search

abduallahmohamed / Social-STGCNN

Code for "Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction" CVPR 2020
MIT License
483 stars 141 forks source link

is the loss calculation wrong? #51

Closed QiyuLuo closed 2 years ago

QiyuLuo commented 3 years ago

In train.py L187-L198, is the loss calculation wrong? loss is the mean value of a batch. The final printed result loss_batch is divided by batch_count, which should be divided by the number of gradient return.

loss = loss/args.batch_size
is_fst_loss = True
loss.backward()

if args.clip_grad is not None:
    torch.nn.utils.clip_grad_norm_(model.parameters(),args.clip_grad)

optimizer.step()
#Metrics
loss_batch += loss.item()
print('TRAIN:','\t Epoch:', epoch,'\t Loss:',loss_batch/batch_count)

And I have another question. In the training process, loss is negative, What kind of case is convergence? Thank you for your reply.

abduallahmohamed commented 2 years ago

Hi, The batch size is 1 the more negative the better for the loss( but watch out overfitting)