Comments (5)
Sounds like bash cannot read the values as integers. Can you try the following from your terminal: python train.py --dataset mnist --isize 32 --nc 1 --niter 15 --anomaly_class 0
, which trains mnist dataset when the anomalous class is 0. If this works, you can make sure that the repo on your machine works fine.
from ganomaly.
If you are running on Ubuntu, the default shell is dash, so the {0..2} increments don't work there. If you run the line as bash experiments/run_cifar.sh
it will work smoothly.
I got that information from stackoverflow.
from ganomaly.
Thanks for your timely response : )
It seems ok as follows:
python train.py --dataset mnist --isize 32 --nc 1 --niter 2 --anomaly_class 0
/home/brucelau/anaconda3/envs/fcn/lib/python3.5/site-packages/torchvision/transforms/transforms.py:188: UserWarning: The use of the transforms.Scale transform is deprecated, please use transforms.Resize instead.
"please use transforms.Resize instead.")
>> Training model Ganomaly.
>> Training model Ganomaly. Epoch 1/2
Avg Run Time (ms/batch): 15.247 AUC: 0.869 max AUC: 0.869
>> Training model Ganomaly. Epoch 2/2
Avg Run Time (ms/batch): 14.507 AUC: 0.857 max AUC: 0.869
>> Training model Ganomaly.[Done]
I'll close this issue and dive into the code.
Thank you!
from ganomaly.
hi samet-akcay
i have got the problem when training mobilefacenet
by using this command : CUDA_VISIBLE_DEVICES='0,1,2,3' python -u train_softmax.py --network y1 --loss-type 4 --margin-m 0.5 --data-dir ../datasets/faces_ms1m_112x112 --prefix ../model-y1 --emb-size = 128
and i got this problem
usage: train_softmax.py [-h] [--data-dir DATA_DIR] [--prefix PREFIX]
[--pretrained PRETRAINED] [--ckpt CKPT]
[--loss-type LOSS_TYPE] [--verbose VERBOSE]
[--max-steps MAX_STEPS] [--end-epoch END_EPOCH]
[--network NETWORK] [--image-size IMAGE_SIZE]
[--version-se VERSION_SE]
[--version-input VERSION_INPUT]
[--version-output VERSION_OUTPUT]
[--version-unit VERSION_UNIT]
[--version-multiplier VERSION_MULTIPLIER]
[--version-act VERSION_ACT]
[--use-deformable USE_DEFORMABLE] [--lr LR]
[--lr-steps LR_STEPS] [--wd WD]
[--fc7-wd-mult FC7_WD_MULT]
[--fc7-lr-mult FC7_LR_MULT] [--fc7-no-bias]
[--bn-mom BN_MOM] [--mom MOM] [--emb-size EMB_SIZE]
[--per-batch-size PER_BATCH_SIZE]
[--margin-m MARGIN_M] [--margin-s MARGIN_S]
[--margin-a MARGIN_A] [--margin-b MARGIN_B]
[--easy-margin EASY_MARGIN] [--margin MARGIN]
[--beta BETA] [--beta-min BETA_MIN]
[--beta-freeze BETA_FREEZE] [--gamma GAMMA]
[--power POWER] [--scale SCALE]
[--rand-mirror RAND_MIRROR] [--cutoff CUTOFF]
[--color COLOR] [--images-filter IMAGES_FILTER]
[--target TARGET] [--ce-loss]
train_softmax.py: error: argument --emb-size: invalid int value: '='
how i can fix it?
from ganomaly.
@GuokaiLiu
I think it may be the version of python, you can try it using python3
from ganomaly.
Related Issues (20)
- how can i balance the model HOT 7
- how can i see the result of test?? HOT 1
- How to distinguish a mnist_pic is normal or anomaly? HOT 17
- Sudden increase of err_d HOT 1
- Changes for Windows10
- Some qutestions about testing
- can it display where is the anomaly when inference? HOT 1
- what is the difference between fixed_fakes_*.png and fakes.png
- Is the testing function missing self.netg.eval? HOT 5
- AttributeError: module 'torch._C' has no attribute '_cuda_setDevice' HOT 4
- What's the performance of the model in terms of custom dataset?
- Can this code be used on sequence data? HOT 1
- How to use ganomaly neural network for single-channel data training
- Program stucks when the input image size is 224x224 HOT 2
- Experiment(To replicate the results in the paper for MNIST and CIFAR10 datasets)
- Testing
- Possible mode collapse HOT 1
- Test problem HOT 2
- Missing net.eval() in the testing code HOT 1
- ROC is changed every time
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 ganomaly.