dedigadot / patchbatch Goto Github PK
View Code? Open in Web Editor NEWPatchBatch - a Batch Augmented Loss for Optical Flow
PatchBatch - a Batch Augmented Loss for Optical Flow
Hi, when i try to run benchmark_kitti, I get an error. I am not sure where is the problem. Can you help in running a benchmark for kitti?
bench_kitti('../../training/image_2/','../../training/flow_noc/','KITTI2015_SPCI',71,255)
Analyzing 000000_10.png 000000_11.png
Calculating descriptors...
Creating NN model_CENTSD_33conv_elu
Traceback (most recent call last):
File "<ipython-input-21-9a2f9cd29ff7>", line 1, in <module>
bench_kitti('../../training/image_2/','../../training/flow_noc/','KITTI2015_SPCI',71,255)
File "/home/ms/ssingh/Climate_models/Final_Models/GAN/data/sceneflow/PatchBatch/benchmark_kitti.py", line 22, in bench_kitti
pb_flow = patchbatch.calc_flow(img1_filename, img2_filename, model_name, None, False)
File "patchbatch.py", line 155, in calc_flow
img_descs = calc_descs(img1_filename, img2_filename, model_name, patch_size, batch_size)
File "patchbatch.py", line 25, in calc_descs
nn_model, theano_func = NN.get_net_and_funcs(net_name, patch_size, batch_size, weights_filename, eparams_filename)
File "pb_NN.py", line 103, in get_net_and_funcs
nn_model = Models.all_models[net_name](patch_size, batch_size)
File "pb_Models.py", line 169, in model_CENTSD_33conv_elu
layer = layer_factory(in_layer=layer,layer_type='conv',**layer_params)
File "pb_Models.py", line 116, in model_CENTSD_33conv
File "/home/ms/ssingh/anaconda2/lib/python2.7/site-packages/lasagne/layers/input.py", line 56, in __init__
self.shape, name))
ValueError: Cannot create InputLayer with a non-positive shape dimension. shape=(256, 1, False, False), self.name='l_in0'
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.