Comments (2)
Have the same request, any idea?
from flownet2-tf.
You should use sess.run with feed_dict and change the input.
Firstly we create a placeholder for images:
im1_pl = tf.placeholder(tf.float32, [n, res.shape[0], res.shape[1], 3])
im2_pl = tf.placeholder(tf.float32, [n, res.shape[0], res.shape[1], 3])
#n is the size of your batch
and rewrite inputs in this way:
inputs = {'input_a': im1_pl, 'input_b': im2_pl}
then in running of a session:
first_sequence=[images you want]
second_sequence=[images you want]
feed_dict = {im1_pl: first_sequence , im2_pl: second_sequence}
and give this feed_dict to sess.run:
pred_flow = sess.run(pred_flow, feed_dict = feed_dict)[0, :, :, :]
from flownet2-tf.
Related Issues (20)
- Error compiling cuda_kernel_helper.h: No such file or directory HOT 3
- Why do we need flow = predict_flow2 * 20.0 in flownet_s.py
- undefined symbol: _ZN10tensorflow12OpDefBuilder4AttrESs HOT 2
- Which tensorflow version to use?
- Can't download pretrained weights from aws HOT 2
- Can't download pretrained weights HOT 4
- AttributeError: 'module' object has no attribute 'contrib'
- No OpKernel was registered... HOT 1
- make error HOT 3
- Update of FN2 to TF2.x?
- Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR HOT 1
- how to transfer the ppm and flo data to the tfrecord ones?
- error: no module named png HOT 1
- Different error when running test: Undefined symbol: _ZN10tensorflow3PadERKN5Eigen9GpuDeviceEPKfiiiiiiPf HOT 10
- I got a very large number of the flow?
- About augmentation
- What version of Tensorflow can I use for training?
- make error
- ImportError: No module named 'matplotlib._path'
- NotFoundError:\.\ops\build\downsample.so not found 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 flownet2-tf.