xview2_1st_place_solution

xview2_1st_place_solution copied to clipboard

Trained mode wights link is not available

3

Thanks for your great job. May I ask for the latest Trained mode wights link? Thanks.

yepengliu

MilenioScience

Add pip upgrade in Dockerfile

1

When I build the **Dockerfile**, it kept of on building the wheel for opencv-python. So, this issue is resolved pip upgrade.

mmuneeburahman

what the purpose of those code?

1

` msk[..., 1][msk[..., 2:].max(axis=2)] = False msk[..., 3][msk[..., 2]] = False msk[..., 4][msk[..., 2]] = False msk[..., 4][msk[..., 3]] = False msk[..., 0][msk[..., 1:].max(axis=2)] = False ` I have a...

zhijiejia

Hi, I have a question about the validate function of classification stage. The codes are in def validate(net,data_loader), train50_cls_cce.py. ` for j in range(msks.shape[0]): # msks.shape[0] is batch size tp[4]...

Kittywyk

Which model is the best one?

2

Thanks to your excellent work! looks like you use several models separately (ResNet34, SeNet154...). May I ask which one has the best results? i.e., from which model does the 1st...

Feiyu-Chen-THU

Can you please give insight into the need for all kinds of randomized transformation on images? And how it is going to help in model? Thanks in advance

shivamspj