Comments (6)
The demo is limited to the VOC categories. You need to run a model that was trained with VOC or finetuned on it.
from blitznet.
Thanks @dvornikita for the clarification. Even for VOC only trained model, I am ending up with a dataloss error as mentioned on another issue.
from blitznet.
Closing due to lack of recent activity.
from blitznet.
Hi, I met the same problem, and I change the VOC_CATS in demo.py to 81 coco categories.
But I get the same error.
When I run
python demo.py --run_name=BlitzNet300_COCO --image_size=300 --detect --segment --eval_min_conf=0.5 --ckpt=1
, I get shape mis-match error below.
Assign requires shapes of both tensors to match. lhs shape= [1,1,512,64] rhs shape= [3,3,512,64]
When I add --seg_filter_size=3 option, I get the error.
Assign requires shapes of both tensors to match. lhs shape= [81] rhs shape= [64]
That means, BlitzNet300_COCO model only takes 64 categories?
Thank you.
from blitznet.
Hello ! I met the same problem, I want to use BlitzNet300_COCO model,how should I do to run the demo please?Have u solve this problem now? Thanks a lot! @dvornikita @kemangjaka
from blitznet.
As I mentioned above, the demo is not meant to work with COCO categories and models trained on COCO. You can either follow the readme and run it with VOC categories, or you will need to modify the code in case you still want to run it with COCO
from blitznet.
Related Issues (20)
- python demo.py --run_name=BlitzNet300_COCO+VOC07+12 --x4 --detect --segment --eval_min_conf=0.5 --ckpt=1 HOT 7
- files = glob(osp.join(self.folder, '*{}'.format(self.data_format))) HOT 1
- tensorflow.python.framework.errors_impl.NotFoundError: /home/cbl/PycharmProjects/blitznet-master/Datasets/voc07-trainval-segmentation; No such file or directory HOT 1
- python training.py --run_name=BlitzNet300_x4_VOC0712_detseg --dataset=voc07+12-segmentation --trunk=resnet50 --x4 --batch_size=32 --optimizer=adam --detect --segment --max_iterations=65000 --lr_decay 40000 50000 HOT 1
- without Preparation3 ,can I train ? HOT 2
- ModuleNotFoundError: No module named 'progressbar' HOT 1
- 1a
- true_number_of_negatives calculation HOT 4
- About the arguments in class feed_forward HOT 1
- Model download HOT 2
- Demo results HOT 2
- Test on MS COCO dataset based on trained checkpoint HOT 3
- Some illogical problems occurred during the detection process.
- How to train on cityscapes? HOT 2
- How to calculate each class of IoUοΌ HOT 4
- About MIoU result HOT 1
- Where is the deconvolution layers?
- Is there any other hidden settings or tricks for training HOT 4
- Pre-trained model and the interface HOT 1
- Download the pre-trained model
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. πππ
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from blitznet.