Comments (7)
In models/CenterNet-104.py, model class definition, the out_dim is hard-coded to 80. For custom datasets with a different out_dim, these need to be changed along with the above-mentioned changes. Just making a note for other users.
from centernet.
I replaced the content of my .data/coco/annotations/instances_{minival2014,trainval2014}.json to my coco style file and replaced the content of my .data/coco/images/{minival2014,trainval2014} to my own images.
following is my CenterNet-104.json file.
{
"system": {
"dataset": "MSCOCO",
"batch_size": 1,
"sampling_function": "kp_detection",
"train_split": "trainval",
"val_split": "minival",
"learning_rate": 0.00025,
"decay_rate": 10,
"val_iter": 200,
"opt_algo": "adam",
"prefetch_size": 6,
"max_iter": 100000,
"stepsize": 4500,
"snapshot": 5000,
"chunk_sizes": [1],
"data_dir": "../data"
},
"db": {
"rand_scale_min": 0.6,
"rand_scale_max": 1.4,
"rand_scale_step": 0.1,
"rand_scales": null,
"rand_crop": true,
"rand_color": true,
"border": 128,
"gaussian_bump": true,
"input_size": [511, 511],
"output_sizes": [[128, 128]],
"test_scales": [1],
"top_k": 70,
"categories": 1,
"kp_categories": 1,
"ae_threshold": 0.5,
"nms_threshold": 0.5,
"max_per_image": 100
}
}
from centernet.
@li10141110 How many categories do you have?
from centernet.
@li10141110 Add these codes above the
dist = tag_mean.unsqueeze(1) - tag_mean.unsqueeze(2)
in models/py_utils/kp_utils.py:
if len(tag_mean.size()) < 2:
tag_mean = tag_mean.unsqueeze(0)`
from centernet.
1 category
from centernet.
Thank you Kaiwen, I make it
from centernet.
Did it work with you? I had the same problem but the solution was to edit the categories number in the config file. I am also training with 1 class but I am having problems in the evaluation.
I have only 1 class, and it's giving me a "key error 0"
category = self._coco_to_class_map[cat_id]
in the db/coco.py file
from centernet.
Related Issues (20)
- RuntimeError: invalid argument 5: k not in range for dimension HOT 11
- GPU memory always the same? HOT 1
- what tag means HOT 1
- [Errno 2] No such file or directory HOT 1
- Why “height_inds = (br_ys < tl_ys)”? HOT 1
- Compiling Corner Pooling Layers Error HOT 1
- ImportError HOT 1
- Where should I change the number of GPUs used?
- CUDA vision 10.2 Unable to compile DCNS according to the process
- KeyError: 'f'
- Error when running this: "python setup.py install --user" HOT 1
- about traindev and testdev
- Transfer learning possible?
- undefined symbol: _ZNSt15__exception_ptr13exception_ptr10_M_releaseEv HOT 1
- cascade corner pooling
- installing on another architecture
- Exception in Thread: ValueError: signal number 32 out of range
- from GIoULoss to CIoULoss
- train can not run ,it start but it doesn't run anymore
- Error when try to create conda environment HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 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. 📊📈🎉
-
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 ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from centernet.