-
# voc dataset
[375,500]
## theoretical optimal config
min_crop_size=[384,480]
max_crop_size=[384,480]
midnet_scale=10 (input_size=[480,480])
# cityscapes dataset
[1024,2048]
## theoretic…
-
Traceback (most recent call last):
File "train.py", line 10, in
from model import FasterRCNNVGG16
File "/home/lxt/cvpr2019-video/simple-faster-rcnn-pytorch/model/__init__.py", line 1, in
…
-
when I run trainval_net.py --dateset pascal_voc --net vgg16 --bs 4 --nw 1 --lr 0.004 --lr_decay_step 8 --cuda ,a error occuers.However,the pycocotools has been installed in the pytorch lib and removed…
-
Hello，codo master
I want to add some keras layer in the project as the perceptual loss. For example, the Vgg16 in the applications of keras is used as the feature extractor. However, it is found t…
-
Hi! I'm receiving an error while trying to train the model on a custom dataset in colab. I created test.txt and training.txt and modified the paths at custom_vqgan.yaml. I don't know if the images dim…
-
Hi thank you for you sharing~
Could you please show your miss rate of test set in reasonable condition?
l used py-faster-rcnn VGG16 on this test set, but the detection result is not good , the m…
-
Hi
I run you code:
./experiments/scripts/faster_rcnn_end2end.sh 0 VGG16 coco
And have some bug:
IOError: [Errno 2] No such file or directory: '/home/dsvn/workspace/Text-Detection-with-FRCN/py-fa…
cttsp updated
7 years ago
-
Hi,
Because I read your paper before, I think it is an interesting topic.
So I try to reproduce it. But when I train the image model, its result is very strange. The validation accuracy always show…
-
"Porównać różne modele z https://keras.io/api/applications/ . Może zabraknąć czasu na zrobienie wielu epok dla każdego modelu - w takiej sytuacji warto np. sprawdzić tylko jeden z całej klasy modeli, …
-
Created a new issue because #88 is poorly named
@ashisharora010 @veralauee
I have tried for a week straight to get this repository working and I'm still not having much luck.
# Can't run co…