把tensorflow保存的checkpoint类型模型冻结，转化为.pb模型输出。调用方法参见我的博文https://blog.csdn.net/weixin_41864878/article/details/84957681
2021-09-17 11:45:25
1KB
1
运行下列脚本，可以打印出模型各个节点变量的名称：
from tensorflow.python import pywrap_tensorflow
import os
checkpoint_path=os.path.join('model.ckpt-131805')
reader=pywrap_tensorflow.NewCheckpointReader(checkpoint_path)
var_to_shape_map=reader.get_variable_to_shape_map()
for key in var_to_shape_map:
print 'tensor_name: ',
2021-09-17 11:02:33
28KB
1
using Neural Networks (SSD) on Tensorflow to do hand detect.
https://github.com/molyswu/hand_detection
2021-09-14 13:09:13
4.68MB
1
using Neural Networks (SSD) on Tensorflow to do hand detect.
https://github.com/molyswu/hand_detection
2021-09-14 13:09:13
26KB
1
using Neural Networks (SSD) on Tensorflow to do hand detect.
https://github.com/molyswu/hand_detection
2021-09-14 13:09:12
84.3MB
1
mobilenet_v2_1.0_224的cpkt文件,有时候下载不了.....做个备份
https://github.com/tensorflow/models/tree/master/research/slim/#Pretrained
2021-08-17 15:44:26
74.68MB
1
Note: SSD300* and SSD512* are the latest models. Current code should reproduce these results.
2021-08-04 12:59:54
93.01MB
1
Semantic-Segmentation-Suite 的ckpt转 pb代码，根据最后一层更改。
2021-05-19 10:24:21
2KB
1