the error on train.py when the iteration=120170 about ssd_pytorch

[acm5656]

I think you can test whether the object can be detected by using the weight of 120000 rounds of training. The loss in my training is also around 2, and if you want to obtain lower loss, you can consider reducing the learning rate.

[xlm998]

how to test not a single image ,and how to eval this train and test result,such as AP and total recall?can you help me?

[acm5656]

I'm sorry that this version doesn't provide the method to eval train and test result. I will complete this function in my spare time.

[xlm998]

thank you for you answer,when use the ssd-pytorch-master on https://github.com/amdegroot/ssd.pytorch, there is a error in training

iter 900 || Loss: 6.6272 || timer: 0.1010 sec.
iter 910 || Loss: 7.0335 || timer: 0.1023 sec.
iter 920 || Loss: 6.6000 || timer: 0.1001 sec.
iter 930 || Loss: 6.7137 || timer: 0.1013 sec.
iter 940 || Loss: 6.9450 || timer: 0.1027 sec.
iter 950 || Loss: 6.5815 || timer: 0.1038 sec.
iter 960 || Loss: 6.8804 || timer: 0.1021 sec.
iter 970 || Loss: 6.6749 || timer: 0.1279 sec.
iter 980 || Loss: 6.4802 || timer: 0.1018 sec.
iter 990 || Loss: 6.1978 || timer: 0.1184 sec.
iter 1000 || Loss: 6.7934 || timer: 0.1019 sec.
iter 1010 || Loss: 6.5664 || timer: 0.1028 sec.
iter 1020 || Loss: 6.6167 || timer: 0.0977 sec.
iter 1030 || Loss: 6.3809 || Traceback (most recent call last):
File "train.py", line 261, in
train()
File "train.py", line 166, in train
images, targets = next(batch_iterator)
File "/home/xlm/anaconda3/envs/M2Det/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 627, in next
raise StopIteration
StopIteration

when i follow the issues in https://github.com/amdegroot/ssd.pytorch

change
images, targets = next(batch_iterator)
with
try:
images,targets = next(batch_iterator)
except StopIteration:
bath_interator = iter(data_loader)
images,targets = next(batch_iterator)
but this error was still occured.

can you help me to address this problem