weilanShi

How to make XML for negative sample (background image) due to large error detection? I made XML for the negative samples and removed the object nodes. However, the trained model...

如何继续训练

16

你好，作者，非常感谢提供tf的yolo，项目很好，但我还是有一个问题：请问如何在训练了一段时间中断了后继续加载之前的模型继续训练呢，目前跑完了设置的epoch，但loss还是比较大，所以想继续接着之前的训练，望回复! 万分感谢！

How to obtain the center point coordinates and depth values during NYU inference

4

I'm appreciating your great work. when i test own depth data, I can't get the center coordinates and depth values of hand bbox advance. Therefore, when I try to remove...

And there is my code to get pb model: import tensorflow as tf #from create_tf_record import * from tensorflow.python.framework import graph_util def freeze_graph(input_checkpoint,output_graph): output_node_names = "pre_hmap" saver = tf.train.import_meta_graph(input_checkpoint +...

How to train our own data set, and it is not included in the 30 category.

2

How to train our own dataset（one category）? and it is not included in the 30 category.How to make the annotations ?

The program can be trained, but during the training,but: This convolution is not supported by cudnn, MXNET convolution is applied

3

The program can be trained, but during the training, it has always been the following program: This convolution is not supported by cudnn, MXNET convolution is applied. What caused this...

推理速度

5

你好，非常感谢开源，请问有做相关的推理耗时的测评吗，速度咋样啊

'NoneType' object has no attribute 'decode'

3

你好，感谢贡献，感谢开源！我尝试转ckpt 模型至ncnn, 先将ckpt 转为了 .h5, 再使用你的方法转为ncnn , 在转的时候，报错如下： Traceback (most recent call last): File "keras2ncnn.py", line 1477, in H5dfParser(args.input_file).parse_graph(keras_graph) File "keras2ncnn.py", line 52, in __init__ self.model_config = json.loads(model_config_raw.decode('utf-8')) AttributeError: 'NoneType'...