Vincentqyw
fix: roma
c74a070
import torch
import torch.nn as nn
import numpy as np
class APLoss(nn.Module):
"""differentiable AP loss, through quantization.
Input: (N, M) values in [min, max]
label: (N, M) values in {0, 1}
Returns: list of query AP (for each n in {1..N})
Note: typically, you want to minimize 1 - mean(AP)
"""
def __init__(self, nq=25, min=0, max=1, euc=False):
nn.Module.__init__(self)
assert isinstance(nq, int) and 2 <= nq <= 100
self.nq = nq
self.min = min
self.max = max
self.euc = euc
gap = max - min
assert gap > 0
# init quantizer = non-learnable (fixed) convolution
self.quantizer = q = nn.Conv1d(1, 2 * nq, kernel_size=1, bias=True)
a = (nq - 1) / gap
# 1st half = lines passing to (min+x,1) and (min+x+1/a,0) with x = {nq-1..0}*gap/(nq-1)
q.weight.data[:nq] = -a
q.bias.data[:nq] = torch.from_numpy(
a * min + np.arange(nq, 0, -1)
) # b = 1 + a*(min+x)
# 2nd half = lines passing to (min+x,1) and (min+x-1/a,0) with x = {nq-1..0}*gap/(nq-1)
q.weight.data[nq:] = a
q.bias.data[nq:] = torch.from_numpy(
np.arange(2 - nq, 2, 1) - a * min
) # b = 1 - a*(min+x)
# first and last one are special: just horizontal straight line
q.weight.data[0] = q.weight.data[-1] = 0
q.bias.data[0] = q.bias.data[-1] = 1
def compute_AP(self, x, label):
N, M = x.shape
# print(x.shape, label.shape)
if self.euc: # euclidean distance in same range than similarities
x = 1 - torch.sqrt(2.001 - 2 * x)
# quantize all predictions
q = self.quantizer(x.unsqueeze(1))
q = torch.min(q[:, : self.nq], q[:, self.nq :]).clamp(
min=0
) # N x Q x M [1600, 20, 1681]
nbs = q.sum(dim=-1) # number of samples N x Q = c
rec = (q * label.view(N, 1, M).float()).sum(
dim=-1
) # nb of correct samples = c+ N x Q
prec = rec.cumsum(dim=-1) / (1e-16 + nbs.cumsum(dim=-1)) # precision
rec /= rec.sum(dim=-1).unsqueeze(1) # norm in [0,1]
ap = (prec * rec).sum(dim=-1) # per-image AP
return ap
def forward(self, x, label):
assert x.shape == label.shape # N x M
return self.compute_AP(x, label)
class PixelAPLoss(nn.Module):
"""Computes the pixel-wise AP loss:
Given two images and ground-truth optical flow, computes the AP per pixel.
feat1: (B, C, H, W) pixel-wise features extracted from img1
feat2: (B, C, H, W) pixel-wise features extracted from img2
aflow: (B, 2, H, W) absolute flow: aflow[...,y1,x1] = x2,y2
"""
def __init__(self, sampler, nq=20):
nn.Module.__init__(self)
self.aploss = APLoss(nq, min=0, max=1, euc=False)
self.name = "pixAP"
self.sampler = sampler
def loss_from_ap(self, ap, rel):
return 1 - ap
def forward(self, feat0, feat1, conf0, conf1, pos0, pos1, B, H, W, N=1200):
# subsample things
scores, gt, msk, qconf = self.sampler(
feat0, feat1, conf0, conf1, pos0, pos1, B, H, W, N=1200
)
# compute pixel-wise AP
n = qconf.numel()
if n == 0:
return 0
scores, gt = scores.view(n, -1), gt.view(n, -1)
ap = self.aploss(scores, gt).view(msk.shape)
pixel_loss = self.loss_from_ap(ap, qconf)
loss = pixel_loss[msk].mean()
return loss
class ReliabilityLoss(PixelAPLoss):
"""same than PixelAPLoss, but also train a pixel-wise confidence
that this pixel is going to have a good AP.
"""
def __init__(self, sampler, base=0.5, **kw):
PixelAPLoss.__init__(self, sampler, **kw)
assert 0 <= base < 1
self.base = base
def loss_from_ap(self, ap, rel):
return 1 - ap * rel - (1 - rel) * self.base