xmyqsh
xmyqsh
in file [proposal_target_layer.py](https://github.com/xmyqsh/FPN/blob/master/lib/rpn_msr/proposal_target_layer.py) L101 `def calc_level(width, height): return min(5, max(2, int(4 + np.log2(np.sqrt(width * height) / 224)))) level = lambda roi : calc_level(roi[3] - roi[1], roi[4] - roi[2]) # roi:...
Hey man, How is your training result? The rpn_loss of my training result is many times larger than the FastRCNN loss. Do you think I should also add k =...
@Zehaos Good! I will try it. But how to evaluate RPN result, AP or AR? Do you know where has the definition of AR in Table 1, average recall?
@Johere You are right. Among the three layers of RPN, only proposal layer used in 'TEST' phase. Anchor target layer is used to generate the delta of anchors for RPN...
@Johere I implement the feature map(P2/P3/P4/P5) choosing operate in proposal layer in 'TEST' phase, and in proposal target layer in 'TRAIN' phase. If you implement this in roi_pooling_layer, be aware...
@Zehaos P6 should be included in RPN's head, but I encountered numerical problem(nan) during training when I added it. Have you encountered similar problem?
@Zehaos Same to you. What's your max pooling's kernel size, 3x3 or 1x1? And your learning rate is 0.02 as the paper says?
@Zehaos After use Kernel size=2, NAN disappeared... Thank you!
@Zehaos How many image_batch_size do you use in fast-rcnn of alternated training? Larger image_batch_size should help training?
@Feynman27 Good!