Python numpy.tile() Examples
The following are 30
code examples of numpy.tile().
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
numpy
, or try the search function
.
Example #1
Source File: resnet_v1_test.py From DOTA_models with Apache License 2.0 | 6 votes |
def create_test_input(batch_size, height, width, channels): """Create test input tensor. Args: batch_size: The number of images per batch or `None` if unknown. height: The height of each image or `None` if unknown. width: The width of each image or `None` if unknown. channels: The number of channels per image or `None` if unknown. Returns: Either a placeholder `Tensor` of dimension [batch_size, height, width, channels] if any of the inputs are `None` or a constant `Tensor` with the mesh grid values along the spatial dimensions. """ if None in [batch_size, height, width, channels]: return tf.placeholder(tf.float32, (batch_size, height, width, channels)) else: return tf.to_float( np.tile( np.reshape( np.reshape(np.arange(height), [height, 1]) + np.reshape(np.arange(width), [1, width]), [1, height, width, 1]), [batch_size, 1, 1, channels]))
Example #2
Source File: sympart.py From pymoo with Apache License 2.0 | 6 votes |
def _calc_pareto_set(self, n_pareto_points=500): # The SYM-PART test problem has 9 equivalent Pareto subsets. h = int(n_pareto_points / 9) PS = zeros((h * 9, self.n_var)) cnt = 0 for row in [-1, 0, 1]: for col in [1, 0, -1]: X1 = np.linspace(row * self.c - self.a, row * self.c + self.a, h) X2 = np.tile(col * self.b, h) PS[cnt * h:cnt * h + h, :] = np.vstack((X1, X2)).T cnt = cnt + 1 if self.w != 0: # If rotated, we apply the rotation matrix to PS # Calculate the rotation matrix RM = np.array([ [cos(self.w), -sin(self.w)], [sin(self.w), cos(self.w)] ]) PS = np.array([np.matmul(RM, x) for x in PS]) return PS
Example #3
Source File: resnet_v1_test.py From DeepLab_v3 with MIT License | 6 votes |
def create_test_input(batch_size, height, width, channels): """Create test input tensor. Args: batch_size: The number of images per batch or `None` if unknown. height: The height of each image or `None` if unknown. width: The width of each image or `None` if unknown. channels: The number of channels per image or `None` if unknown. Returns: Either a placeholder `Tensor` of dimension [batch_size, height, width, channels] if any of the inputs are `None` or a constant `Tensor` with the mesh grid values along the spatial dimensions. """ if None in [batch_size, height, width, channels]: return tf.placeholder(tf.float32, (batch_size, height, width, channels)) else: return tf.to_float( np.tile( np.reshape( np.reshape(np.arange(height), [height, 1]) + np.reshape(np.arange(width), [1, width]), [1, height, width, 1]), [batch_size, 1, 1, channels]))
Example #4
Source File: resnet_v2_test.py From DeepLab_v3 with MIT License | 6 votes |
def create_test_input(batch_size, height, width, channels): """Create test input tensor. Args: batch_size: The number of images per batch or `None` if unknown. height: The height of each image or `None` if unknown. width: The width of each image or `None` if unknown. channels: The number of channels per image or `None` if unknown. Returns: Either a placeholder `Tensor` of dimension [batch_size, height, width, channels] if any of the inputs are `None` or a constant `Tensor` with the mesh grid values along the spatial dimensions. """ if None in [batch_size, height, width, channels]: return tf.placeholder(tf.float32, (batch_size, height, width, channels)) else: return tf.to_float( np.tile( np.reshape( np.reshape(np.arange(height), [height, 1]) + np.reshape(np.arange(width), [1, width]), [1, height, width, 1]), [batch_size, 1, 1, channels]))
Example #5
Source File: competition_model_class.py From Deep_Learning_Weather_Forecasting with Apache License 2.0 | 6 votes |
def sample_batch(self, data_inputs, ground_truth, ruitu_inputs, batch_size, certain_id=None, certain_feature=None): max_i, _, max_j, _ = data_inputs.shape # Example: (1148, 37, 10, 9)-(sample_ind, timestep, sta_id, features) if certain_id == None and certain_feature == None: id_ = np.random.randint(max_j, size=batch_size) i = np.random.randint(max_i, size=batch_size) batch_inputs = data_inputs[i,:,id_,:] batch_ouputs = ground_truth[i,:,id_,:] batch_ruitu = ruitu_inputs[i,:,id_,:] # id used for embedding expd_id = np.expand_dims(id_,axis=1) batch_ids = np.tile(expd_id,(1,37)) #batch_time = elif certain_id != None: pass return batch_inputs, batch_ruitu, batch_ouputs, batch_ids
Example #6
Source File: test_common.py From pyscf with Apache License 2.0 | 6 votes |
def tdhf_frozen_mask(eri, kind="ov"): if isinstance(eri.nocc, int): nocc = int(eri.model.mo_occ.sum() // 2) mask = eri.space else: nocc = numpy.array(tuple(int(i.sum() // 2) for i in eri.model.mo_occ)) assert numpy.all(nocc == nocc[0]) assert numpy.all(eri.space == eri.space[0, numpy.newaxis, :]) nocc = nocc[0] mask = eri.space[0] mask_o = mask[:nocc] mask_v = mask[nocc:] if kind == "ov": mask_ov = numpy.outer(mask_o, mask_v).reshape(-1) return numpy.tile(mask_ov, 2) elif kind == "1ov": return numpy.outer(mask_o, mask_v).reshape(-1) elif kind == "sov": mask_ov = numpy.outer(mask_o, mask_v).reshape(-1) nk = len(eri.model.mo_occ) return numpy.tile(mask_ov, 2 * nk ** 2) elif kind == "o,v": return mask_o, mask_v
Example #7
Source File: test_common.py From pyscf with Apache License 2.0 | 6 votes |
def tdhf_frozen_mask(eri, kind="ov"): if isinstance(eri.nocc, int): nocc = int(eri.model.mo_occ.sum() // 2) mask = eri.space else: nocc = numpy.array(tuple(int(i.sum() // 2) for i in eri.model.mo_occ)) assert numpy.all(nocc == nocc[0]) assert numpy.all(eri.space == eri.space[0, numpy.newaxis, :]) nocc = nocc[0] mask = eri.space[0] mask_o = mask[:nocc] mask_v = mask[nocc:] if kind == "ov": mask_ov = numpy.outer(mask_o, mask_v).reshape(-1) return numpy.tile(mask_ov, 2) elif kind == "1ov": return numpy.outer(mask_o, mask_v).reshape(-1) elif kind == "sov": mask_ov = numpy.outer(mask_o, mask_v).reshape(-1) nk = len(eri.model.mo_occ) return numpy.tile(mask_ov, 2 * nk ** 2) elif kind == "o,v": return mask_o, mask_v
Example #8
Source File: test_common.py From pyscf with Apache License 2.0 | 6 votes |
def tdhf_frozen_mask(eri, kind="ov"): if isinstance(eri.nocc, int): nocc = int(eri.model.mo_occ.sum() // 2) mask = eri.space else: nocc = numpy.array(tuple(int(i.sum() // 2) for i in eri.model.mo_occ)) assert numpy.all(nocc == nocc[0]) assert numpy.all(eri.space == eri.space[0, numpy.newaxis, :]) nocc = nocc[0] mask = eri.space[0] mask_o = mask[:nocc] mask_v = mask[nocc:] if kind == "ov": mask_ov = numpy.outer(mask_o, mask_v).reshape(-1) return numpy.tile(mask_ov, 2) elif kind == "1ov": return numpy.outer(mask_o, mask_v).reshape(-1) elif kind == "sov": mask_ov = numpy.outer(mask_o, mask_v).reshape(-1) nk = len(eri.model.mo_occ) return numpy.tile(mask_ov, 2 * nk ** 2) elif kind == "o,v": return mask_o, mask_v
Example #9
Source File: test_common.py From pyscf with Apache License 2.0 | 6 votes |
def tdhf_frozen_mask(eri, kind="ov"): if isinstance(eri.nocc, int): nocc = int(eri.model.mo_occ.sum() // 2) mask = eri.space else: nocc = numpy.array(tuple(int(i.sum() // 2) for i in eri.model.mo_occ)) assert numpy.all(nocc == nocc[0]) assert numpy.all(eri.space == eri.space[0, numpy.newaxis, :]) nocc = nocc[0] mask = eri.space[0] mask_o = mask[:nocc] mask_v = mask[nocc:] if kind == "ov": mask_ov = numpy.outer(mask_o, mask_v).reshape(-1) return numpy.tile(mask_ov, 2) elif kind == "1ov": return numpy.outer(mask_o, mask_v).reshape(-1) elif kind == "sov": mask_ov = numpy.outer(mask_o, mask_v).reshape(-1) nk = len(eri.model.mo_occ) return numpy.tile(mask_ov, 2 * nk ** 2) elif kind == "o,v": return mask_o, mask_v
Example #10
Source File: resnet_v2_test.py From DOTA_models with Apache License 2.0 | 6 votes |
def create_test_input(batch_size, height, width, channels): """Create test input tensor. Args: batch_size: The number of images per batch or `None` if unknown. height: The height of each image or `None` if unknown. width: The width of each image or `None` if unknown. channels: The number of channels per image or `None` if unknown. Returns: Either a placeholder `Tensor` of dimension [batch_size, height, width, channels] if any of the inputs are `None` or a constant `Tensor` with the mesh grid values along the spatial dimensions. """ if None in [batch_size, height, width, channels]: return tf.placeholder(tf.float32, (batch_size, height, width, channels)) else: return tf.to_float( np.tile( np.reshape( np.reshape(np.arange(height), [height, 1]) + np.reshape(np.arange(width), [1, width]), [1, height, width, 1]), [batch_size, 1, 1, channels]))
Example #11
Source File: operations.py From simpleflow with MIT License | 6 votes |
def compute_gradient(self, grad=None): ''' Compute the gradient for negative operation wrt input value. :param grad: The gradient of other operation wrt the negative output. :type grad: ndarray. ''' input_value = self.input_nodes[0].output_value if grad is None: grad = np.ones_like(self.output_value) output_shape = np.array(np.shape(input_value)) output_shape[self.axis] = 1.0 tile_scaling = np.shape(input_value) // output_shape grad = np.reshape(grad, output_shape) return np.tile(grad, tile_scaling)
Example #12
Source File: ModelingCloth.py From Modeling-Cloth with MIT License | 6 votes |
def zxy_grid(co_y, tymin, tymax, subs, c, t, c_peat, t_peat): # create linespace grid between bottom and top of tri z #subs = 7 t_min = np.min(tymin) t_max = np.max(tymax) divs = np.linspace(t_min, t_max, num=subs, dtype=np.float32) # figure out which triangles and which co are in each section co_bools = (co_y > divs[:-1][:, nax]) & (co_y < divs[1:][:, nax]) tri_bools = (tymin < divs[1:][:, nax]) & (tymax > divs[:-1][:, nax]) for i, j in zip(co_bools, tri_bools): if (np.sum(i) > 0) & (np.sum(j) > 0): c3 = c[i] t3 = t[j] c_peat.append(np.repeat(c3, t3.shape[0])) t_peat.append(np.tile(t3, c3.shape[0]))
Example #13
Source File: tests_complexity.py From NeuroKit with MIT License | 6 votes |
def pyeeg_ap_entropy(X, M, R): N = len(X) Em = pyeeg_embed_seq(X, 1, M) A = np.tile(Em, (len(Em), 1, 1)) B = np.transpose(A, [1, 0, 2]) D = np.abs(A - B) # D[i,j,k] = |Em[i][k] - Em[j][k]| InRange = np.max(D, axis=2) <= R # Probability that random M-sequences are in range Cm = InRange.mean(axis=0) # M+1-sequences in range if M-sequences are in range & last values are close Dp = np.abs(np.tile(X[M:], (N - M, 1)) - np.tile(X[M:], (N - M, 1)).T) Cmp = np.logical_and(Dp <= R, InRange[:-1, :-1]).mean(axis=0) Phi_m, Phi_mp = np.sum(np.log(Cm)), np.sum(np.log(Cmp)) Ap_En = (Phi_m - Phi_mp) / (N - M) return Ap_En
Example #14
Source File: tests_complexity.py From NeuroKit with MIT License | 6 votes |
def pyeeg_samp_entropy(X, M, R): N = len(X) Em = pyeeg_embed_seq(X, 1, M)[:-1] A = np.tile(Em, (len(Em), 1, 1)) B = np.transpose(A, [1, 0, 2]) D = np.abs(A - B) # D[i,j,k] = |Em[i][k] - Em[j][k]| InRange = np.max(D, axis=2) <= R np.fill_diagonal(InRange, 0) # Don't count self-matches Cm = InRange.sum(axis=0) # Probability that random M-sequences are in range Dp = np.abs(np.tile(X[M:], (N - M, 1)) - np.tile(X[M:], (N - M, 1)).T) Cmp = np.logical_and(Dp <= R, InRange).sum(axis=0) # Avoid taking log(0) Samp_En = np.log(np.sum(Cm + 1e-100) / np.sum(Cmp + 1e-100)) return Samp_En # ============================================================================= # Entropy # =============================================================================
Example #15
Source File: mghformat.py From me-ica with GNU Lesser General Public License v2.1 | 6 votes |
def update_header(self): ''' Harmonize header with image data and affine ''' hdr = self._header if not self._data is None: hdr.set_data_shape(self._data.shape) if not self._affine is None: # for more information, go through save_mgh.m in FreeSurfer dist MdcD = self._affine[:3, :3] delta = np.sqrt(np.sum(MdcD * MdcD, axis=0)) Mdc = MdcD / np.tile(delta, (3, 1)) Pcrs_c = np.array([0, 0, 0, 1], dtype=np.float) Pcrs_c[:3] = np.array([self._data.shape[0], self._data.shape[1], self._data.shape[2]], dtype=np.float) / 2.0 Pxyz_c = np.dot(self._affine, Pcrs_c) hdr['delta'][:] = delta hdr['Mdc'][:, :] = Mdc.T hdr['Pxyz_c'][:] = Pxyz_c[:3]
Example #16
Source File: run_audio_attack.py From Black-Box-Audio with MIT License | 6 votes |
def __init__(self, input_wave_file, output_wave_file, target_phrase): self.pop_size = 100 self.elite_size = 10 self.mutation_p = 0.005 self.noise_stdev = 40 self.noise_threshold = 1 self.mu = 0.9 self.alpha = 0.001 self.max_iters = 3000 self.num_points_estimate = 100 self.delta_for_gradient = 100 self.delta_for_perturbation = 1e3 self.input_audio = load_wav(input_wave_file).astype(np.float32) self.pop = np.expand_dims(self.input_audio, axis=0) self.pop = np.tile(self.pop, (self.pop_size, 1)) self.output_wave_file = output_wave_file self.target_phrase = target_phrase self.funcs = self.setup_graph(self.pop, np.array([toks.index(x) for x in target_phrase]))
Example #17
Source File: dynamic_contour_embedding.py From RingNet with MIT License | 6 votes |
def load_dynamic_contour(template_flame_path='None', contour_embeddings_path='None', static_embedding_path='None', angle=0): template_mesh = Mesh(filename=template_flame_path) contour_embeddings_path = contour_embeddings_path dynamic_lmks_embeddings = np.load(contour_embeddings_path, allow_pickle=True).item() lmk_face_idx_static, lmk_b_coords_static = load_static_embedding(static_embedding_path) lmk_face_idx_dynamic = dynamic_lmks_embeddings['lmk_face_idx'][angle] lmk_b_coords_dynamic = dynamic_lmks_embeddings['lmk_b_coords'][angle] dynamic_lmks = mesh_points_by_barycentric_coordinates(template_mesh.v, template_mesh.f, lmk_face_idx_dynamic, lmk_b_coords_dynamic) static_lmks = mesh_points_by_barycentric_coordinates(template_mesh.v, template_mesh.f, lmk_face_idx_static, lmk_b_coords_static) total_lmks = np.vstack([dynamic_lmks, static_lmks]) # Visualization of the pose dependent contour on the template mesh vertex_colors = np.ones([template_mesh.v.shape[0], 4]) * [0.3, 0.3, 0.3, 0.8] tri_mesh = trimesh.Trimesh(template_mesh.v, template_mesh.f, vertex_colors=vertex_colors) mesh = pyrender.Mesh.from_trimesh(tri_mesh) scene = pyrender.Scene() scene.add(mesh) sm = trimesh.creation.uv_sphere(radius=0.005) sm.visual.vertex_colors = [0.9, 0.1, 0.1, 1.0] tfs = np.tile(np.eye(4), (len(total_lmks), 1, 1)) tfs[:, :3, 3] = total_lmks joints_pcl = pyrender.Mesh.from_trimesh(sm, poses=tfs) scene.add(joints_pcl) pyrender.Viewer(scene, use_raymond_lighting=True)
Example #18
Source File: ecg_simulate.py From NeuroKit with MIT License | 5 votes |
def _ecg_simulate_daubechies(duration=10, length=None, sampling_rate=1000, heart_rate=70): """Generate an artificial (synthetic) ECG signal of a given duration and sampling rate. It uses a 'Daubechies' wavelet that roughly approximates a single cardiac cycle. This function is based on `this script <https://github.com/diarmaidocualain/ecg_simulation>`_. """ # The "Daubechies" wavelet is a rough approximation to a real, single, cardiac cycle cardiac = scipy.signal.wavelets.daub(10) # Add the gap after the pqrst when the heart is resting. cardiac = np.concatenate([cardiac, np.zeros(10)]) # Caculate the number of beats in capture time period num_heart_beats = int(duration * heart_rate / 60) # Concatenate together the number of heart beats needed ecg = np.tile(cardiac, num_heart_beats) # Change amplitude ecg = ecg * 10 # Resample ecg = signal_resample( ecg, sampling_rate=int(len(ecg) / 10), desired_length=length, desired_sampling_rate=sampling_rate ) return ecg # ============================================================================= # ECGSYN # =============================================================================
Example #19
Source File: m_log_interp.py From pyscf with Apache License 2.0 | 5 votes |
def interp_csr(self, ff, rrs, rcut=None): """ Interpolation of vector data ff[...,:] and vector arguments rrs[:]. The function can accept also a scalar argument rrs """ assert ff.shape[-1]==self.nr nf = ff.size//self.nr fk2v = ff.reshape(nf, self.nr) if rcut is None: rcut = self.gg[-1] rra = rrs.reshape(-1) if type(rrs)==np.ndarray else np.array([rrs]) # well, converting scalar rrs to array kr2cc,j2r = self.coeffs_csr(rra, rcut) fj2v = (fk2v*kr2cc)[:,j2r] rows,cols = np.repeat(range(nf), j2r.size), np.tile(j2r, nf) return csr_matrix( (fj2v.reshape(-1), (rows, cols)), shape=(nf, rrs.size) )
Example #20
Source File: pano_lsd_align.py From HorizonNet with MIT License | 5 votes |
def edgeFromImg2Pano(edge): edgeList = edge['edgeLst'] if len(edgeList) == 0: return np.array([]) vx = edge['vx'] vy = edge['vy'] fov = edge['fov'] imH, imW = edge['img'].shape R = (imW/2) / np.tan(fov/2) # im is the tangent plane, contacting with ball at [x0 y0 z0] x0 = R * np.cos(vy) * np.sin(vx) y0 = R * np.cos(vy) * np.cos(vx) z0 = R * np.sin(vy) vecposX = np.array([np.cos(vx), -np.sin(vx), 0]) vecposY = np.cross(np.array([x0, y0, z0]), vecposX) vecposY = vecposY / np.sqrt(vecposY @ vecposY.T) vecposX = vecposX.reshape(1, -1) vecposY = vecposY.reshape(1, -1) Xc = (0 + imW-1) / 2 Yc = (0 + imH-1) / 2 vecx1 = edgeList[:, [0]] - Xc vecy1 = edgeList[:, [1]] - Yc vecx2 = edgeList[:, [2]] - Xc vecy2 = edgeList[:, [3]] - Yc vec1 = np.tile(vecx1, [1, 3]) * vecposX + np.tile(vecy1, [1, 3]) * vecposY vec2 = np.tile(vecx2, [1, 3]) * vecposX + np.tile(vecy2, [1, 3]) * vecposY coord1 = [[x0, y0, z0]] + vec1 coord2 = [[x0, y0, z0]] + vec2 normal = np.cross(coord1, coord2, axis=1) normal = normal / np.linalg.norm(normal, axis=1, keepdims=True) panoList = np.hstack([normal, coord1, coord2, edgeList[:, [-1]]]) return panoList
Example #21
Source File: tedana.py From me-ica with GNU Lesser General Public License v2.1 | 5 votes |
def t2smap(catd,mask,tes): """ t2smap(catd,mask,tes) Input: catd has shape (nx,ny,nz,Ne,nt) mask has shape (nx,ny,nz) tes is a 1d numpy array """ nx,ny,nz,Ne,nt = catd.shape N = nx*ny*nz echodata = fmask(catd,mask) Nm = echodata.shape[0] #Do Log Linear fit B = np.reshape(np.abs(echodata[:,:ne])+1, (Nm,(ne)*nt)).transpose() B = np.log(B) x = np.array([np.ones(Ne),-tes]) X = np.tile(x,(1,nt)) X = np.sort(X)[:,::-1].transpose() beta,res,rank,sing = np.linalg.lstsq(X,B) t2s = 1/beta[1,:].transpose() s0 = np.exp(beta[0,:]).transpose() #Goodness of fit alpha = (np.abs(B)**2).sum(axis=0) t2s_fit = blah = (alpha - res)/(2*res) out = np.squeeze(unmask(t2s,mask)),np.squeeze(unmask(s0,mask)),unmask(t2s_fit,mask) return out
Example #22
Source File: misc.py From pymoo with Apache License 2.0 | 5 votes |
def vectorized_cdist(A, B, func_dist=euclidean_distance, fill_diag_with_inf=False, **kwargs): u = np.repeat(A, B.shape[0], axis=0) v = np.tile(B, (A.shape[0], 1)) D = func_dist(u, v, **kwargs) M = np.reshape(D, (A.shape[0], B.shape[0])) if fill_diag_with_inf: np.fill_diagonal(M, np.inf) return M
Example #23
Source File: test_trackvis.py From me-ica with GNU Lesser General Public License v2.1 | 5 votes |
def test_round_trip(): out_f = BytesIO() xyz0 = np.tile(np.arange(5).reshape(5,1), (1, 3)) xyz1 = np.tile(np.arange(5).reshape(5,1) + 10, (1, 3)) streams = [(xyz0, None, None), (xyz1, None, None)] tv.write(out_f, streams, {}) out_f.seek(0) streams2, hdr = tv.read(out_f) assert_true(streamlist_equal(streams, streams2)) # test that we can write in different endianness and get back same result, # for versions 1, 2 and not-specified for in_dict, back_version in (({},2), ({'version':2}, 2), ({'version':1}, 1)): for endian_code in (native_code, swapped_code): out_f.seek(0) tv.write(out_f, streams, in_dict, endian_code) out_f.seek(0) streams2, hdr = tv.read(out_f) assert_true(streamlist_equal(streams, streams2)) assert_equal(hdr['version'], back_version) # test that we can get out and pass in generators out_f.seek(0) streams3, hdr = tv.read(out_f, as_generator=True) # check this is a generator rather than a list assert_true(hasattr(streams3, 'send')) # but that it results in the same output assert_true(streamlist_equal(streams, list(streams3))) # write back in out_f.seek(0) streams3, hdr = tv.read(out_f, as_generator=True) # Now we need a new file object, because we're still using the old one for # our generator out_f_write = BytesIO() tv.write(out_f_write, streams3, {}) # and re-read just to check out_f_write.seek(0) streams2, hdr = tv.read(out_f_write) assert_true(streamlist_equal(streams, streams2))
Example #24
Source File: rmetric.py From pymoo with Apache License 2.0 | 5 votes |
def _trim(self, pop, centeroid, range=0.2): """ Box trimming :param pop: :param centeroid: :param range: :return: """ popsize, objDim = pop.shape diff_matrix = pop - np.tile(centeroid, (popsize, 1))[0] flags = np.sum(abs(diff_matrix) < range / 2, axis=1) filtered_matrix = pop[np.where(flags == objDim)] return filtered_matrix
Example #25
Source File: mixers.py From argus-freesound with MIT License | 5 votes |
def sample_mask(self, size): x_radius = random.randint(*self.sigmoid_range) step = (x_radius * 2) / size[1] x = np.arange(-x_radius, x_radius, step=step) y = torch.sigmoid(torch.from_numpy(x)).numpy() mix_mask = np.tile(y, (size[0], 1)) return torch.from_numpy(mix_mask.astype(np.float32))
Example #26
Source File: batcher_test.py From object_detector_app with MIT License | 5 votes |
def test_batch_and_unpad_2d_tensors_of_different_sizes_in_1st_dimension(self): with self.test_session() as sess: batch_size = 3 num_batches = 2 examples = tf.Variable(tf.constant(2, dtype=tf.int32)) counter = examples.count_up_to(num_batches * batch_size + 2) boxes = tf.tile( tf.reshape(tf.range(4), [1, 4]), tf.stack([counter, tf.constant(1)])) batch_queue = batcher.BatchQueue( tensor_dict={'boxes': boxes}, batch_size=batch_size, batch_queue_capacity=100, num_batch_queue_threads=1, prefetch_queue_capacity=100) batch = batch_queue.dequeue() for tensor_dict in batch: for tensor in tensor_dict.values(): self.assertAllEqual([None, 4], tensor.get_shape().as_list()) tf.initialize_all_variables().run() with slim.queues.QueueRunners(sess): i = 2 for _ in range(num_batches): batch_np = sess.run(batch) for tensor_dict in batch_np: for tensor in tensor_dict.values(): self.assertAllEqual(tensor, np.tile(np.arange(4), (i, 1))) i += 1 with self.assertRaises(tf.errors.OutOfRangeError): sess.run(batch)
Example #27
Source File: ops_test.py From object_detector_app with MIT License | 5 votes |
def test_position_sensitive_with_global_pool_false(self): num_spatial_bins = [3, 2] image_shape = [1, 3, 2, 6] num_boxes = 2 # First channel is 1's, second channel is 2's, etc. image = tf.constant(range(1, 3 * 2 + 1) * 6, dtype=tf.float32, shape=image_shape) boxes = tf.random_uniform((num_boxes, 4)) box_ind = tf.constant([0, 0], dtype=tf.int32) expected_output = [] # Expected output, when crop_size = [3, 2]. expected_output.append(np.expand_dims( np.tile(np.array([[1, 2], [3, 4], [5, 6]]), (num_boxes, 1, 1)), axis=-1)) # Expected output, when crop_size = [6, 4]. expected_output.append(np.expand_dims( np.tile(np.array([[1, 1, 2, 2], [1, 1, 2, 2], [3, 3, 4, 4], [3, 3, 4, 4], [5, 5, 6, 6], [5, 5, 6, 6]]), (num_boxes, 1, 1)), axis=-1)) for crop_size_mult in range(1, 3): crop_size = [3 * crop_size_mult, 2 * crop_size_mult] ps_crop = ops.position_sensitive_crop_regions( image, boxes, box_ind, crop_size, num_spatial_bins, global_pool=False) with self.test_session() as sess: output = sess.run(ps_crop) self.assertAllEqual(output, expected_output[crop_size_mult - 1])
Example #28
Source File: ops_test.py From object_detector_app with MIT License | 5 votes |
def test_position_sensitive_with_equal_channels(self): num_spatial_bins = [2, 2] image_shape = [1, 3, 3, 4] crop_size = [2, 2] image = tf.constant(range(1, 3 * 3 + 1), dtype=tf.float32, shape=[1, 3, 3, 1]) tiled_image = tf.tile(image, [1, 1, 1, image_shape[3]]) boxes = tf.random_uniform((3, 4)) box_ind = tf.constant([0, 0, 0], dtype=tf.int32) # All channels are equal so position-sensitive crop and resize should # work as the usual crop and resize for just one channel. crop = tf.image.crop_and_resize(image, boxes, box_ind, crop_size) crop_and_pool = tf.reduce_mean(crop, [1, 2], keep_dims=True) ps_crop_and_pool = ops.position_sensitive_crop_regions( tiled_image, boxes, box_ind, crop_size, num_spatial_bins, global_pool=True) with self.test_session() as sess: expected_output, output = sess.run((crop_and_pool, ps_crop_and_pool)) self.assertAllClose(output, expected_output)
Example #29
Source File: test_stack.py From spinn with MIT License | 5 votes |
def test_backprop_11(self): """Check a valid 11-transition S S M S M S S S M M M sequence.""" X = np.array([[0, 1, 2, 3, 1, 3, 1, 0, 2, 2, 3], [2, 1, 0, 2, 2, 1, 0, 3, 1, 0, 2]], dtype=np.int32) y = np.array([1, 0], dtype=np.int32) transitions = np.tile([0, 0, 1, 0, 1, 0, 0, 0, 1, 1, 1], (2, 1)).astype(np.int32) stack = self._build(11) simulated_top = self._fake_stack_ff(stack)["c11"] self._test_backprop(simulated_top, stack, X, transitions, y)
Example #30
Source File: test_stack.py From spinn with MIT License | 5 votes |
def test_backprop_5(self): # Simulate a batch of two token sequences, each with the same # transition sequence X = np.array([[0, 1, 2, 3, 1], [2, 1, 3, 0, 1]], dtype=np.int32) y = np.array([1, 0], dtype=np.int32) transitions = np.tile([0, 0, 1, 0, 1], (2, 1)).astype(np.int32) stack = self._build(5) simulated_top = self._fake_stack_ff(stack)["c5"] self._test_backprop(simulated_top, stack, X, transitions, y)