frcnn

frcnn copied to clipboard

How to train on coco anyway?

The input data format this repo support is as follows:

# image-id
image-name
number of boxes
label x1 y1 x2 y2 difficulty
...

So if you like to use the input layer in this repo, you need convert coco to this format, or you can custom your input layer.

Oh, I see....

@makefile BTW, how to design anchor in terms of coco dataset? For those voc it's like this:

 "feat_stride": "16",
 "anchors": "-84, -40, 99, 55,
             -176,  -88,  191,   103,
             -360,  -184,   375,   100,
             -56,   -56,    71,    72,
             -120,  -120,   135,   135,
             -248,  -248,   263,   263,
             -36,   -80,    51,    95,
             -80,   -168,   95,    183,
             -168,  -344,   183,   359",
 "test_score_thresh": "0.5",
 "n_classes": "21",

How to generats anchors in terms of coco dataset?

Try to use examples/FRCNN/generate_anchors.py to generate anchors info.

@makefile Should I change anything in terms of different dataset? I can not found any where to set if I am not using voc.

You can adjust the settings in voc cfg file to adapt to different dataset.

I mean, should those anchors also changed? But I can not see any params to set in generate_anchors.py.

You can set params in function generate_anchors(base_size=16, ratios=[0.5, 1, 2], scales=2**np.arange(3, 6)).