Skip to content

S
simple-faster-rcnn-pytorch

weixin_47816946 / simple-faster-rcnn-pytorch
与 Fork 源项目一致

从无法访问的项目Fork

通知 8
Star 0
Fork 0
S
simple-faster-rcnn-pytorch

前往新版Gitcode，体验更适合开发者的 AI 搜索 >>

提交 50f8eaf9 编写于 作者: C chenyuntc
浏览文件
操作

tiny fix of chainer training

上级 7b8a36ed
隐藏空白更改
内联 并排
Showing with 1 addition and 1 deletion
train_as_chainer.py
浏览文件 @ 50f8eaf9
...@@ -23,7 +23,7 @@ def eval(dataloader, faster_rcnn, test_num=10000): ...@@ -23,7 +23,7 @@ def eval(dataloader, faster_rcnn, test_num=10000):
gt_bboxes, gt_labels, gt_difficults = list(), list(), list() gt_bboxes, gt_labels, gt_difficults = list(), list(), list()
for ii, (imgs, sizes, gt_bboxes_, gt_labels_, gt_difficults_) in tqdm(enumerate(dataloader)): for ii, (imgs, sizes, gt_bboxes_, gt_labels_, gt_difficults_) in tqdm(enumerate(dataloader)):
sizes = [sizes[0][0], sizes[1][0]] sizes = [sizes[0][0], sizes[1][0]]
pred_bboxes_, pred_labels_, pred_scores_ = faster_rcnn.predict(imgs, [sizes]) pred_bboxes_, pred_labels_, pred_scores_ = faster_rcnn.predict2(imgs, [sizes])
gt_bboxes += list(gt_bboxes_.numpy()) gt_bboxes += list(gt_bboxes_.numpy())
gt_labels += list(gt_labels_.numpy()) gt_labels += list(gt_labels_.numpy())
gt_difficults += list(gt_difficults_.numpy()) gt_difficults += list(gt_difficults_.numpy())
......
Markdown is supported
0% 或 .
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 或