-
I tried to run your code for the flickr30k test dataset, but it is giving very low final value of recall.
Can you confirm if this is the case with you as well...
- Raschka book
1. Math prerequisites
Taking a derivative to find a point of minimum or maxim…
-
I cannnot reopen issue #12.
Actually, when I only train the first 40 base classes using the configs in the file "warp_faster_rcnn_R_50_C4_1x.yaml", the AP50 was about 30%. I think it is not reasonabl…
-
### System information
- **What is the top-level directory of the model you are using**: object_detection
- **Have I written custom code (as opposed to using a stock example script provided in Tens…
-
How many epochs did u run in order to obtain the accuracy/error you claimed? I haven't found you have documented that anywhere. If you could explain your training policy a little bit more?
-
Please correct me if im wrong, but should not we have validation dataset while we train ?
I am looking at cifar examples and i noticed that we dont have validation dataset, we just have train and tes…
-
Why use the GMACs？GMACs is different with GFLOPs.
-
I am experiencing an issue when running the 'train.py' command.
This error keeps reoccurring:
File "train.py", line 52, in
from object_detection.builders import model_builder
File "C:…
-
Hi Luowei,
I am trying to get extract_feat_flickr30k to work, and am having issues, even after following https://github.com/LuoweiZhou/detectron-vlp/issues/2
The traceback is below.
Tracebac…