Hướng dẫn dùng torch sqrt python
Returns a new tensor with the square-root of the elements of outi= inputi\text{out}_{i} = \sqrt{\text{input}_{i}} input (Tensor) – the input tensor. out (Tensor, optional) – the output tensor. Example: The following are 30 code examples of torch.sqrt(). 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 torch, or try the search function .Example #1 def _attn(self, q, k, v, sequence_mask): w = torch.matmul(q, k) if self.scale: w = w / math.sqrt(v.size(-1)) b_subset = self.b[:, :, :w.size(-2), :w.size(-1)] if sequence_mask is not None: b_subset = b_subset * sequence_mask.view( sequence_mask.size(0), 1, -1) b_subset = b_subset.permute(1, 0, 2, 3) w = w * b_subset + -1e9 * (1 - b_subset) w = nn.Softmax(dim=-1)(w) w = self.attn_dropout(w) return torch.matmul(w, v) Example #2 def centerness_target(self, pos_bbox_targets): """Compute centerness targets. Args: pos_bbox_targets (Tensor): BBox targets of positive bboxes in shape (num_pos, 4) Returns: Tensor: Centerness target. """ # only calculate pos centerness targets, otherwise there may be nan left_right = pos_bbox_targets[:, [0, 2]] top_bottom = pos_bbox_targets[:, [1, 3]] centerness_targets = ( left_right.min(dim=-1)[0] / left_right.max(dim=-1)[0]) * ( top_bottom.min(dim=-1)[0] / top_bottom.max(dim=-1)[0]) return torch.sqrt(centerness_targets) Example #3 def centerness_target(self, anchors, bbox_targets): # only calculate pos centerness targets, otherwise there may be nan gts = self.bbox_coder.decode(anchors, bbox_targets) anchors_cx = (anchors[:, 2] + anchors[:, 0]) / 2 anchors_cy = (anchors[:, 3] + anchors[:, 1]) / 2 l_ = anchors_cx - gts[:, 0] t_ = anchors_cy - gts[:, 1] r_ = gts[:, 2] - anchors_cx b_ = gts[:, 3] - anchors_cy left_right = torch.stack([l_, r_], dim=1) top_bottom = torch.stack([t_, b_], dim=1) centerness = torch.sqrt( (left_right.min(dim=-1)[0] / left_right.max(dim=-1)[0]) * (top_bottom.min(dim=-1)[0] / top_bottom.max(dim=-1)[0])) assert not torch.isnan(centerness).any() return centerness Example #4 def map_roi_levels(self, rois, num_levels): """Map rois to corresponding feature levels by scales. - scale < finest_scale * 2: level 0 - finest_scale * 2 <= scale < finest_scale * 4: level 1 - finest_scale * 4 <= scale < finest_scale * 8: level 2 - scale >= finest_scale * 8: level 3 Args: rois (Tensor): Input RoIs, shape (k, 5). num_levels (int): Total level number. Returns: Tensor: Level index (0-based) of each RoI, shape (k, ) """ scale = torch.sqrt( (rois[:, 3] - rois[:, 1]) * (rois[:, 4] - rois[:, 2])) target_lvls = torch.floor(torch.log2(scale / self.finest_scale + 1e-6)) target_lvls = target_lvls.clamp(min=0, max=num_levels - 1).long() return target_lvls Example #5 def batch_norm(is_training, X, gamma, beta, moving_mean, moving_var, eps, momentum): # 训练模式和预测模式逻辑不同 if not is_training: # 预测模式下,直接使用传入的移动平均值和方差 X_hat = (X - moving_mean) / torch.sqrt(moving_var + eps) else: assert len(X.shape) in (2, 4) if len(X.shape) == 2: # 使用全连接层,二维数组,计算特征维上的均值和方差 mean = X.mean(dim=0) var = ((X - mean) ** 2).mean(dim=0) else: # 使用卷积层,三维数组 mean = X.mean(dim=0, keepdim=True).mean(dim=2, keepdim=True).mean(dim=3, keepdim=True) var = ((X - mean) ** 2).mean(dim=0, keepdim=True).mean(dim=2, keepdim=True).mean(dim=3, keepdim=True) # 训练模式下用当前的均值和方差做标准化 X_hat = (X - mean) / torch.sqrt(var + eps) # 更新移动平均的均值和方差 moving_mean = momentum * moving_mean + (1.0 - momentum) * mean moving_var = momentum * moving_var + (1.0 - momentum) * var Y = gamma * X_hat + beta # 拉伸和偏移 return Y, moving_mean, moving_var Example #6 def fuse_conv_and_bn(conv, bn): # https://tehnokv.com/posts/fusing-batchnorm-and-conv/ with torch.no_grad(): # init fusedconv = torch.nn.Conv2d(conv.in_channels, conv.out_channels, kernel_size=conv.kernel_size, stride=conv.stride, padding=conv.padding, bias=True) # prepare filters w_conv = conv.weight.clone().view(conv.out_channels, -1) w_bn = torch.diag(bn.weight.div(torch.sqrt(bn.eps + bn.running_var))) fusedconv.weight.copy_(torch.mm(w_bn, w_conv).view(fusedconv.weight.size())) # prepare spatial bias if conv.bias is not None: b_conv = conv.bias else: b_conv = torch.zeros(conv.weight.size(0)) b_bn = bn.bias - bn.weight.mul(bn.running_mean).div(torch.sqrt(bn.running_var + bn.eps)) fusedconv.bias.copy_(b_conv + b_bn) return fusedconv Example #7 def forward(self, input1): self.batchgrid3d = torch.zeros(torch.Size([input1.size(0)]) + self.grid3d.size()) for i in range(input1.size(0)): self.batchgrid3d[i] = self.grid3d self.batchgrid3d = Variable(self.batchgrid3d) #print(self.batchgrid3d) x = torch.sum(torch.mul(self.batchgrid3d, input1[:,:,:,0:4]), 3) y = torch.sum(torch.mul(self.batchgrid3d, input1[:,:,:,4:8]), 3) z = torch.sum(torch.mul(self.batchgrid3d, input1[:,:,:,8:]), 3) #print(x) r = torch.sqrt(x**2 + y**2 + z**2) + 1e-5 #print(r) theta = torch.acos(z/r)/(np.pi/2) - 1 #phi = torch.atan(y/x) phi = torch.atan(y/(x + 1e-5)) + np.pi * x.lt(0).type(torch.FloatTensor) * (y.ge(0).type(torch.FloatTensor) - y.lt(0).type(torch.FloatTensor)) phi = phi/np.pi output = torch.cat([theta,phi], 3) return output Example #8 def evo_norm(x, prefix, running_var, v, weight, bias, training, momentum, eps=0.1, groups=32): if prefix == 'b0': if training: var = torch.var(x, dim=(0, 2, 3), keepdim=True) running_var.mul_(momentum) running_var.add_((1 - momentum) * var) else: var = running_var if v is not None: den = torch.max((var + eps).sqrt(), v * x + instance_std(x, eps)) x = x / den * weight + bias else: x = x * weight + bias else: if v is not None: x = x * torch.sigmoid(v * x) / group_std(x, groups, eps) * weight + bias else: x = x * weight + bias return x Example #9 def forward(self, x): x = self.features(x) x = x.view(x.size(0), -1) if self.convert_to_onnx: x = self.classifier[0](x) # manually perform 1d batchnorm, caffe2 currently requires a resize, # which is hard to squeeze into the exported network bn_1d = self.classifier[1] numerator = (x - Variable(bn_1d.running_mean)) denominator = Variable(torch.sqrt(bn_1d.running_var + bn_1d.eps)) x = numerator/denominator*Variable(bn_1d.weight.data) + Variable(bn_1d.bias.data) x = self.classifier[2](x) x = self.classifier[3](x) x = self.classifier[4](x) return x else: x = self.classifier(x) return x Example #10 def cond_samples(f, replay_buffer, args, device, fresh=False): sqrt = lambda x: int(t.sqrt(t.Tensor([x]))) plot = lambda p, x: tv.utils.save_image(t.clamp(x, -1, 1), p, normalize=True, nrow=sqrt(x.size(0))) if fresh: replay_buffer = uncond_samples(f, args, device, save=False) n_it = replay_buffer.size(0) // 100 all_y = [] for i in range(n_it): x = replay_buffer[i * 100: (i + 1) * 100].to(device) y = f.classify(x).max(1)[1] all_y.append(y) all_y = t.cat(all_y, 0) each_class = [replay_buffer[all_y == l] for l in range(10)] print([len(c) for c in each_class]) for i in range(100): this_im = [] for l in range(10): this_l = each_class[l][i * 10: (i + 1) * 10] this_im.append(this_l) this_im = t.cat(this_im, 0) if this_im.size(0) > 0: plot('{}/samples_{}.png'.format(args.save_dir, i), this_im) print(i) Example #11 def forward(self, x, y): means = torch.mean(x, dim=(2, 3)) m = torch.mean(means, dim=-1, keepdim=True) v = torch.var(means, dim=-1, keepdim=True) means = (means - m) / (torch.sqrt(v + 1e-5)) h = self.instance_norm(x) if self.bias: gamma, alpha, beta = self.embed(y).chunk(3, dim=-1) h = h + means[..., None, None] * alpha[..., None, None] out = gamma.view(-1, self.num_features, 1, 1) * h + beta.view(-1, self.num_features, 1, 1) else: gamma, alpha = self.embed(y).chunk(2, dim=-1) h = h + means[..., None, None] * alpha[..., None, None] out = gamma.view(-1, self.num_features, 1, 1) * h return out Example #12 def forward(ctx, unknown, known): # type: (Any, torch.Tensor, torch.Tensor) -> Tuple[torch.Tensor, torch.Tensor] r""" Find the three nearest neighbors of unknown in known Parameters ---------- unknown : torch.Tensor (B, n, 3) tensor of known features known : torch.Tensor (B, m, 3) tensor of unknown features Returns ------- dist : torch.Tensor (B, n, 3) l2 distance to the three nearest neighbors idx : torch.Tensor (B, n, 3) index of 3 nearest neighbors """ dist2, idx = _ext.three_nn(unknown, known) return torch.sqrt(dist2), idx Example #13 def sample(verts, faces, num=10000, ret_choice = False): dist_uni = torch.distributions.Uniform(torch.tensor([0.0]).cuda(), torch.tensor([1.0]).cuda()) x1,x2,x3 = torch.split(torch.index_select(verts, 0, faces[:,0]) - torch.index_select(verts, 0, faces[:,1]), 1, dim = 1) y1,y2,y3 = torch.split(torch.index_select(verts, 0, faces[:,1]) - torch.index_select(verts, 0, faces[:,2]), 1, dim = 1) a = (x2*y3 - x3*y2)**2 b = (x3*y1 - x1*y3)**2 c = (x1*y2 - x2*y1)**2 Areas = torch.sqrt(a+b+c)/2 Areas = Areas / torch.sum(Areas) cat_dist = torch.distributions.Categorical(Areas.view(-1)) choices = cat_dist.sample_n(num) select_faces = faces[choices] xs = torch.index_select(verts, 0,select_faces[:,0]) ys = torch.index_select(verts, 0,select_faces[:,1]) zs = torch.index_select(verts, 0,select_faces[:,2]) u = torch.sqrt(dist_uni.sample_n(num)) v = dist_uni.sample_n(num) points = (1- u)*xs + (u*(1-v))*ys + u*v*zs if ret_choice: return points, choices else: return points Example #14 def tforward(self, disp, edge=None): self.sobel=self.sobel.to(disp.device) if edge is not None: grad = self.sobel(disp) grad = torch.sqrt(grad[:,0:1,...]**2 + grad[:,1:2,...]**2 + 1e-8) pdf = (1-edge)/self.b0 * torch.exp(-torch.abs(grad)/self.b0) + \ edge/self.b1 * torch.exp(-torch.abs(grad)/self.b1) val = torch.mean(-torch.log(pdf.clamp(min=1e-4))) else: # on qifeng's data we don't have ambient info # therefore we supress edge everywhere grad = self.sobel(disp) grad = torch.sqrt(grad[:,0:1,...]**2 + grad[:,1:2,...]**2 + 1e-8) grad= torch.clamp(grad, 0, 1.0) val = torch.mean(grad) return val Example #15 def map_roi_levels(self, rois, num_levels): """Map rois to corresponding feature levels by scales. - scale < finest_scale: level 0 - finest_scale <= scale < finest_scale * 2: level 1 - finest_scale * 2 <= scale < finest_scale * 4: level 2 - scale >= finest_scale * 4: level 3 Args: rois (Tensor): Input RoIs, shape (k, 5). num_levels (int): Total level number. Returns: Tensor: Level index (0-based) of each RoI, shape (k, ) """ scale = torch.sqrt( (rois[:, 3] - rois[:, 1] + 1) * (rois[:, 4] - rois[:, 2] + 1)) target_lvls = torch.floor(torch.log2(scale / self.finest_scale + 1e-6)) target_lvls = target_lvls.clamp(min=0, max=num_levels - 1).long() return target_lvls Example #16 def map_roi_levels(self, rois, num_levels): """Map rrois to corresponding feature levels by scales. - scale < finest_scale: level 0 - finest_scale <= scale < finest_scale * 2: level 1 - finest_scale * 2 <= scale < finest_scale * 4: level 2 - scale >= finest_scale * 4: level 3 Args: rois (Tensor): Input RRoIs, shape (k, 6). (index, x, y, w, h, angle) num_levels (int): Total level number. Returns: Tensor: Level index (0-based) of each RoI, shape (k, ) """ scale = torch.sqrt(rois[:, 3] * rois[:, 4]) target_lvls = torch.floor(torch.log2(scale / self.finest_scale + 1e-6)) target_lvls = target_lvls.clamp(min=0, max=num_levels - 1).long() return target_lvls Example #17 def gelu(x): """Implementation of the gelu activation function. For information: OpenAI GPT's gelu is slightly different (and gives slightly different results): 0.5 * x * (1 + torch.tanh(math.sqrt(2 / math.pi) * (x + 0.044715 * torch.pow(x, 3)))) """ return x * 0.5 * (1.0 + torch.erf(x / math.sqrt(2.0))) Example #18 def forward(self, x): u = x.mean(-1, keepdim=True) s = (x - u).pow(2).mean(-1, keepdim=True) x = (x - u) / torch.sqrt(s + self.variance_epsilon) return self.weight * x + self.bias Example #19 def forward(self, hidden_states, attention_mask): mixed_query_layer = self.query(hidden_states) mixed_key_layer = self.key(hidden_states) mixed_value_layer = self.value(hidden_states) query_layer = self.transpose_for_scores(mixed_query_layer) key_layer = self.transpose_for_scores(mixed_key_layer) value_layer = self.transpose_for_scores(mixed_value_layer) # Take the dot product between "query" and "key" to get the raw attention scores. attention_scores = torch.matmul(query_layer, key_layer.transpose(-1, -2)) attention_scores = attention_scores / math.sqrt(self.attention_head_size) # Apply the attention mask is (precomputed for all layers in BertModel forward() function) attention_scores = attention_scores + attention_mask # Normalize the attention scores to probabilities. attention_probs = nn.Softmax(dim=-1)(attention_scores) # This is actually dropping out entire tokens to attend to, which might # seem a bit unusual, but is taken from the original Transformer paper. attention_probs = self.dropout(attention_probs) context_layer = torch.matmul(attention_probs, value_layer) context_layer = context_layer.permute(0, 2, 1, 3).contiguous() new_context_layer_shape = context_layer.size()[:-2] + (self.all_head_size,) context_layer = context_layer.view(*new_context_layer_shape) return context_layer Example #20 def gelu(x): return (0.5 * x * (1 + torch.tanh(math.sqrt(2 / math.pi) * (x + 0.044715 * torch.pow(x, 3))))) Example #21 def forward(self, x): u = x.mean(-1, keepdim=True) s = (x - u).pow(2).mean(-1, keepdim=True) x = (x - u) / torch.sqrt(s + self.e) return self.g * x + self.b Example #22 def _load_from_state_dict(self, state_dict, prefix, local_metadata, strict, missing_keys, unexpected_keys, error_msgs): """Override default load function. AWS overrides the function _load_from_state_dict to recover weight_gamma and weight_beta if they are missing. If weight_gamma and weight_beta are found in the checkpoint, this function will return after super()._load_from_state_dict. Otherwise, it will compute the mean and std of the pretrained weights and store them in weight_beta and weight_gamma. """ self.weight_gamma.data.fill_(-1) local_missing_keys = [] super()._load_from_state_dict(state_dict, prefix, local_metadata, strict, local_missing_keys, unexpected_keys, error_msgs) if self.weight_gamma.data.mean() > 0: for k in local_missing_keys: missing_keys.append(k) return weight = self.weight.data weight_flat = weight.view(weight.size(0), -1) mean = weight_flat.mean(dim=1).view(-1, 1, 1, 1) std = torch.sqrt(weight_flat.var(dim=1) + 1e-5).view(-1, 1, 1, 1) self.weight_beta.data.copy_(mean) self.weight_gamma.data.copy_(std) missing_gamma_beta = [ k for k in local_missing_keys if k.endswith('weight_gamma') or k.endswith('weight_beta') ] for k in missing_gamma_beta: local_missing_keys.remove(k) for k in local_missing_keys: missing_keys.append(k) Example #23 def fuse_conv_bn(conv, bn): """During inference, the functionary of batch norm layers is turned off but only the mean and var alone channels are used, which exposes the chance to fuse it with the preceding conv layers to save computations and simplify network structures.""" conv_w = conv.weight conv_b = conv.bias if conv.bias is not None else torch.zeros_like( bn.running_mean) factor = bn.weight / torch.sqrt(bn.running_var + bn.eps) conv.weight = nn.Parameter(conv_w * factor.reshape([conv.out_channels, 1, 1, 1])) conv.bias = nn.Parameter((conv_b - bn.running_mean) * factor + bn.bias) return conv Example #24 def rmsprop_2d(x1, x2, s1, s2): g1, g2, eps = 0.2 * x1, 4 * x2, 1e-6 s1 = gamma * s1 + (1 - gamma) * g1 ** 2 s2 = gamma * s2 + (1 - gamma) * g2 ** 2 x1 -= eta / math.sqrt(s1 + eps) * g1 x2 -= eta / math.sqrt(s2 + eps) * g2 return x1, x2, s1, s2 Example #25 def rmsprop(params, states, hyperparams): eps = 1e-6 gamma = hyperparams['gamma'] for p, s in zip(params, states): s.data = gamma * s.data + (1-gamma) * (p.grad.data)**2 p.data -= hyperparams['lr'] * p.grad.data / torch.sqrt(s + eps) Example #26 def log_rmse(net, features, labels): with torch.no_grad(): # 将小于 1 的值设为 1,使对数取值更稳定 clipped_pred = torch.max(net(features), torch.tensor(1.0)) rmse = torch.sqrt(2 * loss(clipped_pred.log(), labels.log()).mean()) return rmse.item() Example #27 def adagrad_2d(x1, x2, s1, s2): g1, g2, eps = 0.2 * x1, 4 * x2, 1e-6 s1 += g1 ** 2 s2 += g2 ** 2 x1 -= eta / math.sqrt(s1 + eps) * g1 x2 -= eta / math.sqrt(s2 + eps) * g2 return x1, x2, s1, s2 Example #28 def adadelta(params, states, hyperparams): rho, eps = hyperparams['rho'], 1e-5 for p, (s, delta) in zip(params, states): s[:] = rho * s + (1 - rho) * (p.grad.data**2) g = p.grad.data * torch.sqrt((delta + eps) / (s + eps)) p.data -= g delta[:] = rho * delta + (1 - rho) * g * g Example #29 def adam(params, states, hyperparams): beta1, beta2, eps = 0.9, 0.999, 1e-6 for p, (v, s) in zip(params, states): v[:] = beta1 * v + (1 - beta1) * p.grad.data s[:] = beta2 * s + (1 - beta2) * p.grad.data**2 v_bias_corr = v / (1 - beta1 ** hyperparams['t']) s_bias_corr = s / (1 - beta2 ** hyperparams['t']) p.data -= hyperparams['lr'] * v_bias_corr / (torch.sqrt(s_bias_corr) + eps) hyperparams['t'] = 1 Example #30 def forward(self, input1, input2): self.batchgrid3d = torch.zeros(torch.Size([input1.size(0)]) + self.grid3d.size()) for i in range(input1.size(0)): self.batchgrid3d[i] = self.grid3d self.batchgrid3d = Variable(self.batchgrid3d) self.batchgrid = torch.zeros(torch.Size([input1.size(0)]) + self.grid.size()) for i in range(input1.size(0)): self.batchgrid[i] = self.grid self.batchgrid = Variable(self.batchgrid) #print(self.batchgrid3d) x = torch.sum(torch.mul(self.batchgrid3d, input1[:,:,:,0:4]), 3) y = torch.sum(torch.mul(self.batchgrid3d, input1[:,:,:,4:8]), 3) z = torch.sum(torch.mul(self.batchgrid3d, input1[:,:,:,8:]), 3) #print(x) r = torch.sqrt(x**2 + y**2 + z**2) + 1e-5 #print(r) theta = torch.acos(z/r)/(np.pi/2) - 1 #phi = torch.atan(y/x) phi = torch.atan(y/(x + 1e-5)) + np.pi * x.lt(0).type(torch.FloatTensor) * (y.ge(0).type(torch.FloatTensor) - y.lt(0).type(torch.FloatTensor)) phi = phi/np.pi input_u = input2.view(-1,1,1,1).repeat(1,self.height, self.width,1) output = torch.cat([theta,phi], 3) output1 = torch.atan(torch.tan(np.pi/2.0*(output[:,:,:,1:2] + self.batchgrid[:,:,:,2:] * input_u[:,:,:,:]))) /(np.pi/2) output2 = torch.cat([output[:,:,:,0:1], output1], 3) return output2 |