BD + ABC bug (Pytensor input shape) #7
Description
Here's another one.
Config,
model:
name: BirthDeathPoisson
config:
n_init: 1000
Nact: 1000
Ninact: 1000
max_pop: 100000
# Ground truth for scoring and generation
params:
LDA: 0.0
lda: 0.009
gamma: 0.000
mu: 0.003
inference:
name: PyMC
config:
draws: 5
chains: 4
random_seed: 42
epsilon: 1
sum_stat: "identity"
distance: "gaussian"Result:
BirthDeathPoisson
Initializing SMC sampler...
Sampling 4 chains in 4 jobs
Chain 0 ⠼ -:--:-- / 0:00:43 Stage: 0 Beta: 0
Chain 1 ⠴ -:--:-- / 0:00:43 Stage: 0 Beta: 0
Chain 0 ⠴ -:--:-- / 0:00:47 Stage: 0 Beta: 0
Chain 1 ⠴ -:--:-- / 0:00:47 Stage: 0 Beta: 0
Chain 0 ⠏ -:--:-- / 0:00:54 Stage: 0 Beta: 0
Chain 1 ⠏ -:--:-- / 0:00:54 Stage: 0 Beta: 0
Chain 0 ⠸ -:--:-- / 0:00:54 Stage: 0 Beta: 0
Chain 1 ⠸ -:--:-- / 0:00:54 Stage: 0 Beta: 0
Chain 0 ⠼ -:--:-- / 0:00:54 Stage: 0 Beta: 0
Chain 1 ⠼ -:--:-- / 0:00:54 Stage: 0 Beta: 0
Chain 2 ⠼ -:--:-- / 0:00:54 Stage: 0 Beta: 0
Chain 3 ⠼ -:--:-- / 0:00:54 Stage: 0 Beta: 0
concurrent.futures.process._RemoteTraceback:
"""
Traceback (most recent call last):
File "simMAtree/env/lib/python3.12/site-packages/pytensor/compile/function/types.py", line 1037, in __call__
outputs = vm() if output_subset is None else vm(output_subset=output_subset)
^^^^
ValueError: Input dimension mismatch: (input[%i].shape[%i] = %lld, input[%i].shape[%i] = %lld)
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/usr/lib/python3.12/concurrent/futures/process.py", line 264, in _process_worker
r = call_item.fn(*call_item.args, **call_item.kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "simMAtree/env/lib/python3.12/site-packages/pymc/smc/sampling.py", line 316, in _sample_smc_int
smc._initialize_kernel()
File "simMAtree/env/lib/python3.12/site-packages/pymc/smc/kernels.py", line 253, in _initialize_kernel
likelihoods = [self.likelihood_logp_func(sample) for sample in self.tempered_posterior]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "simMAtree/env/lib/python3.12/site-packages/pytensor/compile/function/types.py", line 1047, in __call__
raise_with_op(
File "simMAtree/env/lib/python3.12/site-packages/pytensor/link/utils.py", line 526, in raise_with_op
raise exc_value.with_traceback(exc_trace)
File "simMAtree/env/lib/python3.12/site-packages/pytensor/compile/function/types.py", line 1037, in __call__
outputs = vm() if output_subset is None else vm(output_subset=output_subset)
^^^^
ValueError: Input dimension mismatch: (input[%i].shape[%i] = %lld, input[%i].shape[%i] = %lld)
Apply node that caused the error: Composite{sqr((i0 - i1))}(s{[1.8520000 ... 85965e-01]}, Simulator_s_rv{"(),(),()->()"}.out)
Toposort index: 8
Inputs types: [TensorType(float64, shape=(13,)), TensorType(float64, shape=(13,))]
Inputs shapes: [(13,), (6,)]
Inputs strides: [(8,), (8,)]
Inputs values: ['not shown', 'not shown']
Outputs clients: [[Sum{axes=None}(Composite{sqr((i0 - i1))}.0)]]
HINT: Re-running with most PyTensor optimizations disabled could provide a back-trace showing when this node was created. This can be done by setting the PyTensor flag 'optimizer=fast_compile'. If that does not work, PyTensor optimizations can be disabled with 'optimizer=None'.
HINT: Use the PyTensor flag `exception_verbosity=high` for a debug print-out and storage map footprint of this Apply node.
"""
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "simMAtree/env/bin/simmatree", line 8, in <module>
sys.exit(cli())
^^^^^
File "simMAtree/env/lib/python3.12/site-packages/click/core.py", line 1442, in __call__
return self.main(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "simMAtree/env/lib/python3.12/site-packages/click/core.py", line 1363, in main
rv = self.invoke(ctx)
^^^^^^^^^^^^^^^^
File "simMAtree/env/lib/python3.12/site-packages/click/core.py", line 1830, in invoke
return _process_result(sub_ctx.command.invoke(sub_ctx))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "simMAtree/env/lib/python3.12/site-packages/click/core.py", line 1226, in invoke
return ctx.invoke(self.callback, **ctx.params)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "simMAtree/env/lib/python3.12/site-packages/click/core.py", line 794, in invoke
return callback(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "simMAtree/env/lib/python3.12/site-packages/click/decorators.py", line 46, in new_func
return f(get_current_context().obj, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "simMAtree/env/lib/python3.12/site-packages/src/__main__.py", line 47, in infer_command
inference(
File "simMAtree/env/lib/python3.12/site-packages/src/cli/inference.py", line 47, in inference
inference_data = backend.run_inference(model=model, data=stats)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "simMAtree/env/lib/python3.12/site-packages/src/inference/pymc_backend.py", line 58, in run_inference
idata = pm.sample_smc(
^^^^^^^^^^^^^^
File "simMAtree/env/lib/python3.12/site-packages/pymc/smc/sampling.py", line 193, in sample_smc
results = run_chains(chains, progressbar, params, random_seed, kernel_kwargs, cores)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "simMAtree/env/lib/python3.12/site-packages/pymc/smc/sampling.py", line 405, in run_chains
return tuple(cloudpickle.loads(r.result()) for r in done)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "simMAtree/env/lib/python3.12/site-packages/pymc/smc/sampling.py", line 405, in <genexpr>
return tuple(cloudpickle.loads(r.result()) for r in done)
^^^^^^^^^^
File "/usr/lib/python3.12/concurrent/futures/_base.py", line 449, in result
return self.__get_result()
^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/concurrent/futures/_base.py", line 401, in __get_result
raise self._exception
ValueError: Input dimension mismatch: (input[%i].shape[%i] = %lld, input[%i].shape[%i] = %lld)
Apply node that caused the error: Composite{sqr((i0 - i1))}(s{[1.8520000 ... 85965e-01]}, Simulator_s_rv{"(),(),()->()"}.out)
Toposort index: 8
Inputs types: [TensorType(float64, shape=(13,)), TensorType(float64, shape=(13,))]
Inputs shapes: [(13,), (6,)]
Inputs strides: [(8,), (8,)]
Inputs values: ['not shown', 'not shown']
Outputs clients: [[Sum{axes=None}(Composite{sqr((i0 - i1))}.0)]]
HINT: Re-running with most PyTensor optimizations disabled could provide a back-trace showing when this node was created. This can be done by setting the PyTensor flag 'optimizer=fast_compile'. If that does not work, PyTensor optimizations can be disabled with 'optimizer=None'.
HINT: Use the PyTensor flag `exception_verbosity=high` for a debug print-out and storage map footprint of this Apply node.