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/deform_conv_test.py (19276B)

import unittest

import caffe2.python.hypothesis_test_util as hu
import hypothesis.strategies as st
import numpy as np
from caffe2.proto import caffe2_pb2
from caffe2.python import core, utils, workspace
from hypothesis import assume, given

def _cudnn_supports(dilation=False, nhwc=False):
    """Return True if cuDNN supports this configuration."""
    v = workspace.GetCuDNNVersion()
    if dilation and v < 6000:
        # Dilation not supported until v6
        return False
    if dilation and nhwc:
        # Dilation and NHWC not supported together
        return False
    return True

def _conv_1d_output_size(size, kernel, pad, dilation, stride):
    return max(1, int((size + pad * 2 - (dilation * (kernel - 1) + 1)) / stride) + 1)

def _conv_2d_output_size(size, kernel, pad_h, pad_w, dilation, stride_h, stride_w):
    return [
        _conv_1d_output_size(size, kernel, pad_h, dilation, stride_h),
        _conv_1d_output_size(size, kernel, pad_w, dilation, stride_w),
    ]

def _conv_2d_offsets_dims(
    batch_size,
    size,
    kernel,
    pad_h,
    pad_w,
    dilation,
    stride_h,
    stride_w,
    deformable_group,
):
    dims = [batch_size, 2 * kernel * kernel * deformable_group]
    dims.extend(
        _conv_2d_output_size(size, kernel, pad_h, pad_w, dilation, stride_h, stride_w)
    )
    return dims

def _conv_2d_random_offsets(batch_size, kernel, dims, num_deformable_group):
    o = []
    for y0 in range(0, kernel):
        for x0 in range(0, kernel):
            # stay away from integer offsets which correspond to "ridges" on the
            # interpolated surface resulting in less precise estimates
            x = np.random.randint(0, kernel) + np.random.uniform(0.05, 0.95)
            y = np.random.randint(0, kernel) + np.random.uniform(0.05, 0.95)
            o.append(y - y0)
            o.append(x - x0)
    o = o * num_deformable_group
    e = []
    for v in o:
        e.append([[v] * dims[1]] * dims[0])
    return np.array([e] * batch_size).astype(np.float32)

def _conv_2d_shuffle_offsets(
    batch_size, kernel, dims, num_deformable_group, input_channels, output_channels
):
    o = []
    w0 = [[0 for x in range(kernel)] for y in range(kernel)]
    for y0 in range(0, kernel):
        for x0 in range(0, kernel):
            x = np.random.randint(0, kernel)
            y = np.random.randint(0, kernel)
            o.append(y - y0)
            o.append(x - x0)
            w0[y][x] += 1
    o = o * num_deformable_group
    e = []
    for v in o:
        e.append([[v] * int(dims[1])] * int(dims[0]))
    w0 = [[w0] * input_channels] * output_channels
    return (
        np.array([e] * batch_size).astype(np.float32),
        utils.NCHW2NHWC(np.array(w0).astype(np.float32)),
    )

class TestConvolution(hu.HypothesisTestCase):
    @unittest.skipIf(not workspace.has_gpu_support, "No gpu support")
    @given(
        stride=st.integers(1, 3),
        pad=st.integers(0, 3),
        kernel=st.integers(1, 5),
        dilation=st.integers(1, 3),
        size=st.integers(7, 10),
        input_channels=st.integers(1, 8),
        output_channels=st.integers(1, 8),
        batch_size=st.integers(1, 3),
        order=st.sampled_from(["NCHW"]),
        engine=st.sampled_from(["", "CUDNN", "MKLDNN"]),
        use_bias=st.booleans(),
        deformable_group=st.integers(1, 3),
        **hu.gcs_gpu_only
    )
    def test_null_offset_convolution(
        self,
        stride,
        pad,
        kernel,
        dilation,
        size,
        input_channels,
        output_channels,
        batch_size,
        order,
        engine,
        use_bias,
        deformable_group,
        gc,
        dc,
    ):
        dkernel = dilation * (kernel - 1) + 1

if gc.device_type == caffe2_pb2.CUDA and engine == "CUDNN":
            assume(_cudnn_supports(dilation=(dilation > 1), nhwc=(order == "NHWC")))

assume(engine != "MKLDNN" or use_bias is True)

op = core.CreateOperator(
            "DeformConv",
            ["X", "o", "w", "b"] if use_bias else ["X", "o", "w"],
            ["Y"],
            stride=stride,
            kernel=kernel,
            dilation=dilation,
            pad=pad,
            order=order,
            engine=engine,
            deformable_group=deformable_group,
        )
        offset_dims = _conv_2d_offsets_dims(
            batch_size,
            size,
            kernel,
            pad,
            pad,
            dilation,
            stride,
            stride,
            deformable_group,
        )
        X = (
            np.random.rand(batch_size, size, size, input_channels).astype(np.float32)
            - 0.5
        )
        o = np.zeros(tuple(offset_dims), np.float32)
        w = (
            np.random.rand(output_channels, kernel, kernel, input_channels).astype(
                np.float32
            )
            - 0.5
        )
        b = np.random.rand(output_channels).astype(np.float32) - 0.5
        if order == "NCHW":
            X = utils.NHWC2NCHW(X)
            w = utils.NHWC2NCHW(w)

inputs = [X, o, w, b] if use_bias else [X, o, w]

# Error handling path.
        if size + pad + pad < dkernel or size + pad + pad < dkernel:
            with self.assertRaises(RuntimeError):
                self.assertDeviceChecks(dc, op, inputs, [0])
            return
        if input_channels % deformable_group != 0:
            with self.assertRaises(RuntimeError):
                self.assertDeviceChecks(dc, op, inputs, [0])
            return
        if output_channels % deformable_group != 0:
            with self.assertRaises(RuntimeError):
                self.assertDeviceChecks(dc, op, inputs, [0])
            return

def reference_conv_op(*args):
            reference_op = core.CreateOperator(
                "Conv",
                ["X", "w", "b"] if use_bias else ["X", "w"],
                ["Y0"],
                stride=stride,
                kernel=kernel,
                dilation=dilation,
                pad=pad,
                order=order,
                engine=engine,
                device_option=gc,
            )
            workspace.RunOperatorOnce(reference_op)
            reference_blob = workspace.FetchBlob("Y0")
            return (reference_blob,)

self.assertReferenceChecks(gc, op, inputs, reference_conv_op)

@unittest.skipIf(not workspace.has_gpu_support, "No gpu support")
    @given(
        stride=st.integers(1, 3),
        pad=st.integers(0, 0),
        kernel=st.integers(1, 5),
        dilation=st.integers(1, 3),
        size=st.integers(7, 10),
        input_channels=st.integers(1, 8),
        output_channels=st.integers(1, 8),
        batch_size=st.integers(1, 3),
        order=st.sampled_from(["NCHW"]),
        engine=st.sampled_from(["", "CUDNN", "MKLDNN"]),
        use_bias=st.booleans(),
        deformable_group=st.integers(1, 4),
        **hu.gcs_gpu_only
    )
    def test_flat_input_convolution(
        self,
        stride,
        pad,
        kernel,
        dilation,
        size,
        input_channels,
        output_channels,
        batch_size,
        order,
        engine,
        use_bias,
        deformable_group,
        gc,
        dc,
    ):
        dkernel = dilation * (kernel - 1) + 1

if gc.device_type == caffe2_pb2.CUDA and engine == "CUDNN":
            assume(_cudnn_supports(dilation=(dilation > 1), nhwc=(order == "NHWC")))

assume(engine != "MKLDNN" or use_bias is True)

op = core.CreateOperator(
            "DeformConv",
            ["X", "o", "w", "b"] if use_bias else ["X", "o", "w"],
            ["Y"],
            stride=stride,
            kernel=kernel,
            dilation=dilation,
            pad=pad,
            order=order,
            engine=engine,
            deformable_group=deformable_group,
        )
        X = np.ones((batch_size, size, size, input_channels), np.float32) - 0.5
        output_size = _conv_2d_output_size(
            size, kernel, pad, pad, dilation, stride, stride
        )
        o = _conv_2d_random_offsets(batch_size, kernel, output_size, deformable_group)
        w = np.ones((output_channels, kernel, kernel, input_channels), np.float32) - 0.5
        b = np.random.rand(output_channels).astype(np.float32) - 0.5
        if order == "NCHW":
            X = utils.NHWC2NCHW(X)
            w = utils.NHWC2NCHW(w)

inputs = [X, o, w, b] if use_bias else [X, o, w]

self.assertReferenceChecks(gc, op, inputs, reference_conv_op)

@unittest.skipIf(not workspace.has_gpu_support, "No gpu support")
    @given(
        stride=st.integers(1, 1),
        pad=st.integers(0, 0),
        kernel=st.integers(1, 5),
        dilation=st.integers(1, 1),
        size=st.integers(7, 10),
        input_channels=st.integers(1, 8),
        output_channels=st.integers(1, 8),
        batch_size=st.integers(1, 3),
        order=st.sampled_from(["NCHW"]),
        engine=st.sampled_from(["", "CUDNN", "MKLDNN"]),
        use_bias=st.booleans(),
        deformable_group=st.integers(1, 4),
        **hu.gcs_gpu_only
    )
    def test_shuffle_input_convolution(
        self,
        stride,
        pad,
        kernel,
        dilation,
        size,
        input_channels,
        output_channels,
        batch_size,
        order,
        engine,
        use_bias,
        deformable_group,
        gc,
        dc,
    ):
        dkernel = dilation * (kernel - 1) + 1

if gc.device_type == caffe2_pb2.CUDA and engine == "CUDNN":
            assume(_cudnn_supports(dilation=(dilation > 1), nhwc=(order == "NHWC")))

assume(engine != "MKLDNN" or use_bias is True)

op = core.CreateOperator(
            "DeformConv",
            ["X", "o", "w", "b"] if use_bias else ["X", "o", "w"],
            ["Y"],
            stride=stride,
            kernel=kernel,
            dilation=dilation,
            pad=pad,
            order=order,
            engine=engine,
            deformable_group=deformable_group,
        )
        X = (
            np.random.rand(batch_size, size, size, input_channels).astype(np.float32)
            - 0.5
        )
        output_size = _conv_2d_output_size(
            size, kernel, pad, pad, dilation, stride, stride
        )
        o, w0 = _conv_2d_shuffle_offsets(
            batch_size,
            kernel,
            output_size,
            deformable_group,
            input_channels,
            output_channels,
        )
        w = np.ones((output_channels, kernel, kernel, input_channels), np.float32)
        b = np.random.rand(output_channels).astype(np.float32) - 0.5

if order == "NCHW":
            X = utils.NHWC2NCHW(X)
            w = utils.NHWC2NCHW(w)
            w0 = utils.NHWC2NCHW(w0)

inputs = [X, o, w, b] if use_bias else [X, o, w]

def reference_conv_op(*args):
            with core.DeviceScope(gc):
                workspace.FeedBlob("w0", w0)
            reference_op = core.CreateOperator(
                "Conv",
                ["X", "w0", "b"] if use_bias else ["X", "w0"],
                ["Y0"],
                stride=stride,
                kernel=kernel,
                dilation=dilation,
                pad=pad,
                order=order,
                engine=engine,
                device_option=gc,
            )
            workspace.RunOperatorOnce(reference_op)
            reference_blob = workspace.FetchBlob("Y0")
            return (reference_blob,)

self.assertReferenceChecks(gc, op, inputs, reference_conv_op)

# CUDNN does NOT support different padding values and we skip it
    @unittest.skipIf(not workspace.has_gpu_support, "No gpu support")
    @given(
        stride_h=st.integers(1, 3),
        stride_w=st.integers(1, 3),
        pad_h=st.integers(0, 3),
        pad_w=st.integers(0, 3),
        kernel=st.integers(2, 5),
        size=st.integers(1, 8),
        input_channels=st.integers(1, 3),
        output_channels=st.integers(1, 3),
        batch_size=st.integers(1, 3),
        order=st.sampled_from(["NCHW"]),
        shared_buffer=st.booleans(),
        use_bias=st.booleans(),
        deformable_group=st.integers(1, 3),
        **hu.gcs_gpu_only
    )
    def test_conv_separate_stride_pad_gradients(
        self,
        stride_h,
        stride_w,
        pad_h,
        pad_w,
        kernel,
        size,
        input_channels,
        output_channels,
        batch_size,
        order,
        shared_buffer,
        use_bias,
        deformable_group,
        gc,
        dc,
    ):
        op = core.CreateOperator(
            "DeformConv",
            ["X", "o", "w", "b"] if use_bias else ["X", "o", "w"],
            ["Y"],
            stride_h=stride_h,
            stride_w=stride_w,
            pad_t=pad_h,
            pad_l=pad_w,
            pad_b=pad_h,
            pad_r=pad_w,
            kernel=kernel,
            order=order,
            shared_buffer=int(shared_buffer),
            deformable_group=deformable_group,
        )
        X = (
            np.random.rand(batch_size, size, size, input_channels).astype(np.float32)
            - 0.5
        )
        output_size = _conv_2d_output_size(
            size, kernel, pad_h, pad_w, 1, stride_h, stride_w
        )
        o = _conv_2d_random_offsets(batch_size, kernel, output_size, deformable_group)
        w = (
            np.random.rand(output_channels, kernel, kernel, input_channels).astype(
                np.float32
            )
            - 0.5
        )
        b = np.random.rand(output_channels).astype(np.float32) - 0.5
        if order == "NCHW":
            X = utils.NHWC2NCHW(X)
            w = utils.NHWC2NCHW(w)

inputs = [X, o, w, b] if use_bias else [X, o, w]

# Error handling path.
        if size + pad_h * 2 < kernel or size + pad_w * 2 < kernel:
            with self.assertRaises(RuntimeError):
                self.assertDeviceChecks(dc, op, inputs, [0])
            return
        if input_channels % deformable_group != 0:
            with self.assertRaises(RuntimeError):
                self.assertDeviceChecks(dc, op, inputs, [0])
            return
        if output_channels % deformable_group != 0:
            with self.assertRaises(RuntimeError):
                self.assertDeviceChecks(dc, op, inputs, [0])
            return

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

@unittest.skipIf(not workspace.has_gpu_support, "No gpu support")
    @given(
        stride=st.integers(1, 3),
        pad=st.integers(0, 3),
        kernel=st.integers(1, 5),
        dilation=st.integers(1, 3),
        size=st.integers(7, 10),
        input_channels=st.integers(1, 8),
        output_channels=st.integers(1, 8),
        batch_size=st.integers(1, 3),
        order=st.sampled_from(["NCHW"]),
        engine=st.sampled_from(["", "CUDNN", "MKLDNN"]),
        use_bias=st.booleans(),
        deformable_group=st.integers(1, 3),
        **hu.gcs_gpu_only
    )
    def test_conv_gradients(
        self,
        stride,
        pad,
        kernel,
        dilation,
        size,
        input_channels,
        output_channels,
        batch_size,
        order,
        engine,
        use_bias,
        deformable_group,
        gc,
        dc,
    ):
        dkernel = dilation * (kernel - 1) + 1

if gc.device_type == caffe2_pb2.CUDA and engine == "CUDNN":
            assume(_cudnn_supports(dilation=(dilation > 1), nhwc=(order == "NHWC")))

assume(engine != "MKLDNN" or use_bias is True)

op = core.CreateOperator(
            "DeformConv",
            ["X", "o", "w", "b"] if use_bias else ["X", "o", "w"],
            ["Y"],
            stride=stride,
            kernel=kernel,
            dilation=dilation,
            pad=pad,
            order=order,
            engine=engine,
            deformable_group=deformable_group,
        )
        X = (
            np.random.rand(batch_size, size, size, input_channels).astype(np.float32)
            - 0.5
        )
        output_size = _conv_2d_output_size(
            size, kernel, pad, pad, dilation, stride, stride
        )
        o = _conv_2d_random_offsets(batch_size, kernel, output_size, deformable_group)
        w = (
            np.random.rand(output_channels, kernel, kernel, input_channels).astype(
                np.float32
            )
            - 0.5
        )
        b = np.random.rand(output_channels).astype(np.float32) - 0.5
        if order == "NCHW":
            X = utils.NHWC2NCHW(X)
            w = utils.NHWC2NCHW(w)

inputs = [X, o, w, b] if use_bias else [X, o, w]
        # Error handling path.
        if size + pad + pad < dkernel or size + pad + pad < dkernel:
            with self.assertRaises(RuntimeError):
                self.assertDeviceChecks(dc, op, inputs, [0])
            return
        if input_channels % deformable_group != 0:
            with self.assertRaises(RuntimeError):
                self.assertDeviceChecks(dc, op, inputs, [0])
            return
        if output_channels % deformable_group != 0:
            with self.assertRaises(RuntimeError):
                self.assertDeviceChecks(dc, op, inputs, [0])
            return

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

if __name__ == "__main__":
    import unittest

unittest.main()

cmd: