PyramidBox
PyramidBox copied to clipboard
A Context-assisted Single Shot Face Detector in TensorFlow
How to convert to VOC format.
你好,我按照训练步骤训练了一版,但是效果没有给出的模型那么好,很多误检,是我哪里写的不对吗?代码我也没有改动
I have a question disturbed me. As we know, the anchor will be expanded to detect head and body from face anchors, but it is down-sampled to calculate IOU with...
I turned batch_size into 16 ,an error has occurred.
After running demo.py I am getting this error.Can you please help: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 return f(*args, **kwds) 2018-08-31 11:47:41.373697: W tensorflow/core/framework/allocator.cc:108]...
First of all, thanks for your contribution of sharing your work. I'm wondering if there' re any difference(other than hyperparameters) between the original code and this work that results in...
I didn't know how to transform data to pascal format, so I just re-wrote the code for generating the training data. Now it can directly generate tfrecord from original dataset...
fune train ,after 200000+ the loss is very large?
另外,他基于s3fd,控制低层负样本,找最大的负样本和正样本训练时怎么实现的啊,就是max-in-out这个?谢谢