def tfreloader(mode, ep, bs, ctr, cte, cva):
filename = data_dir + '/' + mode + '.tfrecords'
if mode == 'train':
ct = ctr
elif mode == 'test':
ct = cte
else:
ct = cva
datasets = data_input2.DataSet(bs, ct, ep=ep, mode=mode, filename=filename)
return datasets
row['path'], row['label'])
test_tiles_list.extend(tile_ids)
test_tiles = pd.DataFrame(
test_tiles_list, columns=['slide', 'level', 'path', 'label'])
test_tiles.to_csv(data_dir + '/te_sample.csv',
header=True,
index=False)
tes = test_tiles
tecc = len(tes['label'])
if not os.path.isfile(data_dir + '/test.tfrecords'):
loaders.loader(data_dir, 'test')
m = cnn4.INCEPTION(INPUT_DIM,
HYPERPARAMS,
meta_graph=opt.modeltoload,
log_dir=LOG_DIR,
meta_dir=METAGRAPH_DIR,
model=opt.mode)
print("Loaded! Ready for test!")
if tecc >= bs:
datasets = data_input2.DataSet(bs,
tecc,
ep=1,
cls=2,
mode='test',
filename=data_dir +
'/test.tfrecords')
m.inference(datasets, opt.dirr, testset=tes, pmd=opt.pdmd, bs=bs)
else:
print("Not enough testing images!")
smoothgrad_mask_grayscale)
smoothgrad_mask_grayscale = py_map2jpg(
smoothgrad_mask_grayscale)
sa = im2double(img) * 255
sb = im2double(smoothgrad_mask_grayscale) * 255
scurHeatMap = sa * 0.5 + sb * 0.5
sab = np.hstack((sa, sb))
sfull = np.hstack((scurHeatMap, sab))
cv2.imwrite(str(outpath + str(ct) + '.png'), sfull)
ct += 1
except tf.errors.OutOfRangeError:
print("Done!")
break
if __name__ == "__main__":
THE = data_input.DataSet(64,
10000,
ep=1,
cls=2,
mode='test',
filename='PATH TO test.tfrecords')
reconstruct(THE,
'I3',
2,
'PATH TO trained model',
'PATH TO output dir',
do=0.3,
bs=64)
def tfreloader(mode, ep, bs, ct):
filename = data_dir + '/' + mode + '.tfrecords'
datasets = data_input2.DataSet(bs, ct, ep=ep, mode=mode, filename=filename)
return datasets
def tfreloader(bs, cls, ct):
filename = data_dir + '/test.tfrecords'
datasets = data_input.DataSet(bs, ct, ep=1, cls=cls, mode='test', filename=filename)
return datasets