FSCE
FSCE copied to clipboard
You can use the code below to visualize the features. ``` def plot_embedding(data, label, title,show=None): # param data:data # param label:label # param title:title of output # param show:(int) if...
Traceback (most recent call last): File "tools/train_net.py", line 124, in launch( File "/home/sjk/mrch/FSCE/fsdet/engine/launch.py", line 52, in launch main_func(*args) File "tools/train_net.py", line 100, in main cfg = setup(args) File "tools/train_net.py", line...
When I run the training code with ResNet152 backbone, I got this error every time even though I’d changed the learning rate. Anyone met this problem?
Could you please provide these files for following command?Thank you! python tools/run_experiments.py --num-gpus 2 --shots 1 2 3 5 10 --seeds 0 30 --split 1
1. I notice that in fine-tune stage, the COCO dataset only have one instance per image, despite of there may be number of potential instances, like some image contained chairs,...
Hi, In the Table 2 of the paper, you compare the average ap of mutiple runs of 10 seeds with the results given by TFA which is a average one...
when i training on myself dataset, it will occurs this error, I already change categories of coco `-- Process 1 terminated with the following error: Traceback (most recent call last):...
AssertionError: get_event_storage() has to be called inside a 'with EventStorage(...)' context!
I just have one gpu 3090. And I do not change config, like lr and batchsize, how can I get the same result with paper? My nAP50 = 60.8 (paper...
Hello, thank you for your work, I ran python setup.py build develop this line of code, encountered the following problem, is there any way to solve it? 文件 “setup.py”, line...