Merge pull request #16 from poldracklab/v0.1.0

V0.1.3

README.md

@@ -1,4 +1,10 @@
 # Nondefaced-Detector
+
+[![PyPI version](https://badge.fury.io/py/nondefaced-detector.svg)](https://badge.fury.io/py/nondefaced-detector)
+[![Downloads](https://pepy.tech/badge/nondefaced-detector)](https://pepy.tech/project/nondefaced-detector)
+[![Documentation Status](https://readthedocs.org/projects/nondefaced-detector/badge/?version=latest)](https://nondefaced-detector.readthedocs.io/en/latest/?badge=latest)
+[![License: Apache 2.0](https://img.shields.io/badge/License-Apache_License,_2.0-lightgrey.svg)](https://opensource.org/licenses/Apache-2.0)
+
 A framework to detect if a 3D MRI volume has been defaced.
 
 ## Table of contents
@@ -44,7 +50,7 @@ NOTE: The CPU container will be very slow for training. We highly recommend that
 ### Pip
 
 ```bash
-$ pip install --no-cache-dir nondefaced-detector[gpu]
+$ pip install --no-cache-dir nondefaced-detector[cpu/gpu]
 ```
 
 <!-- USAGE EXAMPLES -->
@@ -56,7 +62,7 @@ Pre-trained networks are avalaible in the *Nondefaced-detector* [models](https:/
 ```bash
 $ docker run --rm -v $PWD:/data nondefaced-detector:latest-cpu \
     predict \
-    --model-path=/opt/nondefaced-detector/nondefaced_detector/models/pretrained_weights \
+    --model-path=$MODEL_PATH \
     /data/example1.nii.gz
 ```
 
@@ -86,8 +92,9 @@ Steps to reproduce inference results from the paper.
 **Step 1:** Get the preprocessed dataset. You need to have [datalad](https://handbook.datalad.org/en/latest/intro/installation.html) installed.
 
 ```bash
-$ datalad clone https://gin.g-node.org/shashankbansal56/nondefaced-detector-reproducibility /data/nondefaced-detector-reproducibility
-$ cd /data/nondefaced-detector-reproducibility
+$ datalad clone https://gin.g-node.org/shashankbansal56/nondefaced-detector-reproducibility /opt/nondefaced-detector-reproducibility
+$ cd /opt/nondefaced-detector-reproducibility
+$ datalad get pretrained_weights/*
 $ datalad get test_ixi/tfrecords/*
 
 ```
@@ -105,12 +112,20 @@ $ conda activate tf-cpu
 ```bash
 $ git clone https://github.com/poldracklab/nondefaced-detector.git
 ```
-**Step 4:** Run the standalone inference script. The inference script uses the pre-trained model weights under `nondefaced_detector/models/pretrained_weights`
+**Step 4:** Run the standalone inference script.
 ```bash
 $ cd nondefaced-detector
 $ pip install -e .
 $ cd nondefaced_detector
-$ python inference.py < PATH_TO_TFRECORDS [/data/nondefaced-detector-reproducibility/test_ixi/tfrecords] >
+$ python inference.py -h
+usage: inference.py [-h] tfrecords_path model_path
+
+positional arguments:
+  tfrecords_path  Path to tfrecords.
+  model_path      Path to pretrained model weights.
+
+optional arguments:
+  -h, --help      show this help message and exit
 ```
 
 ## Paper
@@ -148,7 +163,7 @@ Shashank Bansal - [email protected]
 
 
 <!-- ACKNOWLEDGEMENTS -->
-## Acknowledgements
+## Acknowledgements 
 
 ### Training Dataset
 The original model was trained on 980 defaced MRI scans from 36 different studies that are publicly available at [OpenNeuro.org](https://openneuro.org/)

docker/cpu.Dockerfile

@@ -1,6 +1,36 @@
 FROM tensorflow/tensorflow:2.4.1-jupyter
 
-RUN apt-get install -y vim
+RUN apt-get install software-properties-common -y && add-apt-repository ppa:git-core/ppa -y
+
+RUN apt-get update -y && apt-get upgrade -y
+
+RUN apt-get install -y vim wget
+
+ENV PATH="/root/miniconda3/bin:${PATH}"
+ARG PATH="/root/miniconda3/bin:${PATH}"
+
+RUN wget \
+    https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh \
+    && mkdir /root/.conda \
+    && bash Miniconda3-latest-Linux-x86_64.sh -b \
+    && rm -f Miniconda3-latest-Linux-x86_64.sh 
+
+RUN conda --version
+
+RUN conda install -c conda-forge datalad -y
+
+RUN git config --global user.email "[email protected]"
+RUN git config --global user.name "nondefaced-detector"
+
+RUN datalad clone https://gin.g-node.org/shashankbansal56/nondefaced-detector-reproducibility /opt/nondefaced-detector-reproducibility
+
+RUN cd /opt/nondefaced-detector-reproducibility
+
+RUN datalad get pretrained_weights/*
+RUN datalad get examples/*
+
+ENV MODEL_PATH='/opt/nondefaced-detector-reproducibility/pretrained_weights'
+ARG MODEL_PATH='/opt/nondefaced-detector-reproducibility/pretrained_weights'
 
 RUN pip3 install nobrainer \
                  sklearn \

docker/gpu.Dockerfile

@@ -1,6 +1,36 @@
 FROM tensorflow/tensorflow:latest-gpu-jupyter
 
-RUN apt-get install -y vim
+RUN apt-get install software-properties-common -y && add-apt-repository ppa:git-core/ppa -y
+
+RUN apt-get update -y && apt-get upgrade -y
+
+RUN apt-get install -y vim wget
+
+ENV PATH="/root/miniconda3/bin:${PATH}"
+ARG PATH="/root/miniconda3/bin:${PATH}"
+
+RUN wget \
+    https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh \
+    && mkdir /root/.conda \
+    && bash Miniconda3-latest-Linux-x86_64.sh -b \
+    && rm -f Miniconda3-latest-Linux-x86_64.sh 
+
+RUN conda --version
+
+RUN conda install -c conda-forge datalad -y
+
+RUN git config --global user.email "[email protected]"
+RUN git config --global user.name "nondefaced-detector"
+
+RUN datalad clone https://gin.g-node.org/shashankbansal56/nondefaced-detector-reproducibility /opt/nondefaced-detector-reproducibility
+
+RUN cd /opt/nondefaced-detector-reproducibility
+
+RUN datalad get pretrained_weights/*
+RUN datalad get examples/*
+
+ENV MODEL_PATH='/opt/nondefaced-detector-reproducibility/pretrained_weights'
+ARG MODEL_PATH='/opt/nondefaced-detector-reproducibility/pretrained_weights'
 
 RUN pip3 install --upgrade tensorflow-gpu==2.3.2
 RUN pip3 install nobrainer \