val_outputs_2 = sliding_window_inference(test_images, roi_size,
sw_batch_size, model)
val_outputs_1 = val_outputs_1.argmax(dim=1, keepdim=True)
val_outputs_2 = val_outputs_2.argmax(dim=1, keepdim=True)
#a = val_outputs_1.cpu().detach().numpy()
#b = val_outputs_2.cpu().detach().numpy()
first_lung = largest(val_outputs_1)
second_lung = largest(val_outputs_2 - first_lung)
#second_largest = largest(second_lung)
#val_outputs = both_lungs
#else:
#both_lungs = largest(val_outputs)
g = ndimage.sum(first_lung) * 0.10
if ndimage.sum(second_lung) >= g:
both_lungs = first_lung + second_lung
both_lungs = both_lungs.cpu().clone().numpy()
both_lungs = both_lungs.astype(np.bool)
else:
both_lungs = largest(val_outputs_1)
both_lungs = both_lungs.cpu().clone().numpy()
both_lungs = both_lungs.astype(np.bool)
saver.save_batch(both_lungs, test_data["image_meta_dict"])
print("FINISH!!")
with torch.no_grad():
#saver = NiftiSaver(output_dir='C:\\Users\\isasi\\Downloads\\Pancreas_Segs_Out')
saver = NiftiSaver(output_dir='//home//imoreira//Kidneys_Segs_Out',
output_postfix="seg_kidneys",
output_ext=".nii.gz",
mode="nearest",
padding_mode="zeros")
for i, train_inf_data in enumerate(train_inf_loader):
#for test_data in test_loader:
train_inf_images = train_inf_data["image"].to(device)
roi_size = (96, 96, 96)
sw_batch_size = 4
val_outputs = sliding_window_inference(train_inf_images,
roi_size,
sw_batch_size,
model,
overlap=0.8)
# val_outputs = torch.squeeze(val_outputs, dim=1)
val_outputs = val_outputs.argmax(dim=1, keepdim=True)
#val_outputs = largest(val_outputs)
val_outputs = val_outputs.cpu().clone().numpy()
val_outputs = val_outputs.astype(np.bool)
saver.save_batch(val_outputs, train_inf_data["image_meta_dict"])
#saver = NiftiSaver(output_dir='C:\\Users\\isasi\\Downloads\\Bladder_Segs_Out')
saver = NiftiSaver(
output_dir='//home//imoreira//Segs_Out//',
#output_dir='C:\\Users\\isasi\\Downloads\\Segs_Out',
output_postfix="seg",
output_ext=".nii.gz",
mode="nearest",
padding_mode="zeros")
for i, test_data in enumerate(test_loader):
#for test_data in test_loader:
test_images = test_data["image"].to(device)
roi_size = (96, 96, 96)
sw_batch_size = 4
val_outputs = sliding_window_inference(test_images,
roi_size,
sw_batch_size,
model,
overlap=0.8)
val_outputs = val_outputs.argmax(dim=1, keepdim=True)
#val_outputs = val_outputs.squeeze(dim=0).cpu().clone().numpy()
#val_outputs = largest(val_outputs)
val_outputs = val_outputs.cpu().clone().numpy()
val_outputs = val_outputs.astype(np.int)
#val_outputs = torch.argmax(val_outputs, dim=1)
#val_outputs = val_outputs.squeeze(dim=0).cpu().data.numpy()
saver.save_batch(val_outputs, test_data["image_meta_dict"])
