FM / operator

/usr/local/lib64/python3.6/site-packages/caffe2/python/operator_test/

/usr/local/lib64/python3.6/site-packages/caffe2/python/operator_test

Name	Size	Mode	Actions
__pycache__/	-	0755	rm
activation_ops_test.py	9691	0644	edit dl rm
adadelta_test.py	7932	0644	edit dl rm
adagrad_test.py	7586	0644	edit dl rm
adagrad_test_helper.py	5181	0644	edit dl rm
adam_test.py	21559	0644	edit dl rm
affine_channel_op_test.py	3784	0644	edit dl rm
alias_with_name_test.py	938	0644	edit dl rm
apmeter_test.py	2738	0644	edit dl rm
arg_ops_test.py	1917	0644	edit dl rm
assert_test.py	797	0644	edit dl rm
async_net_barrier_test.py	946	0644	edit dl rm
atomic_ops_test.py	4104	0644	edit dl rm
basic_rnn_test.py	4720	0644	edit dl rm
batch_box_cox_test.py	5080	0644	edit dl rm
batch_bucketize_op_test.py	3730	0644	edit dl rm
batch_moments_op_test.py	2795	0644	edit dl rm
batch_sparse_to_dense_op_test.py	4199	0644	edit dl rm
bbox_transform_test.py	12258	0644	edit dl rm
bisect_percentile_op_test.py	6227	0644	edit dl rm
blobs_queue_db_test.py	3240	0644	edit dl rm
boolean_mask_test.py	16389	0644	edit dl rm
boolean_unmask_test.py	1711	0644	edit dl rm
box_with_nms_limit_op_test.py	8750	0644	edit dl rm
bucketize_op_test.py	930	0644	edit dl rm
cast_op_test.py	1600	0644	edit dl rm
ceil_op_test.py	888	0644	edit dl rm
channel_backprop_stats_op_test.py	2131	0644	edit dl rm
channel_shuffle_test.py	1794	0644	edit dl rm
channel_stats_op_test.py	2639	0644	edit dl rm
checkpoint_test.py	1500	0644	edit dl rm
clip_op_test.py	1984	0644	edit dl rm
clip_tensor_op_test.py	2076	0644	edit dl rm
collect_and_distribute_fpn_rpn_proposals_op_test.py	11269	0644	edit dl rm
concat_op_cost_test.py	2858	0644	edit dl rm
concat_split_op_test.py	7266	0644	edit dl rm
conditional_test.py	995	0644	edit dl rm
conftest.py	1446	0644	edit dl rm
conv_test.py	32473	0644	edit dl rm
conv_transpose_test.py	15945	0644	edit dl rm
copy_ops_test.py	7374	0644	edit dl rm
copy_rows_to_tensor_op_test.py	2526	0644	edit dl rm
cosine_embedding_criterion_op_test.py	1953	0644	edit dl rm
counter_ops_test.py	3348	0644	edit dl rm
crf_test.py	5315	0644	edit dl rm
cross_entropy_ops_test.py	10085	0644	edit dl rm
ctc_beam_search_decoder_op_test.py	5197	0644	edit dl rm
ctc_greedy_decoder_op_test.py	4743	0644	edit dl rm
cudnn_recurrent_test.py	5817	0644	edit dl rm
dataset_ops_test.py	23847	0644	edit dl rm
data_couple_op_test.py	858	0644	edit dl rm
decay_adagrad_test.py	2694	0644	edit dl rm
deform_conv_test.py	19276	0644	edit dl rm
dense_vector_to_id_list_op_test.py	2044	0644	edit dl rm
depthwise_3x3_conv_test.py	1863	0644	edit dl rm
detectron_keypoints.py	7973	0644	edit dl rm
distance_op_test.py	4351	0644	edit dl rm
dropout_op_test.py	2971	0644	edit dl rm
duplicate_operands_test.py	734	0644	edit dl rm
elementwise_linear_op_test.py	1382	0644	edit dl rm
elementwise_logical_ops_test.py	4617	0644	edit dl rm
elementwise_ops_test.py	33354	0644	edit dl rm
elementwise_op_broadcast_test.py	17466	0644	edit dl rm
emptysample_ops_test.py	1977	0644	edit dl rm
enforce_finite_op_test.py	1286	0644	edit dl rm
ensure_clipped_test.py	1505	0644	edit dl rm
ensure_cpu_output_op_test.py	1244	0644	edit dl rm
erf_op_test.py	749	0644	edit dl rm
expand_op_test.py	2109	0644	edit dl rm
fc_operator_test.py	3720	0644	edit dl rm
feature_maps_ops_test.py	21492	0644	edit dl rm
filler_ops_test.py	8476	0644	edit dl rm
find_op_test.py	1316	0644	edit dl rm
flatten_op_test.py	922	0644	edit dl rm
flexible_top_k_test.py	2609	0644	edit dl rm
floor_op_test.py	894	0644	edit dl rm
fused_nbit_rowwise_conversion_ops_test.py	14077	0644	edit dl rm
fused_nbit_rowwise_test_helper.py	2693	0644	edit dl rm
gather_ops_test.py	9216	0644	edit dl rm
gather_ranges_op_test.py	9125	0644	edit dl rm
given_tensor_byte_string_to_uint8_fill_op_test.py	1392	0644	edit dl rm
given_tensor_fill_op_test.py	1503	0644	edit dl rm
glu_op_test.py	1212	0644	edit dl rm
group_conv_test.py	2870	0644	edit dl rm
group_norm_op_test.py	5252	0644	edit dl rm
gru_test.py	12932	0644	edit dl rm
heatmap_max_keypoint_op_test.py	4770	0644	edit dl rm
histogram_test.py	3097	0644	edit dl rm
hsm_test.py	9456	0644	edit dl rm
hyperbolic_ops_test.py	1472	0644	edit dl rm
im2col_col2im_test.py	4311	0644	edit dl rm
image_input_op_test.py	17345	0644	edit dl rm
index_hash_ops_test.py	2885	0644	edit dl rm
index_ops_test.py	4597	0644	edit dl rm
instance_norm_test.py	9917	0644	edit dl rm
integral_image_ops_test.py	3419	0644	edit dl rm
jsd_ops_test.py	1044	0644	edit dl rm
key_split_ops_test.py	1289	0644	edit dl rm
lars_test.py	1354	0644	edit dl rm
layer_norm_op_test.py	14983	0644	edit dl rm
leaky_relu_test.py	5639	0644	edit dl rm
learning_rate_adaption_op_test.py	2837	0644	edit dl rm
learning_rate_op_test.py	8652	0644	edit dl rm
lengths_pad_op_test.py	1625	0644	edit dl rm
lengths_reducer_fused_nbit_rowwise_ops_test.py	15495	0644	edit dl rm
lengths_tile_op_test.py	1332	0644	edit dl rm
lengths_top_k_ops_test.py	2371	0644	edit dl rm
length_split_op_test.py	4868	0644	edit dl rm
listwise_l2r_operator_test.py	8740	0644	edit dl rm
load_save_test.py	33241	0644	edit dl rm
locally_connected_op_test.py	7761	0644	edit dl rm
loss_ops_test.py	902	0644	edit dl rm
lpnorm_op_test.py	2725	0644	edit dl rm
map_ops_test.py	2249	0644	edit dl rm
margin_ranking_criterion_op_test.py	1816	0644	edit dl rm
math_ops_test.py	1603	0644	edit dl rm
matmul_op_test.py	10096	0644	edit dl rm
mean_op_test.py	1469	0644	edit dl rm
merge_id_lists_op_test.py	2989	0644	edit dl rm
mkl_conv_op_test.py	1547	0644	edit dl rm
mkl_packed_fc_op_test.py	2647	0644	edit dl rm
mod_op_test.py	1459	0644	edit dl rm
moments_op_test.py	1722	0644	edit dl rm
momentum_sgd_test.py	6480	0644	edit dl rm
mpi_test.py	8154	0644	edit dl rm
mul_gradient_benchmark.py	1509	0644	edit dl rm
negate_gradient_op_test.py	1518	0644	edit dl rm
ngram_ops_test.py	2327	0644	edit dl rm
normalize_op_test.py	1679	0644	edit dl rm
numpy_tile_op_test.py	1924	0644	edit dl rm
one_hot_ops_test.py	7478	0644	edit dl rm
onnx_while_test.py	3070	0644	edit dl rm
order_switch_test.py	1306	0644	edit dl rm
pack_ops_test.py	12634	0644	edit dl rm
pack_rnn_sequence_op_test.py	2891	0644	edit dl rm
pad_test.py	1377	0644	edit dl rm
partition_ops_test.py	6838	0644	edit dl rm
percentile_op_test.py	4427	0644	edit dl rm
piecewise_linear_transform_test.py	6187	0644	edit dl rm
pooling_test.py	16508	0644	edit dl rm
prepend_dim_test.py	1505	0644	edit dl rm
python_op_test.py	1312	0644	edit dl rm
quantile_test.py	3276	0644	edit dl rm
rand_quantization_op_speed_test.py	3128	0644	edit dl rm
rank_loss_operator_test.py	5752	0644	edit dl rm
rebatching_queue_test.py	9047	0644	edit dl rm
record_queue_test.py	3125	0644	edit dl rm
recurrent_network_test.py	14048	0644	edit dl rm
recurrent_net_executor_test.py	10922	0644	edit dl rm
reduce_ops_test.py	17341	0644	edit dl rm
reduction_ops_test.py	4664	0644	edit dl rm
reshape_ops_test.py	8211	0644	edit dl rm
resize_op_test.py	9417	0644	edit dl rm
rmac_regions_op_test.py	3178	0644	edit dl rm
rms_norm_op_test.py	1325	0644	edit dl rm
rnn_cell_test.py	59707	0644	edit dl rm
roi_align_rotated_op_test.py	7567	0644	edit dl rm
rowwise_counter_test.py	2205	0644	edit dl rm
scale_op_test.py	2177	0644	edit dl rm
segment_ops_test.py	25745	0644	edit dl rm
self_binning_histogram_test.py	12915	0644	edit dl rm
selu_op_test.py	3232	0644	edit dl rm
sequence_ops_test.py	16000	0644	edit dl rm
shape_inference_test.py	25708	0644	edit dl rm
sinusoid_position_encoding_op_test.py	2308	0644	edit dl rm
softmax_ops_test.py	23685	0644	edit dl rm
softplus_op_test.py	516	0644	edit dl rm
sparse_dropout_with_replacement_op_test.py	2885	0644	edit dl rm
sparse_gradient_checker_test.py	1294	0644	edit dl rm
sparse_itemwise_dropout_with_replacement_op_test.py	2913	0644	edit dl rm
sparse_lengths_sum_benchmark.py	4159	0644	edit dl rm
sparse_lp_regularizer_test.py	2553	0644	edit dl rm
sparse_normalize_test.py	3136	0644	edit dl rm
sparse_ops_test.py	3469	0644	edit dl rm
sparse_to_dense_mask_op_test.py	3693	0644	edit dl rm
spatial_bn_op_test.py	20182	0644	edit dl rm
specialized_segment_ops_test.py	11775	0644	edit dl rm
split_op_cost_test.py	8645	0644	edit dl rm
square_root_divide_op_test.py	2179	0644	edit dl rm
stats_ops_test.py	1789	0644	edit dl rm
stats_put_ops_test.py	6596	0644	edit dl rm
storm_test.py	6507	0644	edit dl rm
string_ops_test.py	4154	0644	edit dl rm
text_file_reader_test.py	2517	0644	edit dl rm
thresholded_relu_op_test.py	2323	0644	edit dl rm
tile_op_test.py	3887	0644	edit dl rm
top_k_test.py	9113	0644	edit dl rm
torch_integration_test.py	39941	0644	edit dl rm
transpose_op_test.py	2722	0644	edit dl rm
trigonometric_op_test.py	1715	0644	edit dl rm
unique_ops_test.py	2255	0644	edit dl rm
unique_uniform_fill_op_test.py	1335	0644	edit dl rm
unsafe_coalesce_test.py	2940	0644	edit dl rm
upsample_op_test.py	7308	0644	edit dl rm
utility_ops_test.py	15054	0644	edit dl rm
video_input_op_test.py	10503	0644	edit dl rm
weighted_multi_sample_test.py	1997	0644	edit dl rm
weighted_sample_test.py	2739	0644	edit dl rm
weighted_sum_test.py	3052	0644	edit dl rm
weight_scale_test.py	2057	0644	edit dl rm
wngrad_test.py	8279	0644	edit dl rm
__init__.py	0	0644	edit dl rm

Edit: /usr/local/lib64/python3.6/site-packages/caffe2/python/operator_test/layer_norm_op_test.py (14983B)

from caffe2.python import brew, core, workspace
from caffe2.python.model_helper import ModelHelper
from functools import partial
from hypothesis import given, settings
from typing import Optional, Tuple

import caffe2.python.hypothesis_test_util as hu
import caffe2.python.serialized_test.serialized_test_util as serial
import hypothesis.strategies as st

import numpy as np
import torch

import unittest

def _layer_norm_ref(axis, epsilon, X):
    left = int(np.prod(X.shape[:axis]))
    reshaped = np.reshape(X, [left, -1])
    mean = np.mean(reshaped, axis=1).reshape([left, 1])
    std = np.sqrt(np.mean(np.square(reshaped), axis=1).reshape(
        [left, 1]) - np.square(mean) + epsilon)
    Y = (reshaped - mean) / (std)
    Y = np.reshape(Y, X.shape)
    mean = np.reshape(mean, X.shape[:axis] + (1,))
    std = np.reshape(std, X.shape[:axis] + (1,))
    return (Y, mean, std)

def _layer_norm_with_affine_ref(axis, epsilon, X, gamma, beta):
    Y, mean, std = _layer_norm_ref(axis, epsilon, X)
    Y = Y * gamma + beta
    return (Y, mean, std)

def _layer_norm_grad_ref(axis, gout_full, norm, mean_full, stdev_full, X_full):
    left = int(np.prod(X_full.shape[:axis]))
    right = int(np.prod(X_full.shape[axis:]))
    X = np.reshape(X_full, [left, right])
    stdev = np.reshape(stdev_full, [left, 1])
    mean = np.reshape(mean_full, [left, 1])
    gout = np.reshape(gout_full, [left, right])
    dstdev_end = (-1.0) / np.power(stdev, 2.0) \
        * np.sum((X - mean) * gout, axis=1).reshape([left, 1])
    dmean_end = np.sum(-1.0 / stdev * gout, axis=1).reshape([left, 1])
    dx_end = 1.0 / stdev * gout

# stdev block
    dmean_stdev = -1.0 * mean / stdev * dstdev_end
    dx_stdev = X / (right * stdev) * dstdev_end

# mean block
    dmean = dmean_end + dmean_stdev
    dxmean = (1.0 / right) * dmean

# final outputs
    dx = dx_end + dx_stdev + dxmean
    dx = dx.reshape(X_full.shape)

return [dx]

class TestLayerNormOp(serial.SerializedTestCase):
    @given(X=hu.tensor(min_dim=2), **hu.gcs)
    @settings(deadline=10000)
    def test_layer_norm_grad_op(self, X, gc, dc):
        axis = np.random.randint(0, len(X.shape))
        epsilon = 1e-4
        op = core.CreateOperator(
            "LayerNormGradient",
            ["gout", "out", "mean", "stdev", "in"],
            ["gin"],
            axis=axis,
            epsilon=epsilon,
        )

norm, mean, stdev = _layer_norm_ref(axis, epsilon, X)
        gout = norm

self.assertReferenceChecks(
            device_option=gc,
            op=op,
            inputs=[gout, norm, mean, stdev, X],
            reference=partial(_layer_norm_grad_ref, axis)
        )
        self.assertDeviceChecks(
            device_options=dc,
            op=op,
            inputs=[gout, norm, mean, stdev, X],
            outputs_to_check=[0],
        )

@given(X=hu.tensor(min_dim=2),
           eps=st.floats(1e-5, 1e-3),
           elementwise_affine=st.booleans(),
           **hu.gcs)
    def test_layer_norm_op(self, X, eps, elementwise_affine, gc, dc):
        axis = np.random.randint(0, len(X.shape))

op = core.CreateOperator(
            "LayerNorm",
            ["X", "gamma", "beta"] if elementwise_affine else ["X"],
            ["Y", "mean", "std"],
            axis=axis,
            epsilon=eps,
            elementwise_affine=elementwise_affine,
        )

if elementwise_affine:
            ref = partial(_layer_norm_with_affine_ref, axis, eps)
        else:
            ref = partial(_layer_norm_ref, axis, eps)

if elementwise_affine:
            gamma = np.random.randn(*X.shape[axis:]).astype(np.float32)
            beta = np.random.randn(*X.shape[axis:]).astype(np.float32)
            inputs = [X, gamma, beta]
        else:
            inputs = [X]

self.assertReferenceChecks(
            device_option=gc,
            op=op,
            inputs=inputs,
            reference=ref,
        )
        self.assertDeviceChecks(
            device_options=dc,
            op=op,
            inputs=inputs,
            outputs_to_check=[0, 1, 2],
        )

@given(M=st.integers(1, 10),
           N=st.integers(10, 20),
           axis=st.integers(0, 1),
           eps=st.floats(1e-5, 1e-3),
           elementwise_affine=st.booleans(),
           **hu.gcs)
    @settings(deadline=10000)
    def test_layer_norm_grad(
            self, M, N, axis, eps, elementwise_affine, gc, dc):
        op = core.CreateOperator(
            "LayerNorm",
            ["X", "gamma", "beta"] if elementwise_affine else ["X"],
            ["Y", "mean", "std"],
            axis=axis,
            epsilon=eps,
            elementwise_affine=elementwise_affine,
        )

X = np.arange(M * N).astype(np.float32)
        np.random.shuffle(X)
        X = X.reshape((M, N))
        if elementwise_affine:
            gamma = np.random.randn(*X.shape[axis:]).astype(np.float32)
            beta = np.random.randn(*X.shape[axis:]).astype(np.float32)
            inputs = [X, gamma, beta]
        else:
            inputs = [X]

for i in range(len(inputs)):
            self.assertGradientChecks(gc, op, inputs, i, [0])

@unittest.skipIf(workspace.has_hip_support,
                     "Operator cross-calling doesn't work with hip yet")
    @given(X=hu.tensor(min_dim=2),
           eps=st.floats(1e-5, 1e-3),
           elementwise_affine=st.booleans(),
           **hu.gcs)
    @settings(deadline=10000)
    def test_layer_norm_op_c10(self, X, eps, elementwise_affine, gc, dc):
        axis = np.random.randint(0, len(X.shape))

op = core.CreateOperator(
            "C10LayerNorm_DontUseThisOpYet",
            ["X", "gamma", "beta"] if elementwise_affine else ["X"],
            ["Y", "mean", "std"],
            axis=axis,
            epsilon=eps,
            elementwise_affine=elementwise_affine,
        )

if elementwise_affine:
            ref = partial(_layer_norm_with_affine_ref, axis, eps)
        else:
            ref = partial(_layer_norm_ref, axis, eps)

@unittest.skipIf(workspace.has_hip_support,
                     "Operator cross-calling doesn't work with hip yet")
    @given(X=hu.tensor(min_dim=2),
           eps=st.floats(1e-5, 1e-3),
           elementwise_affine=st.booleans(),
           **hu.gcs)
    def test_layer_norm_op_c10_preallocated_outputs(
            self, X, eps, elementwise_affine, gc, dc):
        # This test case ensures that it works correctly when output tensors are
        # preallocated.
        axis = np.random.randint(0, len(X.shape))

self.ws.create_blob("X").feed(X)
        if elementwise_affine:
            gamma = np.random.randn(*X.shape[axis:]).astype(np.float32)
            beta = np.random.randn(*X.shape[axis:]).astype(np.float32)
            self.ws.create_blob("gamma").feed(gamma)
            self.ws.create_blob("beta").feed(beta)

m = ModelHelper(name="test")
        m.net.C10LayerNorm_DontUseThisOpYet(
            ["X", "gamma", "beta"] if elementwise_affine else ["X"],
            ["Y", "mean", "std"],
            axis=axis,
            epsilon=eps,
            elementwise_affine=elementwise_affine,
        )
        self.ws.create_net(m.param_init_net).run()
        net = self.ws.create_net(m.net)
        # run two times to be extra sure that the outputs are preallocated
        net.run()
        net.run()

if elementwise_affine:
            expected_norm, expected_mean, expected_std = \
                _layer_norm_with_affine_ref(axis, eps, X, gamma, beta)
        else:
            expected_norm, expected_mean, expected_std = _layer_norm_ref(
                axis, eps, X)
        actual_norm = self.ws.fetch_blob('Y')
        actual_mean = self.ws.fetch_blob('mean')
        actual_std = self.ws.fetch_blob('std')

torch.testing.assert_allclose(
            expected_norm, actual_norm, rtol=1e-4, atol=1e-4)
        torch.testing.assert_allclose(expected_mean, actual_mean)
        torch.testing.assert_allclose(expected_std, actual_std)

@given(X=hu.tensor(min_dim=2),
           eps=st.floats(1e-5, 1e-3),
           elementwise_affine=st.booleans(),
           **hu.gcs)
    def test_layer_norm_op_pytorch(self, X, eps, elementwise_affine, gc, dc):
        axis = np.random.randint(0, len(X.shape))

if elementwise_affine:
            gamma = np.random.randn(*X.shape[axis:]).astype(np.float32)
            beta = np.random.randn(*X.shape[axis:]).astype(np.float32)
            expected_norm, expected_mean, expected_std = \
                _layer_norm_with_affine_ref(axis, eps, X, gamma, beta)
            actual_norm, actual_mean, actual_std = torch.ops._caffe2.LayerNorm(
                torch.tensor(X), torch.tensor(gamma), torch.tensor(beta),
                axis, eps, True)
        else:
            expected_norm, expected_mean, expected_std = _layer_norm_ref(
                axis, eps, X)
            actual_norm, actual_mean, actual_std = torch.ops._caffe2.LayerNorm(
                torch.tensor(X), None, None, axis, eps)

# Test case is using workspace.has_cuda_support and not
    # workspace.has_gpu_support to exclude it from HIP because tensor interop
    # doesn't work for HIP tensors yet
    @unittest.skipIf(not workspace.has_cuda_support, "No cuda support")
    @given(X=hu.tensor(min_dim=2),
           eps=st.floats(1e-5, 1e-3),
           elementwise_affine=st.booleans())
    def test_layer_norm_op_pytorch_cuda(self, X, eps, elementwise_affine):
        axis = np.random.randint(0, len(X.shape))

if elementwise_affine:
            gamma = np.random.randn(*X.shape[axis:]).astype(np.float32)
            beta = np.random.randn(*X.shape[axis:]).astype(np.float32)
            expected_norm, expected_mean, expected_std = \
                _layer_norm_with_affine_ref(axis, eps, X, gamma, beta)
            actual_norm, actual_mean, actual_std = torch.ops._caffe2.LayerNorm(
                torch.tensor(X).cuda(),
                torch.tensor(gamma).cuda(),
                torch.tensor(beta).cuda(),
                axis,
                eps,
                True)
        else:
            expected_norm, expected_mean, expected_std = _layer_norm_ref(
                axis, eps, X)
            actual_norm, actual_mean, actual_std = torch.ops._caffe2.LayerNorm(
                torch.tensor(X).cuda(), None, None, axis, eps)

torch.testing.assert_allclose(
            expected_norm, actual_norm.cpu(), rtol=1e-4, atol=1e-4)
        torch.testing.assert_allclose(expected_mean, actual_mean.cpu())
        torch.testing.assert_allclose(expected_std, actual_std.cpu())

@given(X=hu.tensor(min_dim=2),
           eps=st.floats(1e-5, 1e-3),
           elementwise_affine=st.booleans(),
           **hu.gcs)
    @settings(deadline=10000)
    def test_layer_norm_op_jit(self, X, eps, elementwise_affine, gc, dc):
        @torch.jit.script
        def jit_layer_norm(
                X: torch.Tensor,
                gamma: Optional[torch.Tensor] = None,
                beta: Optional[torch.Tensor] = None,
                axis: int = 1,
                eps: float = 1e-5,
                elementwise_affine: bool = False,
        ) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
            return torch.ops._caffe2.LayerNorm(
                X, gamma, beta, axis, eps, elementwise_affine)

axis = np.random.randint(0, len(X.shape))

if elementwise_affine:
            gamma = np.random.randn(*X.shape[axis:]).astype(np.float32)
            beta = np.random.randn(*X.shape[axis:]).astype(np.float32)
            expected_norm, expected_mean, expected_std = \
                _layer_norm_with_affine_ref(axis, eps, X, gamma, beta)
            actual_norm, actual_mean, actual_std = jit_layer_norm(
                torch.tensor(X), torch.tensor(gamma), torch.tensor(beta),
                axis, eps, elementwise_affine)
        else:
            expected_norm, expected_mean, expected_std = _layer_norm_ref(
                axis, eps, X)
            actual_norm, actual_mean, actual_std = jit_layer_norm(
                torch.tensor(X), None, None, axis, eps, elementwise_affine)

@given(X=hu.tensor(min_dim=2), **hu.gcs)
    def test_layer_norm_brew_wrapper(self, X, gc, dc):
        axis = np.random.randint(0, len(X.shape))
        scale_dim = [1] * np.ndim(X)
        scale_dim[axis] = X.shape[axis]

self.ws.create_blob('input').feed(X)

model = ModelHelper(name='test_layer_norm_brew_wrapper')
        brew.layer_norm(
            model,
            'input',
            'output',
            dim_in=X.shape[axis:],
            axis=axis,
            epsilon=1e-4,
        )

self.ws.create_net(model.param_init_net).run()
        self.ws.create_net(model.net).run()

@given(N=st.integers(1, 10), elementwise_affine=st.booleans(), **hu.gcs)
    @settings(deadline=None)
    def test_layer_norm_with_empty_batch(self, N, elementwise_affine, gc, dc):
        X = np.random.randn(0, N).astype(np.float32)
        gamma = np.random.rand(N).astype(np.float32)
        beta = np.random.rand(N).astype(np.float32)

op = core.CreateOperator(
            "LayerNorm",
            ["X", "gamma", "beta"] if elementwise_affine else ["X"],
            ["Y", "mean", "sigma"],
            elementwise_affine=elementwise_affine,
        )

def ref(X, gamma=None, beta=None):
            Y = np.zeros_like(X)
            axis = 1
            mean = np.zeros(X.shape[:axis] + (1,), dtype=X.dtype)
            sigma = np.zeros(X.shape[:axis] + (1,), dtype=X.dtype)
            return Y, mean, sigma

inputs = [X, gamma, beta] if elementwise_affine else [X]
        self.assertReferenceChecks(gc, op, inputs, ref)
        self.assertDeviceChecks(dc, op, inputs, [0, 1])
        for i in range(len(inputs)):
            self.assertGradientChecks(gc, op, inputs, i, [0])

if __name__ == "__main__":
    unittest.main()

cmd: