meghbhalerao

2020-10-29 7:15:17.47: =============================== logger created =======================================
2020-10-29 7:15:17.47: 
2020-10-29 7:15:17.47: ======================== Starting new session ============================
2020-10-29 7:15:17.47: Command line arguments given: 
Namespace(device='cuda', model_cfg='./outputs/dm_e1/holdout_0/0/modelConfig.cfg', reset_trainer=False, saved_model=None, test_cfg=None, train_cfg='./outputs/dm_e1/holdout_0/0/trainConfig.cfg')
2020-10-29 7:15:18.08: Available devices to Tensorflow:
[name: "/device:CPU:0"
device_type: "CPU"
memory_limit: 268435456
locality {

meghbhalerao

import os
import numpy as np
folds = [5,5]
exp_path = "./outputs/resunet_e1_new/"
avg_dice = []
for holdout in os.listdir(os.path.join(exp_path)):
    for fold in os.listdir(os.path.join(exp_path,holdout)):
        if not ".pkl" in fold:
            for item in os.listdir(os.path.join(exp_path,holdout,fold)):
                if "stdout" in item:

meghbhalerao

# Choose the segmentation model here 
# options: unet, resunet, fcn
model:
  {
    architecture: resunet,
    final_layer: softmax
  }
# Set base filters: number of filters present in the initial module of the U-Net convolution; for IncU-Net, keep this divisible by 4
base_filters: 30
# Set the list of labels the model should train on and predict

meghbhalerao

import SimpleITK as sitk

# read image
inputImage = sitk.ReadImage('/path/to/input.nii.gz')

# get result in the form of a numpy array
npa_res = my_algorithm(sitk.GetArrayFromImage(inputImage)) # my_algorithm does something fancy

# Converting back to SimpleITK (assumes we didn't move the image in space as we copy the information from the original)
result_image = sitk.GetImageFromArray(npa_res)