本文整理汇总了Python中torch.round方法的典型用法代码示例。如果您正苦于以下问题：Python torch.round方法的具体用法？Python torch.round怎么用？Python torch.round使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在模块torch的用法示例。

在下文中一共展示了torch.round方法的23个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于我们的系统推荐出更棒的Python代码示例。

示例1: calc_region

​点赞 6

​

# 需要导入模块: import torch [as 别名]

# 或者: from torch import round [as 别名]

def calc_region(bbox, ratio, featmap_size=None):

"""Calculate a proportional bbox region.

The bbox center are fixed and the new h' and w' is h * ratio and w * ratio.

Args:

bbox (Tensor): Bboxes to calculate regions, shape (n, 4).

ratio (float): Ratio of the output region.

featmap_size (tuple): Feature map size used for clipping the boundary.

Returns:

tuple: x1, y1, x2, y2

"""

x1 = torch.round((1 - ratio) * bbox[0] + ratio * bbox[2]).long()

y1 = torch.round((1 - ratio) * bbox[1] + ratio * bbox[3]).long()

x2 = torch.round(ratio * bbox[0] + (1 - ratio) * bbox[2]).long()

y2 = torch.round(ratio * bbox[1] + (1 - ratio) * bbox[3]).long()

if featmap_size is not None:

x1 = x1.clamp(min=0, max=featmap_size[1])

y1 = y1.clamp(min=0, max=featmap_size[0])

x2 = x2.clamp(min=0, max=featmap_size[1])

y2 = y2.clamp(min=0, max=featmap_size[0])

return (x1, y1, x2, y2)

开发者ID:open-mmlab，项目名称:mmdetection，代码行数:25，

示例2: calc_region

​点赞 6

​

# 需要导入模块: import torch [as 别名]

# 或者: from torch import round [as 别名]

def calc_region(bbox, ratio, featmap_size=None):

"""Calculate a proportional bbox region.

The bbox center are fixed and the new h' and w' is h * ratio and w * ratio.

Args:

bbox (Tensor): Bboxes to calculate regions, shape (n, 4)

ratio (float): Ratio of the output region.

featmap_size (tuple): Feature map size used for clipping the boundary.

Returns:

tuple: x1, y1, x2, y2

"""

x1 = torch.round((1 - ratio) * bbox[0] + ratio * bbox[2]).long()

y1 = torch.round((1 - ratio) * bbox[1] + ratio * bbox[3]).long()

x2 = torch.round(ratio * bbox[0] + (1 - ratio) * bbox[2]).long()

y2 = torch.round(ratio * bbox[1] + (1 - ratio) * bbox[3]).long()

if featmap_size is not None:

x1 = x1.clamp(min=0, max=featmap_size[1] - 1)

y1 = y1.clamp(min=0, max=featmap_size[0] - 1)

x2 = x2.clamp(min=0, max=featmap_size[1] - 1)

y2 = y2.clamp(min=0, max=featmap_size[0] - 1)

return (x1, y1, x2, y2)

开发者ID:dingjiansw101，项目名称:AerialDetection，代码行数:25，

示例3: crop

​点赞 6

​

# 需要导入模块: import torch [as 别名]

# 或者: from torch import round [as 别名]

def crop(self, box):

assert isinstance(box, (list, tuple, torch.Tensor)), str(type(box))

# box is assumed to be xyxy

current_width, current_height = self.size

xmin, ymin, xmax, ymax = [round(float(b)) for b in box]

assert xmin <= xmax and ymin <= ymax, str(box)

xmin = min(max(xmin, 0), current_width - 1)

ymin = min(max(ymin, 0), current_height - 1)

xmax = min(max(xmax, 0), current_width)

ymax = min(max(ymax, 0), current_height)

xmax = max(xmax, xmin + 1)

ymax = max(ymax, ymin + 1)

width, height = xmax - xmin, ymax - ymin

cropped_parsing = self.parsing[:, ymin:ymax, xmin:xmax]

cropped_size = width, height

return Parsing(cropped_parsing, cropped_size)

开发者ID:soeaver，项目名称:Parsing-R-CNN，代码行数:22，

示例4: parsing_on_boxes

​点赞 6

​

# 需要导入模块: import torch [as 别名]

# 或者: from torch import round [as 别名]

def parsing_on_boxes(parsing, rois, heatmap_size):

device = rois.device

rois = rois.to(torch.device("cpu"))

parsing_list = []

for i in range(rois.shape[0]):

parsing_ins = parsing[i].cpu().numpy()

xmin, ymin, xmax, ymax = torch.round(rois[i]).int()

cropped_parsing = parsing_ins[ymin:ymax, xmin:xmax]

resized_parsing = cv2.resize(

cropped_parsing,

(heatmap_size[1], heatmap_size[0]),

interpolation=cv2.INTER_NEAREST

)

parsing_list.append(torch.from_numpy(resized_parsing))

if len(parsing_list) == 0:

return torch.empty(0, dtype=torch.int64, device=device)

return torch.stack(parsing_list, dim=0).to(device, dtype=torch.int64)

开发者ID:soeaver，项目名称:Parsing-R-CNN，代码行数:20，

示例5: parsing_on_boxes

​点赞 6

​

# 需要导入模块: import torch [as 别名]

# 或者: from torch import round [as 别名]

def parsing_on_boxes(parsing, rois, heatmap_size):

device = rois.device

rois = rois.to(torch.device("cpu"))

parsing_list = []

for i in range(rois.shape[0]):

parsing_ins = parsing[i].cpu().numpy()

xmin, ymin, xmax, ymax = torch.round(rois[i]).int()

cropped_parsing = parsing_ins[max(0, ymin):ymax, max(0, xmin):xmax]

resized_parsing = cv2.resize(

cropped_parsing, (heatmap_size[1], heatmap_size[0]), interpolation=cv2.INTER_NEAREST

)

parsing_list.append(torch.from_numpy(resized_parsing))

if len(parsing_list) == 0:

return torch.empty(0, dtype=torch.int64, device=device)

return torch.stack(parsing_list, dim=0).to(device, dtype=torch.int64)

开发者ID:soeaver，项目名称:Parsing-R-CNN，代码行数:18，

示例6: _score_of_edge

​点赞 6

​

# 需要导入模块: import torch [as 别名]

# 或者: from torch import round [as 别名]

def _score_of_edge(self, v1, v2):

N1 = v1['boxes'].size(0)

N2 = v2['boxes'].size(0)

score = torch.cuda.FloatTensor(N1,N2).fill_(np.nan)

track_score = torch.cuda.FloatTensor(N1,N2).fill_(np.nan)

for i1 in range(N1):

# scores of i1 box in frame i with all boxes in frame i+1

scores2 = v2['scores'].contiguous().view(-1,1)

scores1 = v1['scores'][i1]

score[i1, :] = scores1 + scores2.t()

if v1['trackedboxes'] is not None and v2['trackedboxes'] is not None:

# overlaps between the boxes with tracked_boxes

# overlaps (N1, N2)

overlap_ratio_1 = bbox_overlaps(v1['boxes'].contiguous(), v1['trackedboxes'][0])

overlap_ratio_2 = bbox_overlaps(v2['boxes'].contiguous(), v1['trackedboxes'][1])

track_score = torch.mm(torch.round(overlap_ratio_1), torch.round(overlap_ratio_2).t())

score[track_score>0.]+=1.0

track_score = (track_score>0.).float()

else:

track_score = torch.cuda.FloatTensor(N1,N2).zero_()

return score, track_score

开发者ID:Feynman27，项目名称:pytorch-detect-to-track，代码行数:25，

示例7: eval_single_seg

​点赞 6

​

# 需要导入模块: import torch [as 别名]

# 或者: from torch import round [as 别名]

def eval_single_seg(predict, target, forground = 1):

pred_seg=torch.round(torch.sigmoid(predict)).int()

pred_seg = pred_seg.data.cpu().numpy()

label_seg = target.data.cpu().numpy().astype(dtype=np.int)

assert(pred_seg.shape == label_seg.shape)

Dice = []

Precsion = []

Jaccard = []

Sensitivity=[]

Specificity=[]

n = pred_seg.shape[0]

for i in range(n):

dice,precsion,jaccard,sensitivity,specificity= compute_score_single(pred_seg[i],label_seg[i])

Dice.append(dice)

Precsion .append(precsion)

Jaccard.append(jaccard)

Sensitivity.append(sensitivity)

Specificity.append(specificity)

return Dice,Precsion,Jaccard,Sensitivity,Specificity

开发者ID:FENGShuanglang，项目名称:Pytorch_Medical_Segmention_Template，代码行数:25，

示例8: test_output_head_activations_work

​点赞 6

​

# 需要导入模块: import torch [as 别名]

# 或者: from torch import round [as 别名]

def test_output_head_activations_work():

"""Tests that output head activations work properly"""

output_dim = [["linear", 5], ["linear", 10], ["linear", 3]]

nn_instance = RNN(input_dim=5, layers_info=[["gru", 20], ["lstm", 8], output_dim],

hidden_activations="relu", output_activation=["softmax", None, "relu"])

x = torch.randn((20, 12, 5)) * -20.0

out = nn_instance(x)

assert out.shape == (20, 18)

sums = torch.sum(out[:, :5], dim=1).detach().numpy()

sums_others = torch.sum(out[:, 5:], dim=1).detach().numpy()

sums_others_2 = torch.sum(out[:, 5:15], dim=1).detach().numpy()

sums_others_3 = torch.sum(out[:, 15:18], dim=1).detach().numpy()

for row in range(out.shape[0]):

assert np.round(sums[row], 4) == 1.0, sums[row]

assert not np.round(sums_others[row], 4) == 1.0, sums_others[row]

assert not np.round(sums_others_2[row], 4) == 1.0, sums_others_2[row]

assert not np.round(sums_others_3[row], 4) == 1.0, sums_others_3[row]

for col in range(3):

assert out[row, 15 + col] >= 0.0, out[row, 15 + col]

开发者ID:p-christ，项目名称:nn_builder，代码行数:25，

示例9: visual

​点赞 6

​

# 需要导入模块: import torch [as 别名]

# 或者: from torch import round [as 别名]

def visual(self, input_ts, target_ts, mask_ts, output_ts=None):

"""

input_ts: [(num_wordsx2+2) x batch_size x (len_word+2)]

target_ts: [(num_wordsx2+2) x batch_size x (len_word)]

mask_ts: [(num_wordsx2+2) x batch_size x (len_word)]

output_ts: [(num_wordsx2+2) x batch_size x (len_word)]

"""

output_ts = torch.round(output_ts * mask_ts) if output_ts is not None else None

input_strings = [self._readable(input_ts[:, 0, i]) for i in range(input_ts.size(2))]

target_strings = [self._readable(target_ts[:, 0, i]) for i in range(target_ts.size(2))]

mask_strings = [self._readable(mask_ts[:, 0, 0])]

output_strings = [self._readable(output_ts[:, 0, i]) for i in range(output_ts.size(2))] if output_ts is not None else None

input_strings = 'Input:\n' + '\n'.join(input_strings)

target_strings = 'Target:\n' + '\n'.join(target_strings)

mask_strings = 'Mask:\n' + '\n'.join(mask_strings)

output_strings = 'Output:\n' + '\n'.join(output_strings) if output_ts is not None else None

# strings = [input_strings, target_strings, mask_strings, output_strings]

# self.logger.warning(input_strings)

# self.logger.warning(target_strings)

# self.logger.warning(mask_strings)

# self.logger.warning(output_strings)

print(input_strings)

print(target_strings)

print(mask_strings)

print(output_strings) if output_ts is not None else None

开发者ID:jingweiz，项目名称:pytorch-dnc，代码行数:27，

示例10: uniform_quantize

​点赞 6

​

# 需要导入模块: import torch [as 别名]

# 或者: from torch import round [as 别名]

def uniform_quantize(k):

class qfn(torch.autograd.Function):

@staticmethod

def forward(ctx, input):

if k == 32:

out = input

elif k == 1:

out = torch.sign(input)

else:

n = float(2 ** k - 1)

out = torch.round(input * n) / n

return out

@staticmethod

def backward(ctx, grad_output):

grad_input = grad_output.clone()

return grad_input

return qfn().apply

开发者ID:zzzxxxttt，项目名称:pytorch_DoReFaNet，代码行数:22，

示例11: micro_f1

​点赞 6

​

# 需要导入模块: import torch [as 别名]

# 或者: from torch import round [as 别名]

def micro_f1(logits, labels):

# Compute predictions

preds = torch.round(nn.Sigmoid()(logits))

# Cast to avoid trouble

preds = preds.long()

labels = labels.long()

# Count true positives, true negatives, false positives, false negatives

tp = torch.nonzero(preds * labels).shape[0] * 1.0

tn = torch.nonzero((preds - 1) * (labels - 1)).shape[0] * 1.0

fp = torch.nonzero(preds * (labels - 1)).shape[0] * 1.0

fn = torch.nonzero((preds - 1) * labels).shape[0] * 1.0

# Compute micro-f1 score

prec = tp / (tp + fp)

rec = tp / (tp + fn)

f1 = (2 * prec * rec) / (prec + rec)

return f1

开发者ID:PetarV-，项目名称:DGI，代码行数:21，

示例12: forward

​点赞 6

​

# 需要导入模块: import torch [as 别名]

# 或者: from torch import round [as 别名]

def forward(self, xs, ds, ilens, alpha=1.0):

"""Calculate forward propagation.

Args:

xs (Tensor): Batch of sequences of char or phoneme embeddings (B, Tmax, D).

ds (LongTensor): Batch of durations of each frame (B, T).

ilens (LongTensor): Batch of input lengths (B,).

alpha (float, optional): Alpha value to control speed of speech.

Returns:

Tensor: replicated input tensor based on durations (B, T*, D).

"""

assert alpha > 0

if alpha != 1.0:

ds = torch.round(ds.float() * alpha).long()

xs = [x[:ilen] for x, ilen in zip(xs, ilens)]

ds = [d[:ilen] for d, ilen in zip(ds, ilens)]

xs = [self._repeat_one_sequence(x, d) for x, d in zip(xs, ds)]

return pad_list(xs, self.pad_value)

开发者ID:espnet，项目名称:espnet，代码行数:23，

示例13: _forward

​点赞 6

​

# 需要导入模块: import torch [as 别名]

# 或者: from torch import round [as 别名]

def _forward(self, xs, x_masks=None, is_inference=False):

xs = xs.transpose(1, -1) # (B, idim, Tmax)

for f in self.conv:

xs = f(xs) # (B, C, Tmax)

# NOTE: calculate in log domain

xs = self.linear(xs.transpose(1, -1)).squeeze(-1) # (B, Tmax)

if is_inference:

# NOTE: calculate in linear domain

xs = torch.clamp(

torch.round(xs.exp() - self.offset), min=0

).long() # avoid negative value

if x_masks is not None:

xs = xs.masked_fill(x_masks, 0.0)

return xs

开发者ID:espnet，项目名称:espnet，代码行数:20，

示例14: _quantize

​点赞 6

​

# 需要导入模块: import torch [as 别名]

# 或者: from torch import round [as 别名]

def _quantize(self, bits, op, real_val):

"""

quantize real value.

Parameters

----------

bits : int

quantization bits length

op : torch.nn.module

target module

real_val : float

real value to be quantized

Returns

-------

float

"""

transformed_val = op.zero_point + real_val / op.scale

qmin = 0

qmax = (1 << bits) - 1

clamped_val = torch.clamp(transformed_val, qmin, qmax)

quantized_val = torch.round(clamped_val)

return quantized_val

开发者ID:microsoft，项目名称:nni，代码行数:25，

示例15: pcl_to_obstacles

​点赞 6

​

# 需要导入模块: import torch [as 别名]

# 或者: from torch import round [as 别名]

def pcl_to_obstacles(pts3d, map_size=40, cell_size=0.2, min_pts=10):

r"""Counts number of 3d points in 2d map cell.

Height is sum-pooled.

"""

device = pts3d.device

map_size_in_cells = get_map_size_in_cells(map_size, cell_size) - 1

init_map = torch.zeros(

(map_size_in_cells, map_size_in_cells), device=device

)

if len(pts3d) <= 1:

return init_map

num_pts, dim = pts3d.size()

pts2d = torch.cat([pts3d[:, 2:3], pts3d[:, 0:1]], dim=1)

data_idxs = torch.round(

project2d_pcl_into_worldmap(pts2d, map_size, cell_size)

)

if len(data_idxs) > min_pts:

u, counts = np.unique(

data_idxs.detach().cpu().numpy(), axis=0, return_counts=True

)

init_map[u[:, 0], u[:, 1]] = torch.from_numpy(counts).to(

dtype=torch.float32, device=device

)

return init_map

开发者ID:facebookresearch，项目名称:habitat-api，代码行数:26，

示例16: multi_class_score

​点赞 6

​

# 需要导入模块: import torch [as 别名]

# 或者: from torch import round [as 别名]

def multi_class_score(one_class_fn, predictions, labels, one_hot=False, unindexed_classes=0):

result = {}

shape = labels.shape

for label_index in range(shape[1] + unindexed_classes):

if one_hot:

class_predictions = torch.round(predictions[:, label_index, :, :, :])

else:

class_predictions = predictions.eq(label_index)

class_predictions = class_predictions.squeeze(1) # remove channel dim

class_labels = labels.eq(label_index).float()

class_labels = class_labels.squeeze(1) # remove channel dim

class_predictions = class_predictions.float()

result[str(label_index)] = one_class_fn(class_predictions, class_labels).mean()

return result

# Inefficient to do this twice, TODO: update multi_class_score to handle this

开发者ID:biomedia-mira，项目名称:istn，代码行数:21，

示例17: CDF_fn

​点赞 6

​

# 需要导入模块: import torch [as 别名]

# 或者: from torch import round [as 别名]

def CDF_fn(pz, bin_width, variable_type, distribution_type):

mean = pz[0] if len(pz) == 2 else pz[0][..., (pz[0].size(-1) - 1) // 2]

MEAN = torch.round(mean / bin_width).long()

bin_locations = torch.arange(-n_bins // 2, n_bins // 2)[None, None, None, None, :] + MEAN.cpu()[..., None]

bin_locations = bin_locations.float() * bin_width

bin_locations = bin_locations.to(device=pz[0].device)

pz = [param[:, :, :, :, None] for param in pz]

cdf = cdf_fn(

bin_locations - bin_width,

pz,

variable_type,

distribution_type,

1./bin_width).cpu().numpy()

# Compute CDFs, reweigh to give all bins at least

# 1 / (2^precision) probability.

# CDF is equal to floor[cdf * (2^precision - n_bins)] + range(n_bins)

CDFs = (cdf * ((1 << precision) - n_bins)).astype('int') \

+ np.arange(n_bins)

return CDFs, MEAN

开发者ID:jornpeters，项目名称:integer_discrete_flows，代码行数:25，

示例18: encode_sample

​点赞 6

​

# 需要导入模块: import torch [as 别名]

# 或者: from torch import round [as 别名]

def encode_sample(

z, pz, variable_type, distribution_type, bin_width=1./256, state=None):

if state is None:

state = rans.x_init

else:

state = rans.unflatten(state)

CDFs, MEAN = CDF_fn(pz, bin_width, variable_type, distribution_type)

# z is transformed to Z to match the indices for the CDFs array

Z = torch.round(z / bin_width).long() + n_bins // 2 - MEAN

Z = Z.cpu().numpy()

if not ((np.sum(Z < 0) == 0 and np.sum(Z >= n_bins-1) == 0)):

print('Z out of allowed range of values, canceling compression')

return None

Z, CDFs = Z.reshape(-1), CDFs.reshape(-1, n_bins).copy()

for symbol, cdf in zip(Z[::-1], CDFs[::-1]):

statfun = statfun_encode(cdf)

state = rans.append_symbol(statfun, precision)(state, symbol)

state = rans.flatten(state)

return state

开发者ID:jornpeters，项目名称:integer_discrete_flows，代码行数:27，

示例19: sample_mixture_discretized_logistic

​点赞 6

​

# 需要导入模块: import torch [as 别名]

# 或者: from torch import round [as 别名]

def sample_mixture_discretized_logistic(mean, logs, pi, inverse_bin_width):

# Sample mixtures

b, c, h, w, n_mixtures = tuple(map(int, pi.size()))

pi = pi.view(b * c * h * w, n_mixtures)

sampled_pi = torch.multinomial(pi, num_samples=1).view(-1)

# Select mixture params

mean = mean.view(b * c * h * w, n_mixtures)

mean = mean[torch.arange(b*c*h*w), sampled_pi].view(b, c, h, w)

logs = logs.view(b * c * h * w, n_mixtures)

logs = logs[torch.arange(b*c*h*w), sampled_pi].view(b, c, h, w)

y = torch.rand_like(mean)

x = torch.exp(logs) * torch.log(y / (1 - y)) + mean

x = torch.round(x * inverse_bin_width) / inverse_bin_width

return x

开发者ID:jornpeters，项目名称:integer_discrete_flows，代码行数:20，

示例20: continuous2discrete

​点赞 5

​

# 需要导入模块: import torch [as 别名]

# 或者: from torch import round [as 别名]

def continuous2discrete(depth, d_min, d_max, n_c):

mask = 1 - (depth > d_min) * (depth < d_max)

depth = torch.round(torch.log(depth / d_min) / np.log(d_max / d_min) * (n_c - 1))

depth[mask] = 0

return depth

开发者ID:miraiaroha，项目名称:ACAN，代码行数:7，

示例21: hard_ordinal_regression

​点赞 5

​

# 需要导入模块: import torch [as 别名]

# 或者: from torch import round [as 别名]

def hard_ordinal_regression(self, pred_prob, d_min, d_max, n_c):

mask = (pred_prob > 0.5).float()

pred_label = torch.sum(mask, 1, keepdim=True)

#pred_label = torch.round(torch.sum(pred_prob, 1, keepdim=True))

pred_depth = (discrete2continuous(pred_label, d_min, d_max, n_c) +

discrete2continuous(pred_label + 1, d_min, d_max, n_c)) / 2

return pred_depth

开发者ID:miraiaroha，项目名称:ACAN，代码行数:9，

示例22: forward

​点赞 5

​

# 需要导入模块: import torch [as 别名]

# 或者: from torch import round [as 别名]

def forward(ctx,x):

return torch.round(x)

开发者ID:joansj，项目名称:blow，代码行数:4，

示例23: _uniform_assignment

​点赞 5

​

# 需要导入模块: import torch [as 别名]

# 或者: from torch import round [as 别名]

def _uniform_assignment(src_lens, trg_lens):

max_trg_len = trg_lens.max()

steps = (src_lens.float() - 1) / (trg_lens.float() - 1) # step-size

# max_trg_len

index_t = utils.new_arange(trg_lens, max_trg_len).float()

index_t = steps[:, None] * index_t[None, :] # batch_size X max_trg_len

index_t = torch.round(index_t).long().detach()

return index_t

开发者ID:pytorch，项目名称:fairseq，代码行数:10，

注：本文中的torch.round方法示例整理自Github/MSDocs等源码及文档管理平台，相关代码片段筛选自各路编程大神贡献的开源项目，源码版权归原作者所有，传播和使用请参考对应项目的License；未经允许，请勿转载。