70 lines
2.5 KiB
Python
Executable file
70 lines
2.5 KiB
Python
Executable file
import numpy as np
|
|
import torch
|
|
import torch.nn.functional as F
|
|
|
|
|
|
def cal_loss(pred, gold, smoothing=True):
|
|
''' Calculate cross entropy loss, apply label smoothing if needed. '''
|
|
|
|
gold = gold.contiguous().view(-1) # gold is the groudtruth label in the dataloader
|
|
|
|
if smoothing:
|
|
eps = 0.2
|
|
n_class = pred.size(1) # the number of feature_dim of the ouput, which is output channels
|
|
|
|
one_hot = torch.zeros_like(pred).scatter(1, gold.view(-1, 1), 1)
|
|
one_hot = one_hot * (1 - eps) + (1 - one_hot) * eps / (n_class - 1)
|
|
log_prb = F.log_softmax(pred, dim=1)
|
|
|
|
loss = -(one_hot * log_prb).sum(dim=1).mean()
|
|
else:
|
|
loss = F.cross_entropy(pred, gold, reduction='mean')
|
|
|
|
return loss
|
|
|
|
|
|
# create a file and write the text into it:
|
|
class IOStream():
|
|
def __init__(self, path):
|
|
self.f = open(path, 'a')
|
|
|
|
def cprint(self, text):
|
|
print(text)
|
|
self.f.write(text+'\n')
|
|
self.f.flush()
|
|
|
|
def close(self):
|
|
self.f.close()
|
|
|
|
|
|
def to_categorical(y, num_classes):
|
|
""" 1-hot encodes a tensor """
|
|
new_y = torch.eye(num_classes)[y.cpu().data.numpy(),]
|
|
if (y.is_cuda):
|
|
return new_y.cuda(non_blocking=True)
|
|
return new_y
|
|
|
|
|
|
def compute_overall_iou(pred, target, num_classes):
|
|
shape_ious = []
|
|
pred = pred.max(dim=2)[1] # (batch_size, num_points) the pred_class_idx of each point in each sample
|
|
pred_np = pred.cpu().data.numpy()
|
|
|
|
target_np = target.cpu().data.numpy()
|
|
for shape_idx in range(pred.size(0)): # sample_idx
|
|
part_ious = []
|
|
for part in range(num_classes): # class_idx! no matter which category, only consider all part_classes of all categories, check all 50 classes
|
|
# for target, each point has a class no matter which category owns this point! also 50 classes!!!
|
|
# only return 1 when both belongs to this class, which means correct:
|
|
I = np.sum(np.logical_and(pred_np[shape_idx] == part, target_np[shape_idx] == part))
|
|
# always return 1 when either is belongs to this class:
|
|
U = np.sum(np.logical_or(pred_np[shape_idx] == part, target_np[shape_idx] == part))
|
|
|
|
F = np.sum(target_np[shape_idx] == part)
|
|
|
|
if F != 0:
|
|
iou = I / float(U) # iou across all points for this class
|
|
part_ious.append(iou) # append the iou of this class
|
|
shape_ious.append(np.mean(part_ious)) # each time append an average iou across all classes of this sample (sample_level!)
|
|
return shape_ious # [batch_size]
|