HiKapok/SSD.TensorFlow
State-of-the-art Single Shot MultiBox Detector in Pure TensorFlow, QQ Group: 758790869
PythonApache-2.0
Issues
- 3
voc_eval.py 211行出现keyerror: File "voc_eval.py", line 211, in voc_eval R = class_recs[image_ids[d]] KeyError: '000000117121'
#140 opened by yangguoqing666 - 1
How can I use multi-GPUs to train the ssd model?
#124 opened by cemiboou - 0
怎样把Tensor转换成NDArray
#141 opened by MSTK2014 - 10
TypeError: `default_name` type (<class 'list'>) is not a string type. When run train_ssd.py, I meet a TpyeError.
#117 opened by CaptainKeer - 0
tensorflow.python.framework.errors_impl.NotFoundError: Could not find directory
#142 opened by ZhaolinWang0110 - 0
请问我在执行eval_ssd.py遇到的问题,下面是报错内容
#139 opened by chenjjjjuu - 0
请问我在执行eval——
#138 opened by chenjjjjuu - 2
InvalidArgumentError (see above for traceback): Restoring from checkpoint failed. This is most likely due to a mismatch between the current graph and the graph from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error: Assign requires shapes of both tensors to match. lhs shape= [1,1,1024,1024] rhs shape= [1,1,4096,4096] [[node save/Assign_29 (defined at E:\Infrared_Deeplearning\SSD-AbsoluteCoord\utility\scaffolds.py:86) ]]
#126 opened by navy63 - 0
- 0
may i have a script for transferring .ckpt to .pb
#136 opened by feifeiwei - 1
How to continue the last training?
#133 opened by 18846935350 - 0
- 1
请问如何在GPU上运行?
#130 opened by chenjjjjuu - 1
eval_ssd.py 生成的预测结果文件中没有filename
#134 opened by leileileidan - 0
voc_eval.py on my own dataset
#120 opened by Kasyene - 1
How to train my own Dataset?
#132 opened by zhang295498 - 0
the pixel of train_image_size is 256
#125 opened by tristehai - 0
How to train my own
#131 opened by zhang295498 - 2
- 0
Why there are no celoss ,locloss and loss images after I finish training on my own dataset?
#129 opened by Taylor0424 - 0
为什么多GPU并行报OOM
#128 opened by DataXujing - 1
为什么开始训练后执行到一定情况就会卡住,然后CPU占用率满,但是gpu为0
#127 opened by bubbliiiing - 0
Is the coordinate position of the detection box upper left corner, lower right corner or upper left corner with width and height?
#123 opened by AndyHon - 1
I can't get the weights of the model.
#122 opened by WangFengtu1996 - 3
- 3
- 1
Detect an image by trained model?
#116 opened by xi3299 - 0
would you explain the modified_smooth_l1?
#115 opened by xiaxia111 - 1
Input nodes missing in frozen graph
#114 opened by sjmjk429 - 0
why not any info printed in traning?
#112 opened by zmhik - 2
- 0
Unhandled cases???
#111 opened by lloydnguyen96 - 0
- 1
questions about voc_eval.py
#107 opened by ydhongHIT - 0
when complete this project
#109 opened by zhuxiaoyangcute - 0
- 0
How can I train from scratch?
#106 opened by chengcchn - 2
join some no labeled image to train dataset
#97 opened by duoduo1234 - 0
How to train without pretrained checkpoint
#105 opened by ydhongHIT - 1
some questions about the eval_ssd.py
#104 opened by ydhongHIT - 1
- 2
gpu fraction
#101 opened by zhengduoru - 0
gpu fraction
#100 opened by zhengduoru - 1
- 5
train_ssd Error
#98 opened by fuaiguo - 7
- 1
the loss is aroung 20 for a long time
#96 opened by jamiechoi1995 - 3
why is the select_threshold 2
#95 opened by tutu123133 - 2
关于hard negative mining过程的疑问,代码疑似有问题
#92 opened by okfang - 1