han

icon location Alright,let's surf on the time.

Results 11 issues of han

How about add Senet to vgg16?Can it achieve?Thx

1 comment

Recall and Precision

has someone evaluate recall and precision,what is your result and how to evaluate them.Thx a lot.

precision is too low,who know why.thx

4 comment

when i make..thx

1 comment

python setup.py build_ext --inplace File "setup.py", line 84 print extra_postargs ^ SyntaxError: Missing parentheses in call to 'print'

python setup.py build_ext --inplace File "setup.py", line 84 print extra_postargs ^ SyntaxError: Missing parentheses in call to 'print'

When test picture doesnt have anchor.How to solve it .thx

Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same

Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same

Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.

thx

when i run eval_refinedet.py

Traceback (most recent call last): File "eval.py", line 446, in thresh=args.confidence_threshold) File "eval.py", line 420, in test_net evaluate_detections(all_boxes, output_dir, dataset) File "eval.py", line 425, in evaluate_detections do_python_eval(output_dir) File "eval.py", line...