for m, n, k, at, bt in config:
dimA = (k,m) if at else (m,k)
dimB = (n,k) if bt else (k,n)
dimC = (m,n)
opA = 'T' if at else 'N'
opB = 'T' if bt else 'N'
op = opA + opB
dtype_data = list()
for dtype in ( np.float32, np.float16 ): #np.float32, np.float16,
A = ng.empty(dimA, dtype=dtype)
B = ng.empty(dimB, dtype=dtype)
C = ng.empty(dimC, dtype=dtype)
if at: A = A.T
if bt: B = B.T
data = matmul(A, B, C, bench=True)
# if dtype is np.float16:
# print ""
# for d in sorted(data):
# print "%7.3f %5.0f %22s %5d" % d
cublas = data.pop()
openai = sorted(data)[0]
inception = True
# find the size of the largest buffers so they can be shared
if layer.sizeF > max_weights:
max_weights = layer.sizeF
max_weight_layer = layer
if layer.sizeI > max_deltas and type(prev_layer) is not DataLayer:
max_deltas = layer.sizeI
max_delta_layer = layer
prev_layer = layer
layers.append(layer)
# Init shared buffers (assumes consistent dtype for now)
shared_deltas.append(ng.empty(max_delta_layer.dimI, dtype=max_delta_layer.dtype))
shared_deltas.append(ng.empty(max_delta_layer.dimI, dtype=max_delta_layer.dtype))
if inception:
shared_deltas.append(ng.empty(max_delta_layer.dimI, dtype=max_delta_layer.dtype))
shared_deltas.append(ng.empty(max_delta_layer.dimI, dtype=max_delta_layer.dtype))
shared_updates = ng.empty(max_weight_layer.dimF, dtype=np.float32)
for i, layer in enumerate(layers):
if verbose:
neon_logger.display(layer)
# Intitalize buffers. Alernate shared delta buffer.
# One layer can't have the same buffer for both error in and error out.
layer.init_activations()
layer.init_weights(shared=shared_updates, zeros=zeros)
dimI2 = layer.dimO
dimO = layer.dimF
opts = update_opts
func = layer.update_conv
else:
raise TypeError("Unknown Kernel Class")
if not compound:
opts = [ dict() ]
if ones:
vals = 1.0
else:
vals = (0.5 - ng.rand()) * 2
devI1 = ng.empty(dimI1, dtype=dtype)
devI2 = ng.empty(dimI2, dtype=dtype)
devO = ng.empty(dimO, dtype=dtype)
devI1[:] = vals
devI2[:] = vals
devO[:] = vals
cpuI1 = nc.array(devI1.get(), dtype=np.float64)
cpuI2 = nc.array(devI2.get(), dtype=np.float64)
cpuO = nc.array(devO.get(), dtype=np.float64)
if compound and opts is not update_opts:
devB = ng.empty((dimO[0], 1), dtype=np.float32)
devS = ng.empty((dimO[0], 1), dtype=np.float32)
devB[:] = vals
devS[:] = vals
cpuB = nc.array(devB.get(), dtype=np.float64)
dimI2 = layer.dimO
dimO = layer.dimF
opts = update_opts
func = layer.update_conv
else:
raise TypeError("Unknown Kernel Class")
if not compound:
opts = [ dict() ]
if ones:
vals = 1.0
else:
vals = (0.5 - ng.rand()) * 2
devI1 = ng.empty(dimI1, dtype=dtype)
devI2 = ng.empty(dimI2, dtype=dtype)
devO = ng.empty(dimO, dtype=dtype)
devI1[:] = vals
devI2[:] = vals
devO[:] = vals
cpuI1 = nc.array(devI1.get(), dtype=np.float64)
cpuI2 = nc.array(devI2.get(), dtype=np.float64)
cpuO = nc.array(devO.get(), dtype=np.float64)
if compound and opts is not update_opts:
devB = ng.empty((dimO[0], 1), dtype=np.float32)
devS = ng.empty((dimO[0], 1), dtype=np.float32)
devB[:] = vals
devS[:] = vals
cpuB = nc.array(devB.get(), dtype=np.float64)
