from time import time import numpy as np import datatest from mxboard import SummaryWriter import tools_for_ex_seg as tool import dice_entropy_loss batch_size = 96 img_path = "/home/sz/hard_ex_segmentation/HEI-MED/data4/test/img/" label_path = "/home/sz/hard_ex_segmentation/HEI-MED/data4/test/label/" img_root = "/home/sz/hard_ex_segmentation/HEI-MED/data4/train_crop/img/" label_root = "/home/sz/hard_ex_segmentation/HEI-MED/data4/train_crop/label/" dataset = datatest.get_dataset(img_root, label_root) train_data = mx.gluon.data.DataLoader(dataset, batch_size, shuffle=True, last_batch='rollover', num_workers=8) ctx = [mx.gpu(4), mx.gpu(5), mx.gpu(6), mx.gpu(7)] net = multi_att_net.set_network() net.collect_params().reset_ctx(ctx) net.load_parameters('pretrain2_double.params', ctx=ctx) def get_batch(batch, ctx): if isinstance(batch, mx.io.DataBatch):
batch_size=150 img_path="/home/sz/hard_ex_segmentation/e_dataset/data2/test/img/" label_path="/home/sz/hard_ex_segmentation/e_dataset/data2/test/label/" img_root="/home/sz/hard_ex_segmentation/IDRID/train_crop/img/" label_root="/home/sz/hard_ex_segmentation/IDRID/train_crop/label/" dataset=data_enhance.get_dataset(img_root,label_root) train_data=mx.gluon.data.DataLoader(dataset, batch_size,shuffle=True, last_batch='rollover',num_workers=8) img_root1="/home/sz/hard_ex_segmentation/IDRID/test_crop/img/" label_root1="/home/sz/hard_ex_segmentation/IDRID/test_crop/label/" testset=datatest.get_dataset(img_root1,label_root1) test_data=mx.gluon.data.DataLoader(testset, batch_size=100,shuffle=False, last_batch='keep',num_workers=8) ctx=[mx.gpu(4),mx.gpu(5)] net=res_u_net_attention.set_network() net.collect_params().reset_ctx(ctx) net.hybridize() def get_batch(batch, ctx): if isinstance(batch, mx.io.DataBatch): data = batch.data[0] label = batch.data[1] else: data, label = batch