-
There are a few broken links. Using https://www.brokenlinkcheck.com/broken-links.php I found 37.
-
Running the file using pretrain(weights) does nothing after the following output.
The required ffmpeg has been installed. In any case, I think the installation method may be wrong. What installatio…
-
Sorry to contact you again, how to draw a picture like Figure 2 has troubled me for several days, I look forward to your early reply, thank you very much.
-
Hi Authors,
I ran the code using the default configuration on Moving MNIST by directly executing `python3 main.py`.
The final MSE obtained after 1000 epochs is around 75.26 which is far higher t…
-
Thanks for sharing your work.Could you tell me how you train the non-id speace and what kind of loss did you use.Cause I find that there are seems not loss for non-id space training have been mentio…
-
Hi, I'm writing an article and have found/tested your implementation of the following structures:
CSPResNeXt50-PANet-SPP
CSPDarknet53-PANet-SPP
CSPResNet50-PANet-SPP
The question is do you ha…
-
Hi,
This work is very interesting! When can we see the training and evaluation code?
Looking forward to your reply.
yifan
-
Are multiple GPUs available?
-
Great job! In this paper, the top1 of 4bit mobilenetv2 is 72.0 and this is beyond SOTA. Is there a way that can reproduce this result?
-
I probably found an issue with the indexing of categories at coco evaluation. This might cause interchanged results for each category which would also affect AP(novel) and AP(base) since it is unknown…