Comments (7)
@VanitarNordic If you set weights='imagenet'
for either FCN_VGG16 or FCN_VGG19, it will load the imagenet pre-trained model accordingly. The other weights will be randomly initialized with 'he_normal'.
- If you want to load Caffe models, you will need to convert the weights and you can google how to do it.
- Loading another FCN model with the same architecture but a different number of outputs will cause shape-mismatch problem and you will need to leave out the mismatched layers.
- I don't know whether VGG16 or VGG19 works better for your problem. It depends.
from keras-fcn.
@VanitarNordic
- For imagenet models, it will automatically download. See https://github.com/JihongJu/keras-fcn/blob/master/keras_fcn/encoders.py#L71
x_train
is image(s), a 4D tensor (batch, height, weight, channels), andy_train
is segmentation(s), 4D tensor (batch, height, weight, classes)
from keras-fcn.
@VanitarNordic They are segmentation models. You can load model weights using model.load_weights
and set by_name
to be true
if you are loading a different model with part of the weights in common.
from keras-fcn.
Thank you very much for your reply.
You can load model weights using model.load_weights and set by_name to be true if you are loading a different model with part of the weights in common.
So if I load the weights and also load the dataset, it will Fine-Tune it, and not do the training from scratch, isn't? Does this applies to the cases when the pre-trained weights is for 21 classes and we want to fine-tune it for example for 2 classes?
I have these questions also:
-
The weights of the Caffe FCN-8s (heavy) and its VOC pre-trained model is belong to the VGG16 model?
-
if I train using VGG19, then I will get better results?
from keras-fcn.
Okay, thank you very much. I think I got the point. Just these two questions remained:
-
You mean I should download the pre-trained classification ImageNet (either VGG16 or VGG19) as something like "init-model" and start training. may I ask you the download links?
-
Typically a VOC segmentation dataset consists of RGB images and RGB PNG labels and some TXT files which define files' names for the training and validation sets. therefore may I ask you how what is X and Y here?
fcn_vgg19.fit(X_train, y_train, batch_size=1)
from keras-fcn.
x_train is image(s), a 4D tensor (batch, height, weight, channels), and y_train is segmentation(s), 4D tensor (batch, height, weight, classes)
Would you please explain this with an Example? both x and y belong to the training set? then when the validation images should be tested?
from keras-fcn.
@VanitarNordic fcn_vgg19
is just an instance of keras functional API model. You can use all Model methods, including fit
, fit_generator
, predict
, etc.
from keras-fcn.
Related Issues (20)
- ValueError: Unknown layer: BilinearUpSampling2D HOT 5
- Trying to Train VGG16 Model for localizing Text from natural images. Used Dataset MSRA-TD500 HOT 7
- pre-trained model HOT 1
- FCN in train.py HOT 2
- weight converter HOT 2
- Training on VOC2011 HOT 4
- filter parameter not used for blocks.vgg_fc HOT 1
- Deleted
- ResourceExhaustedError while runing the program on VGG16 HOT 1
- missing backend when not installed from source HOT 3
- makefile : command not found
- Some typos that worth mentioning
- VOC2011 training ends up with unchanged acc HOT 1
- StopIteration HOT 2
- Model always predicts the dominant class HOT 2
- Train my own dataset? HOT 1
- U-Net: Error when checking target: expected activation_1 to have 3 dimensions, but got array with shape (1, 224, 224, 21) HOT 1
- import error: No module named 'keras_fcn.backend'
- NotImplementedError 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 keras-fcn.