姜涛

how to train the next stages?

7

I apply this method to our own dataset and work well. thanks for your work and code. but only trained one stage,i wanna train more stages, could u give me...

mat_ratio = tf.map_fn(lambda x:(tf.cond(x > 0,lambda: 1/x,lambda:float(args.batch_size))),mat_ratio)

2

so damn hard to understand. can someone help me~~~~~~~~

时隔快一年了,还是没弄懂为什么在替换了MobilentV2后,没法训练STAGE2.是因为mobilenet本身的特性么?

error on trainingsetpreparation

2

stupid misstake.0.0

如果把stage2 也换成mobilenet，有人试过么？

3

没法训练，一直在爆内存。

crop_size = min(crop_size, objcenter[0] / width * min_shape * 2. - 1.) so damn hard to understand.

2

crop_size = min(crop_size, objcenter[0] / width * min_shape * 2. - 1.) crop_size = min(crop_size, (bimg.shape[1] - objcenter[0]) / width * min_shape * 2. - 1) crop_size = min(crop_size, objcenter[1]...

thaks for u sharing.

求好心人解答 多谢。