baiboat

icon location 沈阳

Results 4 issues of baiboat

no file name cityscapesscripts.evaluation.instances2dict_with_polygons

i just found cityscapesscripts.evaluation.instances2dict,where can i found cityscapesscripts.evaluation.instances2dict_with_polygons function?

why it is much slower when i training mobilenetv2-ssdlite than v1,it all most cost one day can only iterate 5000 times,but according to the paper it should much faster,isn't it?

4 comment

TypeError: 'module' object is not callable

环境版本与要求一致，运行python videotest_example.py hy.mp4，提示： Using TensorFlow backend. ../ssd.py:40: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(64, (3, 3), activation="relu", name="conv1_1", padding="same")` name='conv1_1')(net['input']) ../ssd.py:44: UserWarning: Update your `Conv2D` call...

自定义数据集上测试可视化时总是显示的是coco的类别

1 comment

我训练一个自己的数据集，按照文档自定义数据集上训练的介绍新建了config文件，内容如下： _base_ = '../faster_rcnn/faster-rcnn_r50_fpn_1x_coco.py' model = dict(roi_head=dict(bbox_head=dict(num_classes=2))) metainfo = {'classes':('head', 'helmet'), 'palette':[(220, 20, 60), (119, 11, 32)]} train_dataloader = dict(dataset=dict(metainfo=metainfo)) val_dataloader = dict(dataset=dict(metainfo=metainfo)) 训练结束后，测试时的图片却显示的是coco的类别标签，后来我尝试改了coco.py和classes_name.py文件中的类别，也没有作用，我的categories共包含两个类，所以id分别是0和1，但是最终可视化却显示的是coco数据集的类别，请问怎么改？