, and only if You agree to indemnify,
      defend, and hold each Contributor harmless for any liability
      incurred by, or claims asserted against, such Contributor by reason
      of your accepting any such warranty or additional liability.

   END OF TERMS AND CONDITIONS

   APPENDIX: How to apply the Apache License to your work.

      To apply the Apache License to your work, attach the following
      boilerplate notice, with the fields enclosed by brackets "[]"
      replaced with your own identifying information. (Don't include
      the brackets!)  The text should be enclosed in the appropriate
      comment syntax for the file format. We also recommend that a
      file or class name and description of purpose be included on the
      same "printed page" as the copyright notice for easier
      identification within third-party archives.

   Copyright [yyyy] [name of copyright owner]

   Licensed under the Apache License, Version 2.0 (the "License");
   you may not use this file except in compliance with the License.
   You may obtain a copy of the License at

       http://www.apache.org/licenses/LICENSE-2.0

   Unless required by applicable law or agreed to in writing, software
   distributed under the License is distributed on an "AS IS" BASIS,
   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
   See the License for the specific language governing permissions and
   limitations under the License.



================================================
FILE: README.md
================================================
# COVID-19 Detection Neural Network (COVNet)
This is a PyTorch implementation of the paper "[Artificial Intelligence Distinguishes COVID-19 from Community Acquired Pneumonia on Chest CT](https://pubs.rsna.org/doi/10.1148/radiol.2020200905)". It supports training, validation and testing for COVNet.

<img src="assets/overview.png" width="600">

### Updates & Notices
- 2020-03-30: Thanks for the interest in our work. Unfortunately, we do not own the data, and we have to get permission from our collaborators before we share the data and model. We will update later.

## Citation
If you find this code is useful for your research, please consider citing:
```
@article{li2020artificial,
  title={Artificial Intelligence Distinguishes COVID-19 from Community Acquired Pneumonia on Chest CT},
  author={Li, Lin and Qin, Lixin and Xu, Zeguo and Yin, Youbing and Wang, Xin and Kong, Bin and Bai, Junjie and Lu, Yi and Fang, Zhenghan and Song, Qi and Cao, Kunlin and others},
  journal={Radiology},
  year={2020}
}
```

## Setup
### Prerequisites
- Anaconda 3.7
- PyTorch 1.4
- SimpleITK
- batchgenerators
- tensorboardX

### Prepare data
Preprocess the data according to the [Appendix E1 section](https://pubs.rsna.org/doi/suppl/10.1148/radiol.2020200905/suppl_file/ry_200905_supp_in%20press.pdf) of the paper and organize them as the following. A example of train.csv and val.csv are also provided.
```
data
├── caseid1
|   ├── masked_ct.nii
|   └── mask.nii.gz
├── caseid2
|   ├── masked_ct.nii
|   └── mask.nii.gz
├── caseid3
|   ├── masked_ct.nii
|   └── mask.nii.gz
├── caseid4
|   ├── masked_ct.nii
|   └── mask.nii.gz
├── train.csv
└── val.csv
```

## COVNet
<img src="assets/demo.png" width="600">

### Training
Training a COVNet with default arguments. Model checkpoints and tensorboard logs are written out to a unique directory created by default within `experiments/models` and `experiments/logs` respectively after starting training.
```
python main.py
```

### Validation and Testing
You can run validation and testing on the checkpointed best model by:
```
python test.py
```


================================================
FILE: config.py
================================================
import argparse


def parse_arguments():
    """Argument Parser for the commandline argments
    :returns: command line arguments

    """
    ##########################################################################
    #                            Training setting                            #
    ##########################################################################
    parser = argparse.ArgumentParser()
    parser.add_argument('--n_classes', help="Number of classes", type=int,
                        default=3)
    parser.add_argument('--lr', type=float, default=1e-5)
    parser.add_argument('--epochs', type=int, default=50)
    parser.add_argument('--lr_scheduler', type=str,
                        default='plateau', choices=['plateau', 'step'])
    parser.add_argument('--gamma', type=float,
                        help='LR Multiplicative factor if lr_scheduler is step',
                        default=0.1)
    parser.add_argument('--patience', type=int, default=9)
    parser.add_argument('--log-every', type=int, default=100)
    parser.add_argument('--save-model', type=bool, default=True)
    args = parser.parse_args()

    return args


================================================
FILE: data/train.csv
================================================
case,label
caseid1,0
caseid2,1
caseid3,2


================================================
FILE: data/val.csv
================================================
case,label
caseid4,0


================================================
FILE: dataset.py
================================================
import os
import pandas as pd
import numpy as np

import torch
import torch.utils.data as data
import SimpleITK as sitk
from batchgenerators.transforms import noise_transforms
from batchgenerators.transforms import spatial_transforms


class NCovDataset(data.Dataset):
    def __init__(self, root_dir, stage='train'):
        super().__init__()
        self.root_dir = root_dir
        self.stage = stage
        assert stage in ['train', 'val', 'test']

        if stage == 'train':
            split_file = 'train.csv'
        elif stage == 'val':
            split_file = 'val.csv'
        elif stage == 'test':
            # We just assume validation set is the same as test set
            split_file = 'val.csv'

        df = pd.read_csv(os.path.join(root_dir, split_file),
                              converters={'case': str, 'label': int})
        df = df.set_index('case')
        self.case_ids = list(df.index)
        self.labels = df['label'].values.tolist()

    def __len__(self):
        return len(self.case_ids)

    def __getitem__(self, index):
        fn = os.path.join(self.root_dir, self.case_ids[index], 'masked_ct.nii')
        image = sitk.ReadImage(fn)
        array = sitk.GetArrayFromImage(image)

        mask_fn = os.path.join(self.root_dir, self.case_ids[index],
                               'mask.nii.gz')
        mask_image = sitk.ReadImage(mask_fn)
        mask = sitk.GetArrayFromImage(mask_image)

        array, mask = array[None, ...], mask[None, ...]
        if self.stage == 'train':
            # Default randomly mirroring the second and third axes
            array, mask = spatial_transforms.augment_mirroring(
                array, sample_seg=mask, axes=(1, 2))
        array, mask = array[0], mask[0]

        ######################################################
        #  Preprocessing for both train and validation data  #
        ######################################################
        min_value, max_value = -1250, 250
        np.clip(array, min_value, max_value, out=array)
        array = (array - min_value) / (max_value - min_value)

        # data should be a numpy array with shape [x, y, z] or [c, x, y, z]
        # seg should be a numpy array with shape [x, y, z]
        full_channel = np.stack([array, array, array])

        if self.stage == 'train':
            full_channel, mask = self.do_augmentation(full_channel, mask)
        else:
            mask = mask[None, ...]

        # remove the noise in the non-lung regions
        mask = mask[0]
        full_channel[0][mask == 0] = 0
        full_channel[1][mask == 0] = 0
        full_channel[2][mask == 0] = 0
        label = self.labels[index]
        full_channel = torch.FloatTensor(full_channel).permute((1, 0, 2, 3))

        return full_channel, label, self.case_ids[index]

    def do_augmentation(self, array, mask):
        """Augmentation for the training data.

        :array: A numpy array of size [c, x, y, z]
        :returns: augmented image and the corresponding mask

        """
        # normalize image to range [0, 1], then apply this transform
        patch_size = np.asarray(array.shape)[1:]
        augmented = noise_transforms.augment_gaussian_noise(
            array, noise_variance=(0, .015))

        # need to become [bs, c, x, y, z] before augment_spatial
        augmented = augmented[None, ...]
        mask = mask[None, None, ...]
        r_range = (0, (3 / 360.) * 2 * np.pi)
        cval = 0.

        augmented, mask = spatial_transforms.augment_spatial(
            augmented, seg=mask, patch_size=patch_size,
            do_elastic_deform=True, alpha=(0., 100.), sigma=(8., 13.),
            do_rotation=True, angle_x=r_range, angle_y=r_range, angle_z=r_range,
            do_scale=True, scale=(.9, 1.1),
            border_mode_data='constant', border_cval_data=cval,
            order_data=3,
            p_el_per_sample=0.5,
            p_scale_per_sample=.5,
            p_rot_per_sample=.5,
            random_crop=False
        )
        mask = mask[0]
        return augmented[0], mask

    def make_weights_for_balanced_classes(self):
        """Making sampling weights for the data samples
        :returns: sampling weigghts for dealing with class imbalance problem

        """
        n_samples = len(self.labels)
        unique, cnts = np.unique(self.labels, return_counts=True)
        cnt_dict = dict(zip(unique, cnts))

        weights = []
        for label in self.labels:
            weights.append(n_samples / float(cnt_dict[label]))
        return weights


================================================
FILE: main.py
================================================
import os
import numpy as np
import time

from tensorboardX import SummaryWriter
import torch
import torch.optim as optim
import torch.nn as nn
import torch.nn.functional as F

import dataset
import model
import config
import utils


def get_lr(optimizer):
    for param_group in optimizer.param_groups:
        return param_group['lr']


def train_model(model, train_loader, epoch, num_epochs, optimizer, writer,
                current_lr, log_every=100):
    n_classes = model.n_classes
    metric = torch.nn.CrossEntropyLoss()

    y_probs = np.zeros((0, n_classes), np.float)
    losses, y_trues = [], []
    model.train()

    for m in model.modules():
        if isinstance(m, nn.BatchNorm2d):
            m.train()
            m.weight.requires_grad = False
            m.bias.requires_grad = False

    for i, (image, label, case_id) in enumerate(train_loader):
        optimizer.zero_grad()
        if torch.cuda.is_available():
            image = image.cuda()
            label = label.cuda()

        prediction = model.forward(image.float())
        loss = metric(prediction, label.long())
        loss.backward()
        optimizer.step()

        loss_value = loss.item()
        losses.append(loss_value)
        y_prob = F.softmax(prediction, dim=1)
        y_probs = np.concatenate([y_probs, y_prob.detach().cpu().numpy()])
        y_trues.append(label.item())

        metric_collects = utils.calc_multi_cls_measures(y_probs, y_trues)
        n_iter = epoch * len(train_loader) + i
        writer.add_scalar('Train/Loss', loss_value, n_iter)

        if (i % log_every == 0) & (i > 0):
            utils.print_progress(epoch + 1, num_epochs, i, len(train_loader),
                                 np.mean(losses), current_lr, metric_collects)

    train_loss_epoch = np.round(np.mean(losses), 4)
    return train_loss_epoch, metric_collects


def evaluate_model(model, val_loader, epoch, num_epochs, writer, current_lr,
                   log_every=20):
    n_classes = model.n_classes
    metric = torch.nn.CrossEntropyLoss()

    model.eval()
    for m in model.modules():
        if isinstance(m, nn.BatchNorm2d):
            m.train()
            m.weight.requires_grad = False
            m.bias.requires_grad = False

    y_probs = np.zeros((0, n_classes), np.float)
    losses, y_trues = [], []

    for i, (image, label, case_id) in enumerate(val_loader):

        if torch.cuda.is_available():
            image = image.cuda()
            label = label.cuda()

        prediction = model.forward(image.float())
        loss = metric(prediction, label.long())

        loss_value = loss.item()
        losses.append(loss_value)
        y_prob = F.softmax(prediction, dim=1)
        y_probs = np.concatenate([y_probs, y_prob.detach().cpu().numpy()])
        y_trues.append(label.item())

        metric_collects = utils.calc_multi_cls_measures(y_probs, y_trues)

        n_iter = epoch * len(val_loader) + i
        writer.add_scalar('Val/Loss', loss_value, n_iter)

        if (i % log_every == 0) & (i > 0):
            prefix = '*Val|'
            utils.print_progress(epoch + 1, num_epochs, i, len(val_loader),
                                 np.mean(losses), current_lr, metric_collects,
                                 prefix=prefix)

    val_loss_epoch = np.round(np.mean(losses), 4)
    return val_loss_epoch, metric_collects


def main(args):
    """Main function for the training pipeline

    :args: commandlien arguments
    :returns: None

    """
    ##########################################################################
    #                             Basic settings                             #
    ##########################################################################
    exp_dir = 'experiments'
    log_dir = os.path.join(exp_dir, 'logs')
    model_dir = os.path.join(exp_dir, 'models')
    os.makedirs(model_dir, exist_ok=True)

    ##########################################################################
    #  Define all the necessary variables for model training and evaluation  #
    ##########################################################################
    writer = SummaryWriter(log_dir)
    train_dataset = dataset.NCovDataset('data/', stage='train')
    weights = train_dataset.make_weights_for_balanced_classes()
    weights = torch.DoubleTensor(weights)
    sampler = torch.utils.data.sampler.WeightedRandomSampler(
        weights, len(train_dataset.case_ids))

    train_loader = torch.utils.data.DataLoader(
        train_dataset, batch_size=1, num_workers=20,
        drop_last=False, sampler=sampler)

    val_dataset = dataset.NCovDataset('data/', stage='val')
    val_loader = torch.utils.data.DataLoader(
        val_dataset, batch_size=1, shuffle=False, num_workers=11,
        drop_last=False)

    cov_net = model.COVNet(n_classes=args.n_classes)
    if torch.cuda.is_available():
        cov_net = cov_net.cuda()
    optimizer = optim.Adam(cov_net.parameters(), lr=args.lr, weight_decay=0.1)

    if args.lr_scheduler == "plateau":
        scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(
            optimizer, patience=3, factor=.3, threshold=1e-4, verbose=True)
    elif args.lr_scheduler == "step":
        scheduler = torch.optim.lr_scheduler.StepLR(
            optimizer, step_size=3, gamma=args.gamma)

    best_val_loss = float('inf')
    best_val_accu = float(0)

    iteration_change_loss = 0
    t_start_training = time.time()
    ##########################################################################
    #                           Main training loop                           #
    ##########################################################################
    for epoch in range(args.epochs):
        current_lr = get_lr(optimizer)
        t_start = time.time()

        ############################################################
        #  The actual training and validation step for each epoch  #
        ############################################################
        train_loss, train_metric = train_model(
            cov_net, train_loader, epoch, args.epochs, optimizer, writer,
            current_lr, args.log_every)

        with torch.no_grad():
            val_loss, val_metric = evaluate_model(
                cov_net, val_loader, epoch, args.epochs, writer, current_lr)

        ##############################
        #  Adjust the learning rate  #
        ##############################
        if args.lr_scheduler == 'plateau':
            scheduler.step(val_loss)
        elif args.lr_scheduler == 'step':
            scheduler.step()

        t_end = time.time()
        delta = t_end - t_start

        utils.print_epoch_progress(train_loss, val_loss, delta, train_metric,
                                   val_metric)
        iteration_change_loss += 1
        print('-' * 30)

        train_acc, val_acc = train_metric['accuracy'], val_metric['accuracy']
        file_name = ('train_acc_{}_val_acc_{}_epoch_{}.pth'.
                     format(train_acc, val_acc, epoch))
        torch.save(cov_net, os.path.join(model_dir, file_name))

        if val_acc > best_val_accu:
            best_val_accu = val_acc
            if bool(args.save_model):
                torch.save(cov_net, os.path.join(model_dir, 'best.pth'))

        if val_loss < best_val_loss:
            best_val_loss = val_loss
            iteration_change_loss = 0

        if iteration_change_loss == args.patience:
            print(('Early stopping after {0} iterations without the decrease ' +
                  'of the val loss').format(iteration_change_loss))
            break
    t_end_training = time.time()
    print('training took {}s'.
          format(t_end_training - t_start_training))


if __name__ == "__main__":
    args = config.parse_arguments()
    main(args)


================================================
FILE: model.py
================================================
import torch
import torch.nn as nn
from torchvision import models


class COVNet(nn.Module):
    def __init__(self, n_classes):
        super().__init__()
        model = models.resnet50(pretrained=True)
        layer_list = list(model.children())[:-2]
        self.pretrained_model = nn.Sequential(*layer_list)

        self.pooling_layer = nn.AdaptiveAvgPool2d(1)
        self.classifer = nn.Linear(2048, n_classes)
        self.n_classes = n_classes

    def forward(self, x):
        x = torch.squeeze(x, dim=0)
        features = self.pretrained_model(x)
        pooled_features = self.pooling_layer(features)
        pooled_features = pooled_features.view(pooled_features.size(0), -1)
        flattened_features = torch.max(pooled_features, 0, keepdim=True)[0]
        output = self.classifer(flattened_features)
        return output


================================================
FILE: test.py
================================================
import os
from tqdm import tqdm
import numpy as np

import torch.nn as nn
import torch.nn.functional as F
import torch

import model
import config
import dataset
import utils


def evaluate_model(model, val_loader):
    metric = torch.nn.CrossEntropyLoss()
    model.eval()

    for m in model.modules():
        if isinstance(m, nn.BatchNorm2d):
            m.train()
            m.weight.requires_grad = False
            m.bias.requires_grad = False

    y_probs = np.zeros((0, 3), np.float)
    losses, y_trues = [], []

    for i, (image, label, case_id) in enumerate(tqdm(val_loader)):
        if torch.cuda.is_available():
            image = image.cuda()
            label = label.cuda()

        prediction = model.forward(image.float())
        loss = metric(prediction, label.long())

        loss_value = loss.item()
        losses.append(loss_value)
        y_prob = F.softmax(prediction, dim=1).detach().cpu().numpy()

        y_probs = np.concatenate([y_probs, y_prob])
        y_trues.append(label.item())
    metric_collects = utils.calc_multi_cls_measures(y_probs, y_trues)
    val_loss_epoch = np.mean(losses)
    return val_loss_epoch, metric_collects


def main(args):
    """Main function for the testing pipeline

    :args: commandline arguments
    :returns: None

    """
    ##########################################################################
    #                             Basic settings                             #
    ##########################################################################
    exp_dir = 'experiments'
    model_dir = os.path.join(exp_dir, 'models')
    model_file = os.path.join(model_dir, 'best.pth')
    val_dataset = dataset.NCovDataset('data/', stage='val')
    val_loader = torch.utils.data.DataLoader(
        val_dataset, batch_size=1, shuffle=False, num_workers=11,
        drop_last=False)

    cov_net = model.COVNet(n_classes=args.n_classes)
    if torch.cuda.is_available():
        cov_net.cuda()

    state = torch.load(model_file)
    cov_net.load_state_dict(state.state_dict())

    with torch.no_grad():
        val_loss, metric_collects = evaluate_model(cov_net, val_loader)
    prefix = '******Evaluate******'
    utils.print_progress(mean_loss=val_loss, metric_collects=metric_collects,
                         prefix=prefix)


if __name__ == "__main__":
    args = config.parse_arguments()
    main(args)


================================================
FILE: utils.py
================================================
import numpy as np
import pandas as pd
from sklearn.metrics import accuracy_score, precision_score, recall_score


def calc_multi_cls_measures(probs, label):
    """Calculate multi-class classification measures (Accuracy, precision,
    Recall, AUC.

    :probs: NxC numpy array storing probabilities for each case
    :label: ground truth label
    :returns: a dictionary of accuracy, precision and recall

    """
    n_classes = probs.shape[1]
    preds = np.argmax(probs, axis=1)
    accuracy = accuracy_score(label, preds)
    precisions = precision_score(label, preds, average=None,
                                 labels=range(n_classes), zero_division=0.)
    recalls = recall_score(label, preds, average=None, labels=range(n_classes),
                           zero_division=0.)

    metric_collects = {'accuracy': accuracy, 'precisions': precisions,
                       'recalls': recalls}
    return metric_collects


def print_progress(epoch=None, n_epoch=None, n_iter=None, iters_one_batch=None,
                   mean_loss=None, cur_lr=None, metric_collects=None,
                   prefix=None):
    """Print the training progress.

    :epoch: epoch number
    :n_epoch: total number of epochs
    :n_iter: current iteration number
    :mean_loss: mean loss of current batch
    :iters_one_batch: number of iterations per batch
    :cur_lr: current learning rate
    :metric_collects: dictionary returned by function calc_multi_cls_measures
    :returns: None

    """
    accuracy = metric_collects['accuracy']
    precisions = metric_collects['precisions']
    recalls = metric_collects['recalls']

    n_classes = len(precisions)

    log_str = ''
    if epoch is not None:
        log_str += 'Ep: {0}/{1}|'.format(epoch, n_epoch)

    if n_iter is not None:
        log_str += 'It: {0}/{1}|'.format(n_iter, iters_one_batch)

    if mean_loss is not None:
        log_str += 'Loss: {0:.4f}|'.format(mean_loss)

    log_str += 'Acc: {:.4f}|'.format(accuracy)
    templ = 'Pr: ' + ', '.join(['{:.4f}'] * (n_classes-1)) + '|'
    log_str += templ.format(*(precisions[1:].tolist()))
    templ = 'Re: ' + ', '.join(['{:.4f}'] * (n_classes-1)) + '|'
    log_str += templ.format(*(recalls[1:].tolist()))

    if cur_lr is not None:
        log_str += 'lr: {0}'.format(cur_lr)
    log_str = log_str if prefix is None else prefix + log_str
    print(log_str)


def print_epoch_progress(train_loss, val_loss, time_duration, train_metric,
                         val_metric):
    """Print all the information after each epoch.

    :train_loss: average training loss
    :val_loss: average validation loss
    :time_duration: time duration for current epoch
    :train_metric_collects: a performance dictionary for training
    :val_metric_collects: a performance dictionary for validation
    :returns: None

    """
    train_acc, val_acc = train_metric['accuracy'], val_metric['accuracy']
    train_prec, val_prec = train_metric['precisions'], val_metric['precisions']
    train_recalls, val_recalls = train_metric['recalls'], val_metric['recalls']
    log_str = 'Train/Val| Loss: {:.4f}/{:.4f}|'.format(train_loss, val_loss)
    log_str += 'Acc: {:.4f}/{:.4f}|'.format(train_acc, val_acc)

    n_classes = len(train_prec)

    templ = 'Pr: ' + ', '.join(['{:.4f}'] * (n_classes-1)) + '/'
    log_str += templ.format(*(train_prec[1:].tolist()))
    templ = ', '.join(['{:.4f}'] * (n_classes-1)) + '|'
    log_str += templ.format(*(val_prec[1:].tolist()))

    templ = 'Re: ' + ', '.join(['{:.4f}'] * (n_classes - 1)) + '/'
    log_str += templ.format(*(train_recalls[1:].tolist()))
    templ = ', '.join(['{:.4f}'] * (n_classes - 1)) + '|'
    log_str += templ.format(*(val_recalls[1:].tolist()))
    log_str += 'T(s) {:.2f}'.format(time_duration)
    print(log_str)
Download .txt
gitextract_17ft28df/

├── .gitignore
├── LICENSE
├── README.md
├── config.py
├── data/
│   ├── train.csv
│   └── val.csv
├── dataset.py
├── main.py
├── model.py
├── test.py
└── utils.py
Download .txt
SYMBOL INDEX (19 symbols across 6 files)

FILE: config.py
  function parse_arguments (line 4) | def parse_arguments():

FILE: dataset.py
  class NCovDataset (line 12) | class NCovDataset(data.Dataset):
    method __init__ (line 13) | def __init__(self, root_dir, stage='train'):
    method __len__ (line 33) | def __len__(self):
    method __getitem__ (line 36) | def __getitem__(self, index):
    method do_augmentation (line 79) | def do_augmentation(self, array, mask):
    method make_weights_for_balanced_classes (line 112) | def make_weights_for_balanced_classes(self):

FILE: main.py
  function get_lr (line 17) | def get_lr(optimizer):
  function train_model (line 22) | def train_model(model, train_loader, epoch, num_epochs, optimizer, writer,
  function evaluate_model (line 66) | def evaluate_model(model, val_loader, epoch, num_epochs, writer, current...
  function main (line 111) | def main(args):

FILE: model.py
  class COVNet (line 6) | class COVNet(nn.Module):
    method __init__ (line 7) | def __init__(self, n_classes):
    method forward (line 17) | def forward(self, x):

FILE: test.py
  function evaluate_model (line 15) | def evaluate_model(model, val_loader):
  function main (line 47) | def main(args):

FILE: utils.py
  function calc_multi_cls_measures (line 6) | def calc_multi_cls_measures(probs, label):
  function print_progress (line 28) | def print_progress(epoch=None, n_epoch=None, n_iter=None, iters_one_batc...
  function print_epoch_progress (line 71) | def print_epoch_progress(train_loss, val_loss, time_duration, train_metric,
Condensed preview — 11 files, each showing path, character count, and a content snippet. Download the .json file or copy for the full structured content (38K chars).
[
  {
    "path": ".gitignore",
    "chars": 920,
    "preview": "#cmake related files\nCMakeCache.txt\nCMakeFiles\nCMakeScripts\nMakefile\ncmake_install.cmake\ninstall_manifest.txt\nCTestTestf"
  },
  {
    "path": "LICENSE",
    "chars": 12356,
    "preview": "“Commons Clause” License Condition v1.0\n\nThe Software is provided to you by the Licensor under the\nLicense, as defined b"
  },
  {
    "path": "README.md",
    "chars": 2087,
    "preview": "# COVID-19 Detection Neural Network (COVNet)\nThis is a PyTorch implementation of the paper \"[Artificial Intelligence Dis"
  },
  {
    "path": "config.py",
    "chars": 1164,
    "preview": "import argparse\n\n\ndef parse_arguments():\n    \"\"\"Argument Parser for the commandline argments\n    :returns: command line "
  },
  {
    "path": "data/train.csv",
    "chars": 41,
    "preview": "case,label\ncaseid1,0\ncaseid2,1\ncaseid3,2\n"
  },
  {
    "path": "data/val.csv",
    "chars": 21,
    "preview": "case,label\ncaseid4,0\n"
  },
  {
    "path": "dataset.py",
    "chars": 4550,
    "preview": "import os\nimport pandas as pd\nimport numpy as np\n\nimport torch\nimport torch.utils.data as data\nimport SimpleITK as sitk\n"
  },
  {
    "path": "main.py",
    "chars": 7796,
    "preview": "import os\nimport numpy as np\nimport time\n\nfrom tensorboardX import SummaryWriter\nimport torch\nimport torch.optim as opti"
  },
  {
    "path": "model.py",
    "chars": 841,
    "preview": "import torch\nimport torch.nn as nn\nfrom torchvision import models\n\n\nclass COVNet(nn.Module):\n    def __init__(self, n_cl"
  },
  {
    "path": "test.py",
    "chars": 2389,
    "preview": "import os\nfrom tqdm import tqdm\nimport numpy as np\n\nimport torch.nn as nn\nimport torch.nn.functional as F\nimport torch\n\n"
  },
  {
    "path": "utils.py",
    "chars": 3785,
    "preview": "import numpy as np\nimport pandas as pd\nfrom sklearn.metrics import accuracy_score, precision_score, recall_score\n\n\ndef c"
  }
]

About this extraction

This page contains the full source code of the bkong999/COVNet GitHub repository, extracted and formatted as plain text for AI agents and large language models (LLMs). The extraction includes 11 files (35.1 KB), approximately 8.2k tokens, and a symbol index with 19 extracted functions, classes, methods, constants, and types. Use this with OpenClaw, Claude, ChatGPT, Cursor, Windsurf, or any other AI tool that accepts text input. You can copy the full output to your clipboard or download it as a .txt file.

Extracted by GitExtract — free GitHub repo to text converter for AI. Built by Nikandr Surkov.

Copied to clipboard!