Mask RCNN based blood cell classification
- Please download following coco mask rcnn pretrained model to enable transfer learning https://github.com/matterport/Mask_RCNN/releases/download/v2.0/mask_rcnn_coco.h5
- Versions of mask-rcnn, tensorflow, tensorflow-gpu, scikit-image and keras should match the versions mentioned below to successfully run the project
- Fully trained model needed for inference can be found here https://drive.google.com/uc?id=1Y01piV_VTMTaBu4twIohJ9Om9RnV4DNf&export=download
Trained using CUDA 10 with CUDNN enabled GTX 1080 and Ryzen 5800X on Windows 10 build 19042. Python version 3.7.7 64bit with the following packages installed
Package Version
absl-py 0.12.0
astor 0.8.1
backcall 0.2.0
cached-property 1.5.2
colorama 0.4.4
cycler 0.10.0
decorator 4.4.2
gast 0.2.2
google-pasta 0.2.0
grpcio 1.36.1
h5py 2.10.0
imageio 2.9.0
importlib-metadata 3.7.3
ipython 7.21.0
ipython-genutils 0.2.0
jedi 0.18.0
Keras 2.1.5
Keras-Applications 1.0.8
Keras-Preprocessing 1.1.2
kiwisolver 1.3.1
Markdown 3.3.4
mask-rcnn 2.1
matplotlib 3.3.4
networkx 2.5
numpy 1.20.1
opt-einsum 3.3.0
parso 0.8.1
pickleshare 0.7.5
Pillow 8.1.2
pip 19.2.3
prompt-toolkit 3.0.18
protobuf 3.15.6
Pygments 2.8.1
pyparsing 2.4.7
python-dateutil 2.8.1
PyWavelets 1.1.1
PyYAML 5.4.1
scikit-image 0.16.2
scipy 1.6.2
setuptools 41.2.0
six 1.15.0
tensorboard 1.15.0
tensorflow 1.15.3
tensorflow-estimator 1.15.1
tensorflow-gpu 1.15.2
termcolor 1.1.0
tifffile 2021.3.17
traitlets 5.0.5
typing-extensions 3.7.4.3
wcwidth 0.2.5
Werkzeug 1.0.1
wheel 0.36.2
wrapt 1.12.1
zipp 3.4.1