Python register_specialize_device Beispiele

Beispiel #1

                 unroll_patch=None,
                 imshp_logical=imshp_logical,
                 kshp_logical=None,
                 version=-1,
                 direction_hint='bprop inputs')
    din = din(topgrad, filters)
    copy_stack_trace(node.outputs[0], din)
    din = theano.tensor.patternbroadcast(din, node.outputs[0].broadcastable)
    copy_stack_trace(node.outputs[0], din)
    return [din]


# Register Cpu Optmization
conv_groupopt = theano.gof.optdb.LocalGroupDB()
conv_groupopt.__name__ = "conv_opts"
register_specialize_device(conv_groupopt, 'fast_compile', 'fast_run')

# GEMM-based convolution
# It can be disabled by excluding 'conv_gemm'.
conv_groupopt.register('local_abstractconv_gemm', local_abstractconv_gemm, 30,
                       'conv_gemm', 'fast_compile', 'fast_run')
conv_groupopt.register('local_abstractconv_gradweight_gemm',
                       local_abstractconv_gradweight_gemm, 30, 'conv_gemm',
                       'fast_compile', 'fast_run')
conv_groupopt.register('local_abstractconv_gradinputs_gemm',
                       local_abstractconv_gradinputs_gemm, 30, 'conv_gemm',
                       'fast_compile', 'fast_run')
# Legacy convolution
conv_groupopt.register('local_conv2d_cpu', local_conv2d_cpu, 40,
                       'fast_compile', 'fast_run')
conv_groupopt.register('local_conv2d_gradweight_cpu',

Beispiel #2

Datei: opt.py Projekt: DingKe/attention-lvcsr

                 unroll_patch=None,
                 imshp_logical=imshp_logical,
                 kshp_logical=None,
                 version=-1,
                 direction_hint='bprop inputs')
    din = din(topgrad, filters)
    copy_stack_trace(node.outputs[0], din)
    din = theano.tensor.patternbroadcast(din, node.outputs[0].broadcastable)
    copy_stack_trace(node.outputs[0], din)
    return [din]


# Register Cpu Optmization
conv_groupopt = theano.gof.optdb.LocalGroupDB()
conv_groupopt.__name__ = "conv_opts"
register_specialize_device(conv_groupopt, 'fast_compile', 'fast_run')

# GEMM-based convolution
# It can be disabled by excluding 'conv_gemm'.
conv_groupopt.register('local_abstractconv_gemm', local_abstractconv_gemm, 30,
                       'conv_gemm', 'fast_compile', 'fast_run')
conv_groupopt.register('local_abstractconv_gradweight_gemm',
                       local_abstractconv_gradweight_gemm, 30,
                       'conv_gemm', 'fast_compile', 'fast_run')
conv_groupopt.register('local_abstractconv_gradinputs_gemm',
                       local_abstractconv_gradinputs_gemm, 30,
                       'conv_gemm', 'fast_compile', 'fast_run')
# Legacy convolution
conv_groupopt.register('local_conv2d_cpu', local_conv2d_cpu, 40,
                       'fast_compile', 'fast_run')
conv_groupopt.register('local_conv2d_gradweight_cpu',

Beispiel #3

    if node.op.border_mode not in ['full', 'valid']:
        return None
    if not node.op.filter_flip:
        # Not tested yet
        return None

    rval = cpu_conv2d(img,
                      kern,
                      node.op.imshp,
                      node.op.kshp,
                      border_mode=node.op.border_mode,
                      subsample=node.op.subsample)
    return [rval]


register_specialize_device(local_conv2d_cpu, 'fast_compile')


@local_optimizer([AbstractConv2d_gradWeights])
def local_conv2d_gradweight_cpu(node):

    img, topgrad, shape = node.inputs

    if ((not isinstance(img.type, TensorType)
         or not isinstance(topgrad.type, TensorType))):
        return None
    if node.op.border_mode not in ['full', 'valid']:
        return None
    if not node.op.filter_flip:
        # Not tested yet
        return

Beispiel #4

Datei: opt.py Projekt: nitish-awasthi/Theano-PyMC

        imshp_logical=imshp_logical,
        kshp_logical=None,
        version=-1,
        direction_hint="bprop inputs",
    )
    din = din(topgrad, filters)
    copy_stack_trace(node.outputs[0], din)
    din = theano.tensor.patternbroadcast(din, node.outputs[0].broadcastable)
    copy_stack_trace(node.outputs[0], din)
    return [din]


# Register Cpu Optmization
conv_groupopt = theano.gof.optdb.LocalGroupDB()
conv_groupopt.__name__ = "conv_opts"
register_specialize_device(conv_groupopt, "fast_compile", "fast_run")

# GEMM-based convolution
# It can be disabled by excluding 'conv_gemm'.
conv_groupopt.register(
    "local_abstractconv_gemm",
    local_abstractconv_gemm,
    30,
    "conv_gemm",
    "fast_compile",
    "fast_run",
)
conv_groupopt.register(
    "local_abstractconv_gradweight_gemm",
    local_abstractconv_gradweight_gemm,
    30,

Beispiel #5

Datei: abstract_conv2d.py Projekt: natehefner/Theano

    img, kern = node.inputs
    if ((not isinstance(img.type, TensorType) or
         not isinstance(kern.type, TensorType))):
        return None
    if node.op.border_mode not in ['full', 'valid']:
        return None
    if not node.op.filter_flip:
        # Not tested yet
        return None

    rval = cpu_conv2d(img, kern,
                      node.op.imshp, node.op.kshp,
                      border_mode=node.op.border_mode,
                      subsample=node.op.subsample)
    return [rval]
register_specialize_device(local_conv2d_cpu, 'fast_compile')


@local_optimizer([AbstractConv2d_gradWeights])
def local_conv2d_gradweight_cpu(node):

    img, topgrad, shape = node.inputs

    if ((not isinstance(img.type, TensorType) or
         not isinstance(topgrad.type, TensorType))):
        return None
    if node.op.border_mode not in ['full', 'valid']:
        return None
    if not node.op.filter_flip:
        # Not tested yet
        return