ERROR:blocks.main_loop:Error occured during training.
Blocks will attempt to run `on_error` extensions, potentially saving data, before exiting and reraising the error. Note that the usual `after_training` extensions will *not* be run$
The original error will be re-raised and also stored in the training log. Press CTRL + C to halt Blocks immediately.
Traceback (most recent call last):
File "./run.py", line 652, in <module>
if train(d) is None:
File "./run.py", line 501, in train
main_loop.run()
File "/home/alexchang/ENV/local/lib/python2.7/site-packages/blocks/main_loop.py", line 197, in run
reraise_as(e)
File "/home/alexchang/ENV/local/lib/python2.7/site-packages/blocks/utils/__init__.py", line 258, in reraise_as
six.reraise(type(new_exc), new_exc, orig_exc_traceback)
File "/home/alexchang/ENV/local/lib/python2.7/site-packages/blocks/main_loop.py", line 183, in run
while self._run_epoch():
File "/home/alexchang/ENV/local/lib/python2.7/site-packages/blocks/main_loop.py", line 232, in _run_epoch
while self._run_iteration():
File "/home/alexchang/ENV/local/lib/python2.7/site-packages/blocks/main_loop.py", line 253, in _run_iteration
self.algorithm.process_batch(batch)
File "/home/alexchang/ENV/local/lib/python2.7/site-packages/blocks/algorithms/__init__.py", line 287, in process_batch
self._function(*ordered_batch)
File "/usr/local/lib/python2.7/dist-packages/theano/compile/function_module.py", line 871, in __call__
storage_map=getattr(self.fn, 'storage_map', None))
File "/usr/local/lib/python2.7/dist-packages/theano/gof/link.py", line 314, in raise_with_op
reraise(exc_type, exc_value, exc_trace)
File "/usr/local/lib/python2.7/dist-packages/theano/compile/function_module.py", line 859, in __call__
outputs = self.fn()
ValueError: The hardcoded shape for the number of rows in the image (8) isn't the run time shape (7).
Apply node that caused the error: ConvOp{('imshp', (192, 8, 8)),('kshp', (3, 3)),('nkern', 192),('bsize', 200),('dx', 1),('dy', 1),('out_mode', 'valid'),('unroll_batch', 5),('unrol$
_kern', 2),('unroll_patch', False),('imshp_logical', (192, 8, 8)),('kshp_logical', (3, 3)),('kshp_logical_top_aligned', True)}(Elemwise{Composite{(i0 + (i1 * i2))}}[(0, 2)].0, f_9_$
)
Toposort index: 1201
Inputs types: [TensorType(float32, 4D), TensorType(float32, 4D)]
Inputs shapes: [(200, 192, 7, 7), (192, 192, 3, 3)]
Inputs strides: [(37632, 196, 28, 4), (6912, 36, 12, 4)]
Inputs values: ['not shown', 'not shown']
Outputs clients: [[Subtensor{int64::}(ConvOp{('imshp', (192, 8, 8)),('kshp', (3, 3)),('nkern', 192),('bsize', 200),('dx', 1),('dy', 1),('out_mode', 'valid'),('unroll_batch', 5),('un
roll_kern', 2),('unroll_patch', False),('imshp_logical', (192, 8, 8)),('kshp_logical', (3, 3)),('kshp_logical_top_aligned', True)}.0, ScalarFromTensor.0), Subtensor{:int64:}(ConvOp{
('imshp', (192, 8, 8)),('kshp', (3, 3)),('nkern', 192),('bsize', 200),('dx', 1),('dy', 1),('out_mode', 'valid'),('unroll_batch', 5),('unroll_kern', 2),('unroll_patch', False),('imsh
p_logical', (192, 8, 8)),('kshp_logical', (3, 3)),('kshp_logical_top_aligned', True)}.0, ScalarFromTensor.0)]]
Backtrace when the node is created(use Theano flag traceback.limit=N to make it longer):
File "./run.py", line 652, in <module>
if train(d) is None:
File "./run.py", line 411, in train
ladder = setup_model(p)
File "./run.py", line 182, in setup_model
ladder.apply(x, y, x_only)
File "/home/alexchang/Course_105_1/ML/ML2016/ladder_og/ladder.py", line 203, in apply
noise_std=self.p.f_local_noise_std)
File "/home/alexchang/Course_105_1/ML/ML2016/ladder_og/ladder.py", line 185, in encoder
noise_std=noise)
File "/home/alexchang/Course_105_1/ML/ML2016/ladder_og/ladder.py", line 350, in f
z, output_size = self.f_conv(h, spec, in_dim, gen_id('W'))
File "/home/alexchang/Course_105_1/ML/ML2016/ladder_og/ladder.py", line 452, in f_conv
filter_size), border_mode=bm)
HINT: Use the Theano flag 'exception_verbosity=high' for a debugprint and storage map footprint of this apply node.
Original exception:
ValueError: The hardcoded shape for the number of rows in the image (8) isn't the run time shape (7).
Apply node that caused the error: ConvOp{('imshp', (192, 8, 8)),('kshp', (3, 3)),('nkern', 192),('bsize', 200),('dx', 1),('dy', 1),('out_mode', 'valid'),('unroll_batch', 5),('unroll
_kern', 2),('unroll_patch', False),('imshp_logical', (192, 8, 8)),('kshp_logical', (3, 3)),('kshp_logical_top_aligned', True)}(Elemwise{Composite{(i0 + (i1 * i2))}}[(0, 2)].0, f_9_W
)
Toposort index: 1201
Inputs types: [TensorType(float32, 4D), TensorType(float32, 4D)]
Inputs shapes: [(200, 192, 7, 7), (192, 192, 3, 3)]
Inputs strides: [(37632, 196, 28, 4), (6912, 36, 12, 4)]
Inputs values: ['not shown', 'not shown']
Outputs clients: [[Subtensor{int64::}(ConvOp{('imshp', (192, 8, 8)),('kshp', (3, 3)),('nkern', 192),('bsize', 200),('dx', 1),('dy', 1),('out_mode', 'valid'),('unroll_batch', 5),('un
roll_kern', 2),('unroll_patch', False),('imshp_logical', (192, 8, 8)),('kshp_logical', (3, 3)),('kshp_logical_top_aligned', True)}.0, ScalarFromTensor.0), Subtensor{:int64:}(ConvOp{
('imshp', (192, 8, 8)),('kshp', (3, 3)),('nkern', 192),('bsize', 200),('dx', 1),('dy', 1),('out_mode', 'valid'),('unroll_batch', 5),('unroll_kern', 2),('unroll_patch', False),('imsh
p_logical', (192, 8, 8)),('kshp_logical', (3, 3)),('kshp_logical_top_aligned', True)}.0, ScalarFromTensor.0)]]
Backtrace when the node is created(use Theano flag traceback.limit=N to make it longer):
File "./run.py", line 652, in <module>
if train(d) is None:
File "./run.py", line 411, in train
ladder = setup_model(p)
File "./run.py", line 182, in setup_model
ladder.apply(x, y, x_only)
File "/home/alexchang/Course_105_1/ML/ML2016/ladder_og/ladder.py", line 203, in apply
noise_std=self.p.f_local_noise_std)
File "/home/alexchang/Course_105_1/ML/ML2016/ladder_og/ladder.py", line 350, in f
z, output_size = self.f_conv(h, spec, in_dim, gen_id('W'))
File "/home/alexchang/Course_105_1/ML/ML2016/ladder_og/ladder.py", line 452, in f_conv
filter_size), border_mode=bm)
HINT: Use the Theano flag 'exception_verbosity=high' for a debugprint and storage map footprint of this apply node.
Error messages are shown below:
Do you have any idea?