Jitesh Malipeddi

I have the groundtruths and detections in the form of `x_min,y_min,x_max,y_max`. Can I use the order `x_min,y_max,x_max,y_min` to match the corresponding order of ` ` mentioned in the txt file...

Even I have the same question, did you find an answer to it? If so, could you please share the same?

Try reducing the dimension and see if it works?

You can use a .txt file for your annotation of the particular format. absoulte_path_to_image,x_min,y_min,x_max,y_max,class label. For example, 000000000071.jpg,261,139,275,142,car. You don't need to have a CSV file. If you already have...

You can check this link out. It may help you https://drive.google.com/drive/folders/1cCCDj9hXlRzAbwWOrm8Qk9cl0QOWimyT

In the annotation file, use something like /home/jitesh/Desktop/train/000000000071.jpg,261,139,275,142,car instead of 000000000071.jpg,261,139,275,142,car And in regard to your question about there being two different types of annotation files, annotation_train.txt is for training...

You can use an earlier version that works(0.16.0) from the releases page [here](https://github.com/sc0ty/subsync/releases) and choose the required installer based on the OS under the Assets section. Just don't update the...

Thank you for your response. Sorry for the delay It actually does not seem to work, when I am printing the shape, it is `torch.Size([1, 1])` The new error after...

> You can also manually updated the dic. Like this: > > ``` > state_dict =checkpoint['state_dict'] > from collections import OrderedDict > new_state_dict = OrderedDict() > > for k, v...

CUDA version 10.1 worked for me