GCN issue for some datasets

For datasets: "davis_southern_women_graph", "florentine_families_graph", "les_miserables_graph"

Traceback (most recent call last):
  File "/home/nmilosev/Projects/graspe/src/graspe/tests/test_gcn.py", line 30, in <module>
    test_gcn_all()
  File "/home/nmilosev/Projects/graspe/src/graspe/tests/test_gcn.py", line 24, in test_gcn_all
    e.embed()
  File "/home/nmilosev/Projects/graspe/src/graspe/embeddings/embedding_gcn.py", line 95, in embed
    logits = net(dgl_g, inputs)
  File "/home/nmilosev/.conda/envs/graspe/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/nmilosev/Projects/graspe/src/graspe/embeddings/embedding_gcn.py", line 25, in forward
    h = self.conv2(g, h)
  File "/home/nmilosev/.conda/envs/graspe/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/nmilosev/.conda/envs/graspe/lib/python3.8/site-packages/dgl/nn/pytorch/conv/graphconv.py", line 269, in forward
    graph.update_all(fn.copy_src(src='h', out='m'),
  File "/home/nmilosev/.conda/envs/graspe/lib/python3.8/site-packages/dgl/heterograph.py", line 4501, in update_all
    ndata = core.message_passing(g, message_func, reduce_func, apply_node_func)
  File "/home/nmilosev/.conda/envs/graspe/lib/python3.8/site-packages/dgl/core.py", line 283, in message_passing
    ndata = invoke_gspmm(g, mfunc, rfunc)
  File "/home/nmilosev/.conda/envs/graspe/lib/python3.8/site-packages/dgl/core.py", line 255, in invoke_gspmm
    z = op(graph, x)
  File "/home/nmilosev/.conda/envs/graspe/lib/python3.8/site-packages/dgl/ops/spmm.py", line 170, in func
    return gspmm(g, 'copy_lhs', reduce_op, x, None)
  File "/home/nmilosev/.conda/envs/graspe/lib/python3.8/site-packages/dgl/ops/spmm.py", line 62, in gspmm
    ret = gspmm_internal(g._graph, op,
  File "/home/nmilosev/.conda/envs/graspe/lib/python3.8/site-packages/dgl/backend/pytorch/sparse.py", line 260, in gspmm
    return GSpMM.apply(gidx, op, reduce_op, lhs_data, rhs_data)
  File "/home/nmilosev/.conda/envs/graspe/lib/python3.8/site-packages/dgl/backend/pytorch/sparse.py", line 64, in forward
    out, (argX, argY) = _gspmm(gidx, op, reduce_op, X, Y)
  File "/home/nmilosev/.conda/envs/graspe/lib/python3.8/site-packages/dgl/sparse.py", line 152, in _gspmm
    _CAPI_DGLKernelSpMM(gidx, op, reduce_op,
  File "dgl/_ffi/_cython/./function.pxi", line 287, in dgl._ffi._cy3.core.FunctionBase.__call__
  File "dgl/_ffi/_cython/./function.pxi", line 232, in dgl._ffi._cy3.core.FuncCall
  File "dgl/_ffi/_cython/./base.pxi", line 155, in dgl._ffi._cy3.core.CALL
dgl._ffi.base.DGLError: [17:24:03] /opt/dgl/src/array/kernel.cc:39: Check failed: arrays[i].IsContiguous(): Expect U_data to be a contiguous tensor
Stack trace:
  [bt] (0) /home/nmilosev/.conda/envs/graspe/lib/python3.8/site-packages/dgl/libdgl.so(dmlc::LogMessageFatal::~LogMessageFatal()+0x4f) [0x7f30d86f47af]
  [bt] (1) /home/nmilosev/.conda/envs/graspe/lib/python3.8/site-packages/dgl/libdgl.so(+0x32d227) [0x7f30d881b227]
  [bt] (2) /home/nmilosev/.conda/envs/graspe/lib/python3.8/site-packages/dgl/libdgl.so(+0x32eeb6) [0x7f30d881ceb6]
  [bt] (3) /home/nmilosev/.conda/envs/graspe/lib/python3.8/site-packages/dgl/libdgl.so(+0x32fac1) [0x7f30d881dac1]
  [bt] (4) /home/nmilosev/.conda/envs/graspe/lib/python3.8/site-packages/dgl/libdgl.so(DGLFuncCall+0x48) [0x7f30d8da6478]
  [bt] (5) /home/nmilosev/.conda/envs/graspe/lib/python3.8/site-packages/dgl/_ffi/_cy3/core.cpython-38-x86_64-linux-gnu.so(+0x16d4e) [0x7f30d84e3d4e]
  [bt] (6) /home/nmilosev/.conda/envs/graspe/lib/python3.8/site-packages/dgl/_ffi/_cy3/core.cpython-38-x86_64-linux-gnu.so(+0x1727b) [0x7f30d84e427b]
  [bt] (7) /home/nmilosev/.conda/envs/graspe/bin/python(_PyObject_MakeTpCall+0x22f) [0x5565fc2c385f]
  [bt] (8) /home/nmilosev/.conda/envs/graspe/bin/python(_PyEval_EvalFrameDefault+0x475) [0x5565fc346e35]
graphsinspace / graspe

GCN issue for some datasets #14
