提交 03f5f8c4 编写于 作者: B Benedict

Fix issue #452 for PyTorch 0.4.0

上级 81c9033a
......@@ -51,7 +51,7 @@ class roibatchLoader(data.Dataset):
# for ratio cross 1, we make it to be 1.
target_ratio = 1
self.ratio_list_batch[left_idx:(right_idx+1)] = target_ratio
self.ratio_list_batch[left_idx:(right_idx+1)] = torch.tensor(target_ratio.astype(np.float64)) # trainset ratio list ,each batch is same number
def __getitem__(self, index):
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册