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

MoCoGAN: Decomposing Motion and Content for Video Generation

PSPNet in Chainer

Deep learning (neural network) based remote photoplethysmography: how to extract pulse signal from video using deep learning tools

Tensorflow AffordanceNet and AffContext implementations

Code for "Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation" ICCV'21

A PyTorch implementation for V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

Source code for paper "Deep Diffusion Models for Robust Channel Estimation", TBA.

PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution' (CVPRW 2017)

PSANet: Point-wise Spatial Attention Network for Scene Parsing, ECCV2018.

Official code release for ICCV 2021 paper SNARF: Differentiable Forward Skinning for Animating Non-rigid Neural Implicit Shapes.

A light-weight image labelling tool for Python designed for creating segmentation data sets.

Semantic Segmentation Architectures Implemented in PyTorch

Implementation of light baking system for ray tracing based on Activision's UberBake

Codes for AAAI22 paper "Learning to Solve Travelling Salesman Problem with Hardness-Adaptive Curriculum"

3D-aware GANs based on NeRF (arXiv).

Generate saved_model, tfjs, tf-trt, EdgeTPU, CoreML, quantized tflite and .pb from .tflite.

TACTO: A Fast, Flexible and Open-source Simulator for High-Resolution Vision-based Tactile Sensors

Le dataset des images du projet d'IA de 2021

ScriptProfilerPy - Module to visualize where your python script is slow

Implementation of ECCV20 paper: the devil is in classification: a simple framework for long-tail object detection and instance segmentation