Pytorch implementation of NEGEV method. Paper: "Negative Evidence Matters in Interpretable Histology Image Classification".

Last update: Dec 01, 2022

Overview

Pytorch 1.10.0 code for:

Negative Evidence Matters in Interpretable Histology Image Classification (https://arxiv. org/abs/xxxx.xxxxx)

Citation:

@article{negevsbelharbi2021,
  title={Negative Evidence Matters  in Interpretable Histology Image Classification},
  author={Belharbi, S. and  Pedersoli, M and
  Ben Ayed, I. and McCaffrey, L. and Granger, E.},
  journal={CoRR},
  volume={abs/xxxx.xxxxx},
  year={2021}
}

Issues:

Please create a github issue.

Method:

Results:

Requirements:

Python 3.7.10
Pytorch 1.10.0
torchvision 0.11.1

pip install torch==1.10.0 -f https://download.pytorch.org/whl/cu111/torch-1.10.0%2Bcu111-cp37-cp37m-linux_x86_64.whl
pip install torchvision==0.11.1 -f https://download.pytorch.org/whl/cu111/torchvision-0.11.1%2Bcu111-cp37-cp37m-linux_x86_64.whl

Full dependencies
Build and install CRF:
- Install Swig
- CRF (not used in this work, but it is part of the code.)

cdir=$(pwd)
cd dlib/crf/crfwrapper/bilateralfilter
swig -python -c++ bilateralfilter.i
python setup.py install
cd $cdir
cd dlib/crf/crfwrapper/colorbilateralfilter
swig -python -c++ colorbilateralfilter.i
python setup.py install

Download datasets :

2.1. Links to dataset:

2.2. Download datasets:

GlaS: ./download-glas-dataset.sh.

You find the splits in ./folds.

Run code :

CAM-method: CAM over GLAS using ResNet50:

cudaid=$1
export CUDA_VISIBLE_DEVICES=$cudaid
getfreeport() {
freeport=$(python -c 'import socket; s=socket.socket(); s.bind(("", 0)); print(s.getsockname()[1]); s.close()')
}
export OMP_NUM_THREADS=50
export NCCL_BLOCKING_WAIT=1
plaunch=$(python -c "from os import path; import torch; print(path.join(path.dirname(torch.__file__), 'distributed', 'launch.py'))")
getfreeport
torchrun --nnodes=1 --node_rank=0 --nproc_per_node=1  \
                         --master_port=$freeport main_wsol.py \ --local_world_size=1 \
                         --task STD_CL \
                         --encoder_name resnet50 \
                         --arch STDClassifier \
                         --runmode final-mode \
                         --opt__name_optimizer sgd \
                         --batch_size 32 \
                         --eval_checkpoint_type best_localization \
                         --opt__step_size 250 \
                         --opt__gamma 0.1 \
                         --max_epochs 1000 \
                         --freeze_cl False \
                         --support_background True \
                         --method CAM \
                         --spatial_pooling WGAP \
                         --dataset GLAS \
                         --fold 0 \
                         --cudaid 0 \
                         --debug_subfolder None \
                         --amp True \
                         --opt__lr 0.003 \
                         --exp_id 11_19_2021_09_32_36_109051__423849

NEGEV-method: over GLAS using ResNet50:

cudaid=$1
export CUDA_VISIBLE_DEVICES=$cudaid
getfreeport() {
freeport=$(python -c 'import socket; s=socket.socket(); s.bind(("", 0)); print(s.getsockname()[1]); s.close()')
}
export OMP_NUM_THREADS=50
export NCCL_BLOCKING_WAIT=1
plaunch=$(python -c "from os import path; import torch; print(path.join(path.dirname(torch.__file__), 'distributed', 'launch.py'))")
getfreeport
torchrun --nnodes=1 --node_rank=0 --nproc_per_node=1 \
                         --master_port=$freeport main_wsol.py \ --local_world_size=1 \
                         --task NEGEV \
                         --world_size 1 \
                         --task NEGEV \
                         --encoder_name resnet50 \
                         --arch UnetNEGEV \
                         --runmode final-mode \
                         --opt__name_optimizer sgd \
                         --dist_backend mpi \
                         --batch_size 32 \
                         --eval_checkpoint_type best_localization \
                         --opt__step_size 250 \
                         --opt__gamma 0.1 \
                         --max_epochs 1000 \
                         --freeze_cl True \
                         --support_background True \
                         --method CAM \
                         --spatial_pooling WGAP \
                         --dataset GLAS \
                         --fold 0 \
                         --cudaid 0 \
                         --debug_subfolder None \
                         --amp True \
                         --opt__lr 0.1 \
                         --negev_ptretrained_cl_cp best_localization \
                         --elb_init_t 1.0 \
                         --elb_max_t 10.0 \
                         --elb_mulcoef 1.01 \
                         --sl_ng True \
                         --sl_ng_seeder probability_seeder \
                         --sl_ng_lambda 1.0 \
                         --sl_ng_start_ep 0 \
                         --sl_ng_end_ep -1 \
                         --sl_ng_min 1 \
                         --sl_ng_max 1 \
                         --sl_ng_ksz 3 \
                         --crf_ng False \
                         --jcrf_ng False \
                         --neg_samples_ng False \
                         --max_sizepos_ng False \
                         --exp_id 12_13_2021_00_49_48_796469__3314599

Train the CAM-method first. Then, copy the best model from the exp folder into the folder ./pretrained. Copy the whole folder with this name format GLAS-0-resnet50-CAM-WGAP-cp_best_localization.

Pytorch implementation of NEGEV method. Paper: "Negative Evidence Matters in Interpretable Histology Image Classification".

Related tags

Overview

Pytorch 1.10.0 code for:

Citation:

Issues:

Content:

Method:

Results:

Requirements:

Download datasets :

2.1. Links to dataset:

2.2. Download datasets:

Run code :

Owner

Soufiane Belharbi

BOOKSUM: A Collection of Datasets for Long-form Narrative Summarization

Yolov5-opencv-cpp-python - Example of using ultralytics YOLO V5 with OpenCV 4.5.4, C++ and Python

Repo for the ACMMM20 submission: "Personalized breath based biometric authentication with wearable multimodality".

Calling Julia from Python - an experiment on data loading

FinEAS: Financial Embedding Analysis of Sentiment 📈

This repo contains the implementation of the algorithm proposed in Off-Belief Learning, ICML 2021.

TabNet for fastai

Incorporating Transformer and LSTM to Kalman Filter with EM algorithm

PSTR: End-to-End One-Step Person Search With Transformers (CVPR2022)

Direct design of biquad filter cascades with deep learning by sampling random polynomials.

Dilated RNNs in pytorch

SGoLAM - Simultaneous Goal Localization and Mapping

Bravia core script for python

A Keras implementation of YOLOv3 (Tensorflow backend)

A basic implementation of Layer-wise Relevance Propagation (LRP) in PyTorch.

Repo for "Benchmarking Robustness of 3D Point Cloud Recognition against Common Corruptions" https://arxiv.org/abs/2201.12296

Code for EMNLP 2021 main conference paper "Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification"

MaskTrackRCNN for video instance segmentation based on mmdetection

Ludwig is a toolbox that allows to train and evaluate deep learning models without the need to write code.

Self-supervised learning optimally robust representations for domain generalization.