-
Hi, I'm very impressed by your work. I want to know whether your team has implemented experiments on other baselines, like TopoCount on SANet, CAN, or VGG16 without unet architecture.
I've tested som…
-
著書を拝読させていただきました。
第一章 画像分類と転移学習（VGG16)を試させていただき、学習させることができました。
しかし、初学者のため学習データと検証データの正解率や損失の推移のグラフを作出する方法がわかりません。どのようにcodeを追加すればよろしいのでしょうか？
お忙しいところ恐縮ですが、ご教示いただければ幸いです。
-
Add standard vision models that replicates: https://pytorch.org/docs/stable/torchvision/models.html
We want Flux implementations of the architectures. These can be untrained models for now, and we …
-
Thanks for this great repository.
In the ECCV paper, you used a VGG backbone. Could you please share its checkpoints? I understand you have provided a better ResNet backbone already, but I need to …
-
This happens when running the examples for training on VOC, as well as Open Images. My goal is to train on Open Images.
-
I used the vanilla codes and prepare pascal voc 2007 datasets as suggested methods. I set learning rate as 0.01 and use 8 gpus, 24 batch size for training. However, the rcnn_cls loss will be Nan after…
-
I got a vgg16 successfully trained on a custom dataset and it loaded perfectly while testing.
The test_net.py code has a "imdb.evaluate_detections" at the end and this function is not implemented ye…
-
I only do the 25000 iteration, and test the model, but have the following problem. Do you have any ideal what is the problem?
Writing aeroplane VOC results file
Writing bicycle VOC results file
Wri…
-
For VGG16 and AlexNet
Start verifying results ...
Item=0 is wrong (result=0.000000, golden_ref=-6.000000)
Item=1 is wro…
GUUTA updated
4 years ago
-
I have tried many ways to run commands `python trainval_net.py`, but I always failed.
I wish someone can help me to run this work.
Now I have this strange problem:
```
(BNCO) hy@compute01:~/BNCO/B…