Hello, I met some difficulties when modifying the yolov5-face model. I am looking forward to your help. I am very grateful.My English is not very good. Sorry if I offended youQAQ
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [6, 5]], which is output 0 of AsStridedBackward0, is at version 26; expected version 0 instead. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later. Good luck!
The approximate code is as follows
train.py
for epoch in range(start_epoch, epochs): # epoch ------------------------------------------------------------------
model.train()
#with torch.autograd.detect_anomaly():
# Update image weights (optional)
if opt.image_weights:
# Generate indices
if rank in [-1, 0]:
cw = model.class_weights.cpu().numpy() * (1 - maps) ** 2 / nc # class weights
iw = labels_to_image_weights(dataset.labels, nc=nc, class_weights=cw) # image weights
dataset.indices = random.choices(range(dataset.n), weights=iw, k=dataset.n) # rand weighted idx
# Broadcast if DDP
if rank != -1:
indices = (torch.tensor(dataset.indices) if rank == 0 else torch.zeros(dataset.n)).int()
dist.broadcast(indices, 0)
if rank != 0:
dataset.indices = indices.cpu().numpy()
# Update mosaic border
# b = int(random.uniform(0.25 * imgsz, 0.75 * imgsz + gs) // gs * gs)
# dataset.mosaic_border = [b - imgsz, -b] # height, width borders
mloss = torch.zeros(5, device=device) # mean losses
if rank != -1:
dataloader.sampler.set_epoch(epoch)
pbar = enumerate(dataloader)
logger.info(('\n' + '%10s' * 9) % ('Epoch', 'gpu_mem', 'box', 'obj', 'cls', 'landmark', 'total', 'targets', 'img_size'))
if rank in [-1, 0]:
pbar = tqdm(pbar, total=nb) # progress bar
optimizer.zero_grad()
for i, (imgs, targets, paths, _) in pbar: # batch -------------------------------------------------------------
ni = i + nb * epoch # number integrated batches (since train start)
imgs = imgs.to(device, non_blocking=True).float() / 255.0 # uint8 to float32, 0-255 to 0.0-1.0
# Warmup
if ni <= nw:
xi = [0, nw] # x interp
# model.gr = np.interp(ni, xi, [0.0, 1.0]) # iou loss ratio (obj_loss = 1.0 or iou)
accumulate = max(1, np.interp(ni, xi, [1, nbs / total_batch_size]).round())
for j, x in enumerate(optimizer.param_groups):
# bias lr falls from 0.1 to lr0, all other lrs rise from 0.0 to lr0
x['lr'] = np.interp(ni, xi, [hyp['warmup_bias_lr'] if j == 2 else 0.0, x['initial_lr'] * lf(epoch)])
if 'momentum' in x:
x['momentum'] = np.interp(ni, xi, [hyp['warmup_momentum'], hyp['momentum']])
# Multi-scale
if opt.multi_scale:
sz = random.randrange(imgsz * 0.5, imgsz * 1.5 + gs) // gs * gs # size
sf = sz / max(imgs.shape[2:]) # scale factor
if sf != 1:
ns = [math.ceil(x * sf / gs) * gs for x in imgs.shape[2:]] # new shape (stretched to gs-multiple)
imgs = F.interpolate(imgs, size=ns, mode='bilinear', align_corners=False)
# Forward
with amp.autocast(enabled=cuda):
pred = model(imgs) # forward
loss, loss_items = compute_loss(pred, targets.to(device), model) # loss scaled by batch_size
if rank != -1:
loss = loss * opt.world_size # gradient averaged between devices in DDP mode
# Backward
scaler.scale(loss).backward()
loss.py
def compute_loss(p, targets, model): # predictions, targets, model
device = targets.device
lcls, lbox, lobj, lmark = torch.zeros(1, device=device), torch.zeros(1, device=device), torch.zeros(1, device=device), torch.zeros(1, device=device)
tcls, tbox, indices, anchors, tlandmarks, lmks_mask = build_targets(p, targets, model) # targets
h = model.hyp # hyperparameters
# Define criteria
BCEcls = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['cls_pw']], device=device)) # weight=model.class_weights)
BCEobj = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['obj_pw']], device=device))
landmarks_loss = LandmarksLoss(1.0)
# Class label smoothing https://arxiv.org/pdf/1902.04103.pdf eqn 3
cp, cn = smooth_BCE(eps=0.0)
# Focal loss
g = h['fl_gamma'] # focal loss gamma
if g > 0:
BCEcls, BCEobj = FocalLoss(BCEcls, g), FocalLoss(BCEobj, g)
# Losses
nt = 0 # number of targets
no = len(p) # number of outputs
balance = [4.0, 1.0, 0.4] if no == 3 else [4.0, 1.0, 0.4, 0.1] # P3-5 or P3-6
for i, pi in enumerate(p): # layer index, layer predictions
b, a, gj, gi = indices[i] # image, anchor, gridy, gridx
tobj = torch.zeros_like(pi[..., 0], device=device) # target obj
n = b.shape[0] # number of targets
if n:
nt = nt + n # cumulative targets
ps = pi[b, a, gj, gi] # prediction subset corresponding to targets
# Regression
pxy = ps[:, :2].sigmoid() * 2. - 0.5
pwh = (ps[:, 2:4].sigmoid() * 2) ** 2 * anchors[i]
pbox = torch.cat((pxy, pwh), 1) # predicted box
iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, CIoU=True) # iou(prediction, target)
lbox = lbox + (1.0 - iou).mean() # iou loss
# Objectness
tobj[b, a, gj, gi] = (1.0 - model.gr) + model.gr * iou.detach().clamp(0).type(tobj.dtype) # iou ratio
# Classification
if model.nc > 1: # cls loss (only if multiple classes)
t = torch.full_like(ps[:, 57:], cn, device=device) # targets
t[range(n), tcls[i]] = cp
lcls = lcls + BCEcls(ps[:, 57:], t) # BCE
plandmarks = ps[:,5:57]
for j in range(0, 52, 2):
plandmarks[:, j:j+2] = plandmarks[:, j:j+2] * anchors[i]
lmark = lmark + landmarks_loss(plandmarks, tlandmarks[i], lmks_mask[i])
lobj = lobj + BCEobj(pi[..., 4], tobj) * balance[i] # obj loss
s = 3 / no # output count scaling
lbox = lbox * h['box'] * s
lobj = lobj * h['obj'] * s * (1.4 if no == 4 else 1.)
lcls = lcls * h['cls'] * s
lmark = lmark * h['landmark'] * s
bs = tobj.shape[0] # batch size
loss = lbox + lobj + lcls + lmark
return loss * bs, torch.cat((lbox, lobj, lcls, lmark, loss)).detach()
def build_targets(p, targets, model):
# Build targets for compute_loss(), input targets(image,class,x,y,w,h)
det = model.module.model[-1] if is_parallel(model) else model.model[-1] # Detect() module
na, nt = det.na, targets.shape[0] # number of anchors, targets
tcls, tbox, indices, anch, landmarks, lmks_mask = [], [], [], [], [], []
#gain = torch.ones(7, device=targets.device) # normalized to gridspace gain
gain = torch.ones(59, device=targets.device)
ai = torch.arange(na, device=targets.device).float().view(na, 1).repeat(1, nt) # same as .repeat_interleave(nt)
targets = torch.cat((targets.repeat(na, 1, 1), ai[:, :, None]), 2) # append anchor indices
g = 0.5 # bias
off = torch.tensor([[0, 0],
[1, 0], [0, 1], [-1, 0], [0, -1], # j,k,l,m
# [1, 1], [1, -1], [-1, 1], [-1, -1], # jk,jm,lk,lm
], device=targets.device).float() * g # offsets
for i in range(det.nl):
anchors = det.anchors[i]
gain[2:6] = torch.tensor(p[i].shape)[[3, 2, 3, 2]] # xyxy gain
#landmarks 10
gain[6:58] = torch.tensor(p[i].shape)[[3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2,
3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2]] # xyxy gain
# Match targets to anchors
t = targets * gain
if nt:
# Matches
r = t[:, :, 4:6] / anchors[:, None] # wh ratio
j = torch.max(r, 1. / r).max(2)[0] < model.hyp['anchor_t'] # compare
# j = wh_iou(anchors, t[:, 4:6]) > model.hyp['iou_t'] # iou(3,n)=wh_iou(anchors(3,2), gwh(n,2))
t = t[j] # filter
# Offsets
gxy = t[:, 2:4] # grid xy
gxi = gain[[2, 3]] - gxy # inverse
j, k = ((gxy % 1. < g) & (gxy > 1.)).T
l, m = ((gxi % 1. < g) & (gxi > 1.)).T
j = torch.stack((torch.ones_like(j), j, k, l, m))
t = t.repeat((5, 1, 1))[j]
offsets = (torch.zeros_like(gxy)[None] + off[:, None])[j]
else:
t = targets[0]
offsets = 0
# Define
b, c = t[:, :2].long().T # image, class
gxy = t[:, 2:4] # grid xy
gwh = t[:, 4:6] # grid wh
gij = (gxy - offsets).long()
gi, gj = gij.T # grid xy indices
# Append
a = t[:, 58].long() # anchor indices
indices.append((b, a, gj.clamp_(0, gain[3] - 1), gi.clamp_(0, gain[2] - 1))) # image, anchor, grid indices
tbox.append(torch.cat((gxy - gij, gwh), 1)) # box
anch.append(anchors[a]) # anchors
tcls.append(c) # class
#landmarks
lks = t[:,6:58]
#lks_mask = lks > 0
#lks_mask = lks_mask.float()
lks_mask = torch.where(lks < 0, torch.full_like(lks, 0.), torch.full_like(lks, 1.0))
#应该是关键点的坐标除以anch的宽高才对，便于模型学习。使用gwh会导致不同关键点的编码不同，没有统一的参考标准
for i in range(0, 52, 2):
lks[:, [i, i+1]] = (lks[:, [i, i+1]] - gij)
lks_mask_new = lks_mask
lmks_mask.append(lks_mask_new)
landmarks.append(lks)
#print('lks: ', lks.size())
return tcls, tbox, indices, anch, landmarks, lmks_mask
After using the instruction: torch.autograd.set_detect_anomaly(True)
I got the wrong position
# Classification
if model.nc > 1: # cls loss (only if multiple classes)
t = torch.full_like(ps[:, 57:], cn, device=device) # targets
t[range(n), tcls[i]] = cp
lcls = lcls + BCEcls(ps[:, 57:], t) # BCE
When I comment out the last line of code, the program runs smoothly
I really hope to get your help QAQ