上述211行附近的代码如下，请具体指出问题 def build_targets(self, p, targets): # Build targets for compute_loss(), input targets(image,class,x,y,w,h) na, nt = self.na, targets.shape[0] # number of anchors, targets tcls, tbox, indices, anch = [], [], [], [] gain = torch.ones(7, device=targets.device) # normalized to gridspace gain 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(self.nl): anchors = self.anchors[i] gain[2:6] = torch.tensor(p[i].shape)[[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] < self.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[:, 6].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 return tcls, tbox, indices, anch

根据你提供的代码，第 211 行出现错误的地方是在 indices.append((b, a, gj.clamp_(0, gain[3] - 1), gi.clamp_(0, gain[2] - 1))) 这一行。

问题出现在使用 clamp_() 函数时，尝试将 Float 类型的 gj 和 gi 转换为 __int64 类型。由于 clamp_() 函数会直接修改张量的值，而且 __int64 类型不能容纳 Float 类型的值，因此会导致类型转换错误。

要解决这个问题，你可以使用 clamp() 函数而不是 clamp_() 函数，这样就可以返回一个新的张量，而不会修改原始张量的值。修改代码如下：

indices.append((b, a, gj.clamp(0, int(gain[3]) - 1), gi.clamp(0, int(gain[2]) - 1)))  # image, anchor, grid indices

这样修改后，应该就能解决 RuntimeError: result type Float can't be cast to the desired output type __int64 的问题了。