The patchbatch from dedigadot

patchbatch's People

Contributors

Stargazers

Watchers

patchbatch's Issues

running benchmark_kitti.py

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'

Recommend Projects