Comments (7)
Another attempt, I installed tensorflow-gpu 1.6.0 for CUDA library 8.0 but still running python inference.py --img-path=./input/outdoor_1.png --dataset=ade20k --filter-scale=2 --model=others
generates "no checkpoint file found" and the results are not he same as the one stated here.
from icnet-tensorflow.
Hey @aliericcantona, it seems that the checkpoint is missing, so you cannot load the pre-trained weights. You can refer to #45.
from icnet-tensorflow.
change checkpoints.txt to checkpoints
from icnet-tensorflow.
thanks it works. Actually checkpoint.txt --> checkpoint
from icnet-tensorflow.
the results are not exactly the same as the one you posted just slightly different (may be because of the slightly trained model difference). The color model (labels) are exactly the same as PSPNET ADE20K or different?
from icnet-tensorflow.
@aliericcantona, I have updated the model but the output results not, so the results would be a little different.
from icnet-tensorflow.
If you want to apply to other datasets, change following four lines
IGNORE_LABEL = 255 # The class number of background
INPUT_SIZE = '720, 720' # Input size for training
BATCH_SIZE = 16
LEARNING_RATE = 1e-3
MOMENTUM = 0.9
NUM_CLASSES = 19
NUM_STEPS = 60001
POWER = 0.9
RANDOM_SEED = 1234
WEIGHT_DECAY = 0.0001
PRETRAINED_MODEL =
SNAPSHOT_DIR = './snapshots/'
SAVE_NUM_IMAGES = 4
SAVE_PRED_EVERY = 50
these codes in train.py,in model file has ade20k weights,but failed to train, PRETRAINED_MODEL how to load ,PRETRAINED_MODEL = ?
from icnet-tensorflow.
Related Issues (20)
- Errors in restoring the session evalucation.py and network.py
- ValueError: Shape must be rank 4 but is rank 3 for 'data_sub2' (op: 'ResizeBilinear') with input shapes: [720,720,3], [2]. HOT 3
- Why is it suddenly 'killed' run train.py? HOT 1
- How predict the result to use my training model ckpt.meta?
- Dimension not equal HOT 1
- ValueError:Variable conv does not exist
- ValueError when using own dataset HOT 2
- Training own dataset
- Inference time is too high(about 3.5x as supposed to be ~0.04s)
- multi GPU training?
- tensorflow's version HOT 1
- How to use the pre-trained modle of ade20k provided by author,I use the code in demo.ipynb,but it can't open the file,the cityscapes works well.
- Training over-fitting after every epochs
- same classification result with every pixel HOT 1
- can get correct result
- bad results of voc2012
- The update stops and the loss does not drop HOT 4
- Assign requires shapes of both tensors to match. lhs shape= [13] rhs shape= [150]
- 上一个项目
- 关于ade20k的分割结果,颜色和标签有对应关系吗?
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 icnet-tensorflow.