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/adam_test.py (21559B)

import functools

import hypothesis
from hypothesis import given
import hypothesis.strategies as st
import numpy as np

from caffe2.python import core
import caffe2.python.hypothesis_test_util as hu

class TestAdam(hu.HypothesisTestCase):

@staticmethod
    def ref_adam(param, mom1, mom2, grad, LR, ITER,
                 beta1, beta2, epsilon, output_grad=False):
        t = ITER + 1
        corrected_local_rate = np.sqrt(1 - np.power(beta2, t)) / \
            (1 - np.power(beta1, t))
        mom1_out = (beta1 * mom1) + (1 - beta1) * grad
        mom2_out = (beta2 * mom2) + (1 - beta2) * np.square(grad)
        grad_out = corrected_local_rate * mom1_out / \
            (np.sqrt(mom2_out) + epsilon)
        param_out = param + LR * grad_out
        if output_grad:
            return param_out, mom1_out, mom2_out, grad_out
        else:
            return param_out, mom1_out, mom2_out

@staticmethod
    def ref_smart_decay_adam(param, mom1, mom2, last_seen, grad, LR, ITER,
                             beta1, beta2, epsilon):

for name in ('param', 'mom1', 'mom2', 'last_seen', 'grad',
                     'LR', 'ITER', 'beta1', 'beta2', 'epsilon'):
            print("{} {} {}".format(name, locals()['name'], type(locals()['name'])))

t = ITER + 1
        k = t - last_seen
        k = k.flatten()[0]

last_seen_out = t * np.ones_like(last_seen)

# Make up for lost minibatches.
        mom2_out = (beta2**k * mom2) + (1 - beta2) * np.square(grad)
        param_out = param
        mom1_out = mom1

# For catchup
        assert k >= 1
        for i in range(k):
            mom1_out *= beta1
            if i == k - 1:
                mom1_out += grad * (1 - beta1)
            param_out += LR * mom1_out / (np.sqrt(mom2_out) + epsilon)
        grad_out = mom1_out / (np.sqrt(mom2_out) + epsilon)

return param_out, mom1_out, mom2_out, last_seen_out

@staticmethod
    def ref_row_wise_adam(param, mom1, mom2, grad, LR, ITER,
                          beta1, beta2, epsilon, output_grad=False):
        t = ITER + 1
        corrected_local_rate = np.sqrt(1 - np.power(beta2, t)) / \
            (1 - np.power(beta1, t))
        mom1_out = (beta1 * mom1) + (1 - beta1) * grad
        mom2_out = (beta2 * mom2) + (1 - beta2) * np.mean(np.square(grad))
        grad_out = corrected_local_rate * mom1_out / (np.sqrt(mom2_out) + epsilon)
        param_out = param + LR * grad_out
        if output_grad:
            return param_out, mom1_out, mom2_out, grad_out
        else:
            return param_out, mom1_out, mom2_out

@given(inputs=hu.tensors(n=4),
           ITER=st.integers(min_value=0, max_value=10000),
           LR=st.floats(min_value=0.01, max_value=0.99,
                        allow_nan=False, allow_infinity=False),
           beta1=st.floats(min_value=0.01, max_value=0.99,
                           allow_nan=False, allow_infinity=False),
           beta2=st.floats(min_value=0.01, max_value=0.99,
                           allow_nan=False, allow_infinity=False),
           epsilon=st.floats(min_value=0.01, max_value=0.99,
                             allow_nan=False, allow_infinity=False),
           **hu.gcs)
    def test_adam(self, inputs, ITER, LR, beta1, beta2, epsilon, gc, dc):
        param, mom1, mom2, grad = inputs
        mom2 = np.abs(mom2)
        ITER = np.array([ITER], dtype=np.int64)
        LR = np.array([LR], dtype=np.float32)

op = core.CreateOperator(
            "Adam",
            ["param", "mom1", "mom2", "grad", "lr", "iter"],
            ["output_param", "output_mom1", "output_mom2"],
            beta1=beta1, beta2=beta2, epsilon=epsilon)

# Iter lives on the CPU
        input_device_options = {'iter': hu.cpu_do}

self.assertReferenceChecks(
            gc, op,
            [param, mom1, mom2, grad, LR, ITER],
            functools.partial(
                self.ref_adam,
                beta1=beta1, beta2=beta2, epsilon=epsilon),
            input_device_options=input_device_options)

@given(inputs=hu.tensors(n=4),
           ITER=st.integers(min_value=0, max_value=10000),
           LR=st.floats(min_value=0.01, max_value=0.99,
                        allow_nan=False, allow_infinity=False),
           beta1=st.floats(min_value=0.01, max_value=0.99,
                           allow_nan=False, allow_infinity=False),
           beta2=st.floats(min_value=0.01, max_value=0.99,
                           allow_nan=False, allow_infinity=False),
           epsilon=st.floats(min_value=0.01, max_value=0.99,
                             allow_nan=False, allow_infinity=False),
           **hu.gcs_cpu_only)
    def test_adam_output_grad(self, inputs, ITER, LR, beta1, beta2, epsilon, gc, dc):
        param, mom1, mom2, grad = inputs
        mom2 = np.abs(mom2)
        ITER = np.array([ITER], dtype=np.int64)
        LR = np.array([LR], dtype=np.float32)

op = core.CreateOperator(
            "Adam",
            ["param", "mom1", "mom2", "grad", "lr", "iter"],
            ["output_param", "output_mom1", "output_mom2", "output_grad"],
            beta1=beta1, beta2=beta2, epsilon=epsilon)

# Iter lives on the CPU
        input_device_options = {'iter': hu.cpu_do}

self.assertReferenceChecks(
            gc, op,
            [param, mom1, mom2, grad, LR, ITER],
            functools.partial(
                self.ref_adam,
                beta1=beta1, beta2=beta2, epsilon=epsilon, output_grad=True),
            input_device_options=input_device_options)

@given(inputs=hu.tensors(n=4),
           ITER=st.integers(min_value=0, max_value=10000),
           LR=st.floats(min_value=0.01, max_value=0.99,
                        allow_nan=False, allow_infinity=False),
           beta1=st.floats(min_value=0.01, max_value=0.99,
                           allow_nan=False, allow_infinity=False),
           beta2=st.floats(min_value=0.01, max_value=0.99,
                           allow_nan=False, allow_infinity=False),
           epsilon=st.floats(min_value=0.01, max_value=0.99,
                             allow_nan=False, allow_infinity=False),
           data_strategy=st.data(),
           **hu.gcs)
    def test_sparse_adam(self, inputs, ITER, LR, beta1, beta2, epsilon,
                         data_strategy, gc, dc):
        param, mom1, mom2, grad = inputs
        mom2 = np.absolute(mom2)
        ITER = np.array([ITER], dtype=np.int64)
        LR = np.array([LR], dtype=np.float32)

# Create an indexing array containing values which index into grad
        indices = data_strategy.draw(
            hu.tensor(
                max_dim=1,
                min_value=1,
                max_value=grad.shape[0],
                dtype=np.int64,
                elements=st.sampled_from(np.arange(grad.shape[0])),
            ),
        )

# Verify that the generated indices are unique
        hypothesis.assume(
            np.array_equal(
                np.unique(indices.flatten()),
                np.sort(indices.flatten())))

# Sparsify grad
        grad = grad[indices]

op = core.CreateOperator(
            "SparseAdam",
            ["param", "mom1", "mom2", "indices", "grad", "lr", "iter"],
            ["param", "mom1", "mom2"],
            beta1=beta1, beta2=beta2, epsilon=epsilon)

def ref_sparse(param, mom1, mom2, indices, grad, LR, ITER):
            param_out = np.copy(param)
            mom1_out = np.copy(mom1)
            mom2_out = np.copy(mom2)

for i, index in enumerate(indices):
                param_out[index], mom1_out[index], mom2_out[index] = \
                    self.ref_adam(param[index], mom1[index], mom2[index],
                                  grad[i], LR, ITER,
                                  beta1, beta2, epsilon)
            return (param_out, mom1_out, mom2_out)

# Iter lives on the CPU
        input_device_options = {'iter': hu.cpu_do}

self.assertReferenceChecks(
            gc, op,
            [param, mom1, mom2, indices, grad, LR, ITER],
            ref_sparse,
            input_device_options=input_device_options)

@given(inputs=hu.tensors(n=4),
           ITER=st.integers(min_value=0, max_value=10),
           LR=st.floats(min_value=0.000001, max_value=0.1,
                        allow_nan=False, allow_infinity=False),
           beta1=st.floats(min_value=0.0, max_value=0.99999,
                           allow_nan=False, allow_infinity=False),
           beta2=st.floats(min_value=0.9, max_value=0.999999,
                           allow_nan=False, allow_infinity=False),
           epsilon=st.floats(min_value=0.00001, max_value=0.99,
                             allow_nan=False, allow_infinity=False),
           data_strategy=st.data(),
           **hu.gcs)
    def test_smart_decay_sparse_adam(self, inputs, ITER, LR, beta1, beta2, epsilon,
                                     data_strategy, gc, dc):
        param, mom1, mom2, grad = inputs
        mom2 = np.absolute(mom2)
        _iter, _lr = ITER, LR  # Keep the scalar types for reference
        ITER = np.array([ITER], dtype=np.int64)
        LR = np.array([LR], dtype=np.float32)

# Here we will define the last_seen tensor as being randomly from 0 to ITER
        # (the value of t to be tested will be ITER+1)
        last_seen = data_strategy.draw(
            hypothesis.extra.numpy.arrays(
                dtype=np.int64,
                shape=(param.shape[0],),
                elements=st.integers(min_value=0, max_value=_iter),
                unique=False,
            )
        )

# Verify that the generated indices are unique
        hypothesis.assume(
            np.array_equal(
                np.unique(indices.flatten()),
                np.sort(indices.flatten())))

# Sparsify grad
        grad = grad[indices]

op = core.CreateOperator(
            "SmartDecaySparseAdam",
            ["param", "mom1", "mom2", "last_seen", "indices", "grad", "lr", "iter"],
            ["param", "mom1", "mom2", "last_seen"],
            beta1=beta1, beta2=beta2, epsilon=epsilon)

def ref_sparse(param, mom1, mom2, last_seen, indices, grad, LR, ITER):
            param_out = np.copy(param)
            mom1_out = np.copy(mom1)
            mom2_out = np.copy(mom2)
            last_seen_out = np.copy(last_seen)

for i, index in enumerate(indices):
                param_out[index], mom1_out[index], mom2_out[index], last_seen_out[index] = \
                    self.ref_smart_decay_adam(param[index], mom1[index], mom2[index], last_seen[index],
                                              grad[i], LR, ITER,
                                              beta1, beta2, epsilon)
            return (param_out, mom1_out, mom2_out, last_seen_out)

# Iter lives on the CPU
        input_device_options = {'iter': hu.cpu_do}

self.assertReferenceChecks(
            gc, op,
            [param, mom1, mom2, last_seen, indices, grad, LR, ITER],
            ref_sparse,
            input_device_options=input_device_options)

@given(inputs=hu.tensors(n=4),
           ITER=st.integers(min_value=0, max_value=10000),
           LR=st.floats(min_value=0.01, max_value=0.99,
                        allow_nan=False, allow_infinity=False),
           beta1=st.floats(min_value=0.01, max_value=0.99,
                           allow_nan=False, allow_infinity=False),
           beta2=st.floats(min_value=0.01, max_value=0.99,
                           allow_nan=False, allow_infinity=False),
           epsilon=st.floats(min_value=0.01, max_value=0.99,
                             allow_nan=False, allow_infinity=False),
           data_strategy=st.data(),
           **hu.gcs)
    def test_sparse_adam_output_grad(self, inputs, ITER, LR, beta1, beta2, epsilon,
                                     data_strategy, gc, dc):
        param, mom1, mom2, grad = inputs
        mom2 = np.absolute(mom2)
        ITER = np.array([ITER], dtype=np.int64)
        LR = np.array([LR], dtype=np.float32)

# Verify that the generated indices are unique
        hypothesis.assume(
            np.array_equal(
                np.unique(indices.flatten()),
                np.sort(indices.flatten())))

# Sparsify grad
        grad = grad[indices]

op = core.CreateOperator(
            "SparseAdam",
            ["param", "mom1", "mom2", "indices", "grad", "lr", "iter"],
            ["param", "mom1", "mom2", "output_grad"],
            beta1=beta1, beta2=beta2, epsilon=epsilon)

def ref_sparse_output_grad(param, mom1, mom2, indices, grad, LR, ITER,
                                   beta1, beta2, epsilon, output_grad):
            param_out = np.copy(param)
            mom1_out = np.copy(mom1)
            mom2_out = np.copy(mom2)
            grad_out = np.copy(grad)

for i, index in enumerate(indices):
                param_out[index], mom1_out[index], mom2_out[index], grad_out[i] = \
                    self.ref_adam(param[index], mom1[index], mom2[index],
                                  grad[i], LR, ITER,
                                  beta1, beta2, epsilon, output_grad)
            return (param_out, mom1_out, mom2_out, grad_out)

# Iter lives on the CPU
        input_device_options = {'iter': hu.cpu_do}

self.assertReferenceChecks(
            gc, op,
            [param, mom1, mom2, indices, grad, LR, ITER],
            functools.partial(
                ref_sparse_output_grad,
                beta1=beta1, beta2=beta2, epsilon=epsilon, output_grad=True),
            input_device_options=input_device_options)

@given(inputs=hu.tensors(n=3),
           ITER=st.integers(min_value=0, max_value=10000),
           LR=st.floats(min_value=0.01, max_value=0.99,
                        allow_nan=False, allow_infinity=False),
           beta1=st.floats(min_value=0.01, max_value=0.99,
                           allow_nan=False, allow_infinity=False),
           beta2=st.floats(min_value=0.01, max_value=0.99,
                           allow_nan=False, allow_infinity=False),
           epsilon=st.floats(min_value=0.01, max_value=0.99,
                             allow_nan=False, allow_infinity=False),
           data_strategy=st.data(),
           **hu.gcs)
    def test_row_wise_sparse_adam(self, inputs, ITER, LR, beta1, beta2, epsilon,
                                  data_strategy, gc, dc):
        param, mom1, grad = inputs
        ITER = np.array([ITER], dtype=np.int64)
        LR = np.array([LR], dtype=np.float32)

# Create a 1D row-wise average 2nd moment tensor.
        mom2 = data_strategy.draw(
            hu.tensor1d(min_len=param.shape[0], max_len=param.shape[0],
                        elements=hu.elements_of_type(dtype=np.float32))
        )
        mom2 = np.absolute(mom2)

# Note that unlike SparseAdam, RowWiseSparseAdam uses a moment
        # tensor that is strictly 1-dimensional and equal in length to the
        # first dimension of the parameters, so indices must also be
        # 1-dimensional.
        indices = indices.flatten()

hypothesis.note('indices.shape: %s' % str(indices.shape))

# Verify that the generated indices are unique
        hypothesis.assume(np.array_equal(np.unique(indices), np.sort(indices)))

# Sparsify grad
        grad = grad[indices]

op = core.CreateOperator(
            "RowWiseSparseAdam",
            ["param", "mom1", "mom2", "indices", "grad", "lr", "iter"],
            ["param", "mom1", "mom2"],
            beta1=beta1, beta2=beta2, epsilon=epsilon)

def ref_row_wise_sparse(param, mom1, mom2, indices, grad, LR, ITER):
            param_out = np.copy(param)
            mom1_out = np.copy(mom1)
            mom2_out = np.copy(mom2)
            for i, index in enumerate(indices):
                param_out[index], mom1_out[index], mom2_out[index] = \
                    self.ref_row_wise_adam(param[index], mom1[index], mom2[index],
                                           grad[i], LR, ITER,
                                           beta1, beta2, epsilon)
            return (param_out, mom1_out, mom2_out)

# Iter lives on the CPU
        input_device_options = {'iter': hu.cpu_do}

self.assertDeviceChecks(
            dc, op,
            [param, mom1, mom2, indices, grad, LR, ITER],
            [0, 1, 2],
            input_device_options=input_device_options)

self.assertReferenceChecks(
            gc, op,
            [param, mom1, mom2, indices, grad, LR, ITER],
            ref_row_wise_sparse,
            input_device_options=input_device_options)

@given(inputs=hu.tensors(n=3),
           ITER=st.integers(min_value=0, max_value=10000),
           LR=st.floats(min_value=0.01, max_value=0.99,
                        allow_nan=False, allow_infinity=False),
           beta1=st.floats(min_value=0.01, max_value=0.99,
                           allow_nan=False, allow_infinity=False),
           beta2=st.floats(min_value=0.01, max_value=0.99,
                           allow_nan=False, allow_infinity=False),
           epsilon=st.floats(min_value=0.01, max_value=0.99,
                             allow_nan=False, allow_infinity=False),
           data_strategy=st.data(),
           **hu.gcs)
    def test_row_wise_sparse_adam_output_grad(self, inputs, ITER, LR, beta1, beta2,
                                              epsilon, data_strategy, gc, dc):
        param, mom1, grad = inputs
        ITER = np.array([ITER], dtype=np.int64)
        LR = np.array([LR], dtype=np.float32)

hypothesis.note('indices.shape: %s' % str(indices.shape))

# Verify that the generated indices are unique
        hypothesis.assume(np.array_equal(np.unique(indices), np.sort(indices)))

# Sparsify grad
        grad = grad[indices]

op = core.CreateOperator(
            "RowWiseSparseAdam",
            ["param", "mom1", "mom2", "indices", "grad", "lr", "iter"],
            ["param", "mom1", "mom2", "output_grad"],
            beta1=beta1, beta2=beta2, epsilon=epsilon)

def ref_row_wise_sparse_output_grad(param, mom1, mom2, indices, grad, LR, ITER,
                                            beta1, beta2, epsilon, output_grad):
            param_out = np.copy(param)
            mom1_out = np.copy(mom1)
            mom2_out = np.copy(mom2)
            grad_out = np.copy(grad)

for i, index in enumerate(indices):
                param_out[index], mom1_out[index], mom2_out[index], grad_out[i] = \
                    self.ref_row_wise_adam(param[index], mom1[index], mom2[index],
                                           grad[i], LR, ITER,
                                           beta1, beta2, epsilon, output_grad)
            return (param_out, mom1_out, mom2_out, grad_out)

# Iter lives on the CPU
        input_device_options = {'iter': hu.cpu_do}

self.assertDeviceChecks(
            dc, op,
            [param, mom1, mom2, indices, grad, LR, ITER],
            [0, 1, 2, 3],
            input_device_options=input_device_options)

self.assertReferenceChecks(
            gc, op,
            [param, mom1, mom2, indices, grad, LR, ITER],
            functools.partial(
                ref_row_wise_sparse_output_grad,
                beta1=beta1, beta2=beta2, epsilon=epsilon, output_grad=True),
            input_device_options=input_device_options)

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

cmd: