-
+ set +x
grep: experiments/logs/faster_rcnn_end2end_VGG16_.txt.2017-06-20_00-04-24: No such file or directory
+ python ./tools/test_net.py --device GPU --device_id 0 --weights --imdb voc_2007_test -…
-
请问将输入调小，比如320，应该设置anchor size，和其他超参？
-
when i try to import
`from vis.modifiers import Jitteren`
i got an import error:
`ModuleNotFoundError: No module named 'vis.modifiers'`
i install it through source
-
영상을 1차원 MLP로 변환한 후 인식을 하면 Overfitting되는 문제가 있다. 1차원 데이터에서는 영상의 위치에 대한 정보를 얻기 어렵기 때문이다. 이에 반해 2차원 데이터에서는 원본 영상의 특징을 쉽게 획득할 수 있다. 이 방법이 CNN(Convolutional neural network)방법이다. (영상의 특징을 찾는 단계에서는 영상을 1차원으로…
-
Hi,when I use ckpt v1 format,the command line as follows,
python ./faster_rcnn/test_net.py --gpu 0 --weights ./models/VGGnet_fast_rcnn_iter_150000.ckpt --imdb voc_2007_test --cfg ./experiments/cfgs/f…
ygren updated
5 years ago
-
I was running the following command:
python faster_rcnn/train_net.py --gpu 0 --weights ./data/pretrain_mod
el/Resnet50.npy --imdb voc_2007_trainval --iters 70000 --cfg ./experiments/cfgs/faster_rc…
-
Hello Rémi,
Hope you are doing well. I have several general questions, notably about the parameters you used for your pre-trained model.
If I understood well, you used 15k patchs and the number o…
-
I want to write a c++ program to detect video/camera, I hope the c++ program's detection effect is just like ssd_pascal_webcam.py.
I can run ssd_detect.cpp in eclipse C++, I know this program c…
-
after training the model ，i didn`t get the xxx.ckpt file，so my test failed。and it repeated the print message “waiting for xxx.ckpt file exist”。we should get the xxxx.ckpt file，which like the VGGnet_fa…
-
A simple baseline is described here: https://arxiv.org/pdf/1512.02167.pdf (Simple Baseline for Visual Question Answering)
We have almost all of this already, except for the image CNN. The images ar…