Issues
- 0
对于ROI Align层中的截取过程不太理解,希望博主能拨冗解答!!
#54 opened by stariveryoung - 2
安装keras时出现依赖项冲突
#53 opened by stariveryoung - 0
如何单独获得每个预测实例的分割结果
#52 opened by svoeff - 4
train.py:232: UserWarning: Output "ROI" missing from loss dictionary. We assume this was done on purpose, and we will not be expecting any data to be passed to "ROI" during training.
#32 opened by CaoXiang-space - 5
请问可以在已有模型上继续训练么
#7 opened by evilvlso - 0
- 1
- 1
IndexError: boolean index did not match indexed array along dimension 0; dimension is 1 but corresponding boolean dimension is 8
#49 opened by bankshotbandwidth - 3
预测出来的图片中并没有区分实例类别
#40 opened by DarlingOhayo1 - 1
- 0
coco数据集标签文件是自带的instances_val2017.json吗
#47 opened by sparksWLL - 0
可以出一个pytorch版本的吗?
#46 opened by pjw2146087 - 2
测试的时候出现IndexError: list index out of range
#45 opened by Pengfeicc - 4
- 3
调用多显卡时显示报错
#43 opened by revquiet - 1
ValueError: **slice index -1 of dimension 0 out of bounds.** for '{{node loss/rpn_class_loss_loss/strided_slice}} =
#42 opened by immaping - 12
1000+图片,但仍显示数据集过小
#41 opened by right135 - 24
tensorflow.python.framework.errors_impl.InvalidArgumentError: indices[1] = 130885 is not in [0, 65472)
#39 opened by zDAIght - 11
开始训练 shape 数据集的错误
#31 opened by xudaopao - 2
使用resnet50训练
#38 opened by theoning - 1
训练时怎么只加载主干网络的权重?
#37 opened by gfzwytc - 1
- 1
- 4
tf2版本的代码
#22 opened by codeseeking - 7
- 10
我cuda版本太高了(11.4),导致tensorflow-gpu无法兼容
#34 opened by 31901026sxc - 1
- 8
- 11
训练中的bug
#28 opened by jiangzhenyudlut - 5
需要requirements.txt文件
#26 opened by 20000131 - 2
num_workers在哪里修改
#27 opened by 20000131 - 1
请问之后会出pytorch版本的mask-rcnn吗
#25 opened by Moris-Zhan - 1
- 2
ValueError: None values not supported.
#23 opened by super-ys - 1
我的cdua版本是10.0,tensorflow-gpu版本是1.13.1,但是cudnn没有找到与cunda10.0对应的cudnn7.4版本,有人遇到相同问题吗
#13 opened by Jess1989 - 2
图片中标注比较多,训练速度特别慢?请教下如何优化呢?
#21 opened by jiangxinufo - 5
一张图有100多个实例 怎么提高速度训练啊 太慢了
#6 opened by dlml - 1
- 1
- 2
老大,请问下同张图片的不同角度能否准确识别
#18 opened by yelynn - 5
有人试过转换成tflite吗?
#17 opened by lbininhbl - 12
- 1
LVIS数据集使用coco.py问题
#16 opened by xdnjust - 1
- 3
关于自己数据集里mask文件夹内图片的读取
#14 opened by yanyu-holo - 4
Open Error! Try again!
#10 opened by qiqingwang577 - 2
训练过程中出现loss为nan
#4 opened by FortuneStar - 2
ValueError: Error when checking input: expected input_image_meta to have shape (13,) but got array with shape (16,)
#11 opened by qiqingwang577 - 4
请问这个报错怎么办,是我版本不对吗? ValueError: Cannot iterate over a shape with unknown rank.
#8 opened by qiqingwang577 - 1
predict.py
#9 opened by babyta