Python mxnet.ndarray.split() Examples
The following are 30
code examples of mxnet.ndarray.split().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
mxnet.ndarray
, or try the search function
.
Example #1
Source File: test_contrib_autograd.py From SNIPER-mxnet with Apache License 2.0 | 6 votes |
def test_out_grads(): x = nd.ones((3, 5)) dx = nd.zeros_like(x) mark_variables([x], [dx]) da = None db = nd.array([1,2,3,4,5]) dc = nd.array([5,4,3,2,1]) with train_section(): a, b, c = nd.split(x, axis=0, num_outputs=3, squeeze_axis=True) backward([a, b, c], [da, db, dc]) assert (dx.asnumpy() == np.array( [[1,1,1,1,1], [1,2,3,4,5], [5,4,3,2,1]])).all()
Example #2
Source File: test_autograd.py From SNIPER-mxnet with Apache License 2.0 | 6 votes |
def test_out_grads(): x = nd.ones((3, 5)) dx = nd.zeros_like(x) mark_variables([x], [dx]) da = None db = nd.array([1,2,3,4,5]) dc = nd.array([5,4,3,2,1]) with record(): a, b, c = nd.split(x, axis=0, num_outputs=3, squeeze_axis=True) backward([a, b, c], [da, db, dc]) assert (dx.asnumpy() == np.array( [[1,1,1,1,1], [1,2,3,4,5], [5,4,3,2,1]])).all()
Example #3
Source File: test_autograd.py From dynamic-training-with-apache-mxnet-on-aws with Apache License 2.0 | 6 votes |
def test_out_grads(): x = nd.ones((3, 5)) dx = nd.zeros_like(x) mark_variables([x], [dx]) da = None db = nd.array([1,2,3,4,5]) dc = nd.array([5,4,3,2,1]) with record(): a, b, c = nd.split(x, axis=0, num_outputs=3, squeeze_axis=True) backward([a, b, c], [da, db, dc]) assert (dx.asnumpy() == np.array( [[1,1,1,1,1], [1,2,3,4,5], [5,4,3,2,1]])).all()
Example #4
Source File: test_contrib_autograd.py From dynamic-training-with-apache-mxnet-on-aws with Apache License 2.0 | 6 votes |
def test_out_grads(): x = nd.ones((3, 5)) dx = nd.zeros_like(x) mark_variables([x], [dx]) da = None db = nd.array([1,2,3,4,5]) dc = nd.array([5,4,3,2,1]) with train_section(): a, b, c = nd.split(x, axis=0, num_outputs=3, squeeze_axis=True) backward([a, b, c], [da, db, dc]) assert (dx.asnumpy() == np.array( [[1,1,1,1,1], [1,2,3,4,5], [5,4,3,2,1]])).all()
Example #5
Source File: tensor.py From dgl with Apache License 2.0 | 6 votes |
def split(x, sizes_or_sections, dim): if isinstance(sizes_or_sections, list) and len(sizes_or_sections) == 1: assert len(x) == sizes_or_sections[0] return [x] if MX_VERSION.version[0] == 1 and MX_VERSION.version[1] >= 5: if isinstance(sizes_or_sections, (np.ndarray, list)): sizes_or_sections1 = tuple(np.cumsum(sizes_or_sections)[:-1]) return nd.split_v2(x, sizes_or_sections1, axis=dim) if isinstance(sizes_or_sections, list) or isinstance(sizes_or_sections, np.ndarray): # Old MXNet doesn't support split with different section sizes. np_arr = x.asnumpy() indices = np.cumsum(sizes_or_sections)[:-1] res = np.split(np_arr, indices, axis=dim) return [tensor(arr, dtype=x.dtype) for arr in res] else: return nd.split(x, sizes_or_sections, axis=dim)
Example #6
Source File: irevnet.py From imgclsmob with MIT License | 6 votes |
def inverse(self, y): import mxnet.ndarray as F scale_sqr = self.scale * self.scale batch, y_channels, y_height, y_width = y.shape assert (y_channels % scale_sqr == 0) x_channels = y_channels // scale_sqr x_height = y_height * self.scale x_width = y_width * self.scale x = y.transpose(axes=(0, 2, 3, 1)) x = x.reshape(batch, y_height, y_width, scale_sqr, x_channels) d3_split_seq = x.split(axis=3, num_outputs=(x.shape[3] // self.scale)) d3_split_seq = [t.reshape(batch, y_height, x_width, x_channels) for t in d3_split_seq] x = F.stack(*d3_split_seq, axis=0) x = x.swapaxes(0, 1).transpose(axes=(0, 2, 1, 3, 4)).reshape(batch, x_height, x_width, x_channels) x = x.transpose(axes=(0, 3, 1, 2)) return x
Example #7
Source File: utils.py From training_results_v0.6 with Apache License 2.0 | 5 votes |
def subtract_imagenet_mean_preprocess_batch(batch): """Subtract ImageNet mean pixel-wise from a BGR image.""" batch = F.swapaxes(batch,0, 1) (r, g, b) = F.split(batch, num_outputs=3, axis=0) r = r - 123.680 g = g - 116.779 b = b - 103.939 batch = F.concat(b, g, r, dim=0) batch = F.swapaxes(batch,0, 1) return batch
Example #8
Source File: lstm_crf.py From training_results_v0.6 with Apache License 2.0 | 5 votes |
def _get_lstm_features(self, sentence): self.hidden = self.init_hidden() length = sentence.shape[0] embeds = self.word_embeds(sentence).reshape((length, 1, -1)) lstm_out, self.hidden = self.lstm(embeds, self.hidden) lstm_out = lstm_out.reshape((length, self.hidden_dim)) lstm_feats = self.hidden2tag(lstm_out) return nd.split(lstm_feats, num_outputs=length, axis=0, squeeze_axis=True)
Example #9
Source File: utils.py From training_results_v0.6 with Apache License 2.0 | 5 votes |
def add_imagenet_mean_batch(batch): batch = F.swapaxes(batch,0, 1) (b, g, r) = F.split(batch, num_outputs=3, axis=0) r = r + 123.680 g = g + 116.779 b = b + 103.939 batch = F.concat(b, g, r, dim=0) batch = F.swapaxes(batch,0, 1) """ batch = denormalizer(batch) """ return batch
Example #10
Source File: utils.py From MXNet-Gluon-Style-Transfer with MIT License | 5 votes |
def tensor_save_bgrimage(tensor, filename, cuda=False): (b, g, r) = F.split(tensor, num_outputs=3, axis=0) tensor = F.concat(r, g, b, dim=0) tensor_save_rgbimage(tensor, filename, cuda)
Example #11
Source File: utils.py From MXNet-Gluon-Style-Transfer with MIT License | 5 votes |
def subtract_imagenet_mean_batch(batch): """Subtract ImageNet mean pixel-wise from a BGR image.""" batch = F.swapaxes(batch,0, 1) (r, g, b) = F.split(batch, num_outputs=3, axis=0) r = r - 123.680 g = g - 116.779 b = b - 103.939 batch = F.concat(r, g, b, dim=0) batch = F.swapaxes(batch,0, 1) return batch
Example #12
Source File: utils.py From MXNet-Gluon-Style-Transfer with MIT License | 5 votes |
def subtract_imagenet_mean_preprocess_batch(batch): """Subtract ImageNet mean pixel-wise from a BGR image.""" batch = F.swapaxes(batch,0, 1) (r, g, b) = F.split(batch, num_outputs=3, axis=0) r = r - 123.680 g = g - 116.779 b = b - 103.939 batch = F.concat(b, g, r, dim=0) batch = F.swapaxes(batch,0, 1) return batch
Example #13
Source File: utils.py From MXNet-Gluon-Style-Transfer with MIT License | 5 votes |
def add_imagenet_mean_batch(batch): batch = F.swapaxes(batch,0, 1) (b, g, r) = F.split(batch, num_outputs=3, axis=0) r = r + 123.680 g = g + 116.779 b = b + 103.939 batch = F.concat(b, g, r, dim=0) batch = F.swapaxes(batch,0, 1) """ batch = denormalizer(batch) """ return batch
Example #14
Source File: utils.py From MXNet-Gluon-Style-Transfer with MIT License | 5 votes |
def preprocess_batch(batch): batch = F.swapaxes(batch, 0, 1) (r, g, b) = F.split(batch, num_outputs=3, axis=0) batch = F.concat(b, g, r, dim=0) batch = F.swapaxes(batch, 0, 1) return batch
Example #15
Source File: model.py From NER_BiLSTM_CRF_Chinese with Apache License 2.0 | 5 votes |
def _get_lstm_features(self, sentence): self.hidden = self.init_hidden() length = sentence.shape[0] embeds = self.word_embeds(sentence).reshape((length, 1, -1)) lstm_out, self.hidden = self.lstm(embeds, self.hidden) lstm_out = lstm_out.reshape((length, self.hidden_dim)) lstm_feats = self.hidden2tag(lstm_out) return nd.split(lstm_feats, num_outputs=length, axis=0, squeeze_axis=True)
Example #16
Source File: utils.py From SNIPER-mxnet with Apache License 2.0 | 5 votes |
def tensor_save_bgrimage(tensor, filename, cuda=False): (b, g, r) = F.split(tensor, num_outputs=3, axis=0) tensor = F.concat(r, g, b, dim=0) tensor_save_rgbimage(tensor, filename, cuda)
Example #17
Source File: utils.py From SNIPER-mxnet with Apache License 2.0 | 5 votes |
def subtract_imagenet_mean_batch(batch): """Subtract ImageNet mean pixel-wise from a BGR image.""" batch = F.swapaxes(batch,0, 1) (r, g, b) = F.split(batch, num_outputs=3, axis=0) r = r - 123.680 g = g - 116.779 b = b - 103.939 batch = F.concat(r, g, b, dim=0) batch = F.swapaxes(batch,0, 1) return batch
Example #18
Source File: utils.py From SNIPER-mxnet with Apache License 2.0 | 5 votes |
def subtract_imagenet_mean_preprocess_batch(batch): """Subtract ImageNet mean pixel-wise from a BGR image.""" batch = F.swapaxes(batch,0, 1) (r, g, b) = F.split(batch, num_outputs=3, axis=0) r = r - 123.680 g = g - 116.779 b = b - 103.939 batch = F.concat(b, g, r, dim=0) batch = F.swapaxes(batch,0, 1) return batch
Example #19
Source File: utils.py From SNIPER-mxnet with Apache License 2.0 | 5 votes |
def add_imagenet_mean_batch(batch): batch = F.swapaxes(batch,0, 1) (b, g, r) = F.split(batch, num_outputs=3, axis=0) r = r + 123.680 g = g + 116.779 b = b + 103.939 batch = F.concat(b, g, r, dim=0) batch = F.swapaxes(batch,0, 1) """ batch = denormalizer(batch) """ return batch
Example #20
Source File: utils.py From SNIPER-mxnet with Apache License 2.0 | 5 votes |
def preprocess_batch(batch): batch = F.swapaxes(batch, 0, 1) (r, g, b) = F.split(batch, num_outputs=3, axis=0) batch = F.concat(b, g, r, dim=0) batch = F.swapaxes(batch, 0, 1) return batch
Example #21
Source File: utils.py From training_results_v0.6 with Apache License 2.0 | 5 votes |
def subtract_imagenet_mean_batch(batch): """Subtract ImageNet mean pixel-wise from a BGR image.""" batch = F.swapaxes(batch,0, 1) (r, g, b) = F.split(batch, num_outputs=3, axis=0) r = r - 123.680 g = g - 116.779 b = b - 103.939 batch = F.concat(r, g, b, dim=0) batch = F.swapaxes(batch,0, 1) return batch
Example #22
Source File: utils.py From training_results_v0.6 with Apache License 2.0 | 5 votes |
def tensor_save_bgrimage(tensor, filename, cuda=False): (b, g, r) = F.split(tensor, num_outputs=3, axis=0) tensor = F.concat(r, g, b, dim=0) tensor_save_rgbimage(tensor, filename, cuda)
Example #23
Source File: utils.py From dynamic-training-with-apache-mxnet-on-aws with Apache License 2.0 | 5 votes |
def tensor_save_bgrimage(tensor, filename, cuda=False): (b, g, r) = F.split(tensor, num_outputs=3, axis=0) tensor = F.concat(r, g, b, dim=0) tensor_save_rgbimage(tensor, filename, cuda)
Example #24
Source File: irevnet.py From imgclsmob with MIT License | 5 votes |
def hybrid_forward(self, F, x1, x2): if self.do_padding: x = F.concat(x1, x2, dim=1) x = self.pad(x) x1, x2 = F.split(x, axis=1, num_outputs=2) fx2 = self.bottleneck(x2) if self.do_downscale: x1 = self.psi(x1) x2 = self.psi(x2) y1 = fx2 + x1 return x2, y1
Example #25
Source File: irevnet.py From imgclsmob with MIT License | 5 votes |
def inverse(self, x, _): import mxnet.ndarray as F x1, x2 = F.split(x, axis=1, num_outputs=2) return x1, x2
Example #26
Source File: irevnet.py From imgclsmob with MIT License | 5 votes |
def hybrid_forward(self, F, x, _): x1, x2 = F.split(x, axis=1, num_outputs=2) return x1, x2
Example #27
Source File: irevnet.py From imgclsmob with MIT License | 5 votes |
def hybrid_forward(self, F, x): batch, x_channels, x_height, x_width = x.shape y_channels = x_channels * self.scale * self.scale assert (x_height % self.scale == 0) y_height = x_height // self.scale y = x.transpose(axes=(0, 2, 3, 1)) d2_split_seq = y.split(axis=2, num_outputs=(y.shape[2] // self.scale)) d2_split_seq = [t.reshape(batch, y_height, y_channels) for t in d2_split_seq] y = F.stack(*d2_split_seq, axis=1) y = y.transpose(axes=(0, 3, 2, 1)) return y
Example #28
Source File: score_fun.py From dgl with Apache License 2.0 | 5 votes |
def edge_func(self, edges): real_head, img_head = nd.split(edges.src['emb'], num_outputs=2, axis=-1) real_tail, img_tail = nd.split(edges.dst['emb'], num_outputs=2, axis=-1) phase_rel = edges.data['emb'] / (self.emb_init / np.pi) re_rel, im_rel = nd.cos(phase_rel), nd.sin(phase_rel) real_score = real_head * re_rel - img_head * im_rel img_score = real_head * im_rel + img_head * re_rel real_score = real_score - real_tail img_score = img_score - img_tail #sqrt((x*x).sum() + eps) score = mx.nd.sqrt(real_score * real_score + img_score * img_score + self.eps).sum(-1) return {'score': self.gamma - score}
Example #29
Source File: score_fun.py From dgl with Apache License 2.0 | 5 votes |
def create_neg(self, neg_head): if neg_head: def fn(heads, relations, tails, num_chunks, chunk_size, neg_sample_size): hidden_dim = heads.shape[1] emb_real, emb_img = nd.split(tails, num_outputs=2, axis=-1) rel_real, rel_img = nd.split(relations, num_outputs=2, axis=-1) real = emb_real * rel_real + emb_img * rel_img img = -emb_real * rel_img + emb_img * rel_real emb_complex = nd.concat(real, img, dim=-1) tmp = emb_complex.reshape(num_chunks, chunk_size, hidden_dim) heads = heads.reshape(num_chunks, neg_sample_size, hidden_dim) heads = nd.transpose(heads, axes=(0, 2, 1)) return nd.linalg_gemm2(tmp, heads) return fn else: def fn(heads, relations, tails, num_chunks, chunk_size, neg_sample_size): hidden_dim = heads.shape[1] emb_real, emb_img = nd.split(heads, num_outputs=2, axis=-1) rel_real, rel_img = nd.split(relations, num_outputs=2, axis=-1) real = emb_real * rel_real - emb_img * rel_img img = emb_real * rel_img + emb_img * rel_real emb_complex = nd.concat(real, img, dim=-1) tmp = emb_complex.reshape(num_chunks, chunk_size, hidden_dim) tails = tails.reshape(num_chunks, neg_sample_size, hidden_dim) tails = nd.transpose(tails, axes=(0, 2, 1)) return nd.linalg_gemm2(tmp, tails) return fn
Example #30
Source File: score_fun.py From dgl with Apache License 2.0 | 5 votes |
def edge_func(self, edges): real_head, img_head = nd.split(edges.src['emb'], num_outputs=2, axis=-1) real_tail, img_tail = nd.split(edges.dst['emb'], num_outputs=2, axis=-1) real_rel, img_rel = nd.split(edges.data['emb'], num_outputs=2, axis=-1) score = real_head * real_tail * real_rel \ + img_head * img_tail * real_rel \ + real_head * img_tail * img_rel \ - img_head * real_tail * img_rel # TODO: check if there exists minus sign and if gamma should be used here(jin) return {'score': nd.sum(score, -1)}