Comments (8)
I will upload the data_prepration script by end of the day, you should be able to generate train.pkl and other files from that script.
from aesthetic_attributes_maps.
from aesthetic_attributes_maps.
@gautamMalu Traceback (most recent call last):
File "data_preparation.py", line 53, in
x = prepare_image(_image, spp=False)
TypeError: prepare_image() got an unexpected keyword argument 'spp'
from aesthetic_attributes_maps.
I delete spp and set target_size =[299, 299].
from aesthetic_attributes_maps.
I have updated the code, try now. Let me know if you face any problems. I am also updating the README.md, it will take some time probably by tomorrow.
from aesthetic_attributes_maps.
ImportError: No module named SpatialPyramidPooling
I comment it
from aesthetic_attributes_maps.
@gautamMalu starting training now
Traceback (most recent call last):
File "train.py", line 93, in
model.fit_generator(datagen.flow(train_data[0], train_data[1],batch_size=batch_size),8448, nb_epoch, verbose=2,
File "/opt/conda/lib/python2.7/site-packages/keras/preprocessing/image.py", line 461, in flow
save_format=save_format)
File "/opt/conda/lib/python2.7/site-packages/keras/preprocessing/image.py", line 770, in init
(np.asarray(x).shape, np.asarray(y).shape))
ValueError: X (images tensor) and y (labels) should have the same length. Found: X.shape = (8458, 299, 299, 3), y.shape = ()
Also, what does 8448 mean ?
since train size =8458,batchsize = 16,so it should be 8458/16?
from aesthetic_attributes_maps.
Try with fit
instead fit_generator()
like:
model.fit(train_data[0], train_data[1], batch_size=batch_size, nb_epoch=nb_epoch, callbacks=[checkpoint, tb],#, lr_scheduler], validation_data=(val_data[0], val_data[1]), shuffle=True, initial_epoch=initial_epoch)
8448 == number images to be cosindered in one epoch, actually with batch size = 16
and total number of images 8458, I have set it up to be 8448 because 8458/16 is fraction.
Just try with the fit
instead of fit_generator
once it will consume more RAM though.
from aesthetic_attributes_maps.
Related Issues (3)
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 aesthetic_attributes_maps.