Comments (9)
@lucky-xu-1994 你好,你这个搞定了嘛?我发现找不到模型的输入输出节点
from ssd-tensorflow.
@lucky-xu-1994 你好,你这个搞定了嘛?我发现找不到模型的输入输出节点
你把ckpt文件的输入输出节点打印出来,如果是这个工程文件的的话,
我找到的是六个特征图的输出节点,每个特征图输出一个分类和位置回归,例如:第一个特征图是“ssd_512_vgg/softmax/Softmax”(分类),"ssd_512_vgg/block4_box/Reshape"(位置回归),要是想得到最终的结果,需要将所有层的输出综合一起做非极大值抑制,具体可以参考工程文件中的notebooks/ssd_notebook.ipynb,
输入节点是一个队列输入,如果想要方便测试单张图片,可以在冻结模型时通过输入占位符进行冻结。
from ssd-tensorflow.
可以加qq或微信吗?qq:843783062 微信:tk-conquer
from ssd-tensorflow.
@lucky-xu-1994 然后我就很迷惑
from ssd-tensorflow.
@lucky-xu-1994 然后我就很迷惑
你要打印的是节点名字,试试这个,找一下soft_max输出
from tensorflow.python import pywrap_tensorflow
import tensorflow as tf
import os
model_dir = '/home/pb/'
ckpt='/home/logs/model.ckpt-332005'
with tf.Session() as sess:
saver = tf.train.import_meta_graph(ckpt +'.meta', clear_devices=True)
graph_def = tf.get_default_graph().as_graph_def(add_shapes=True)
node_list = [n.name for n in graph_def.node]
result_file = os.path.join(model_dir,'result1.txt')
with open(result_file,'w+') as f:
for node in node_list:
#print("node_name", node)
f.write(node+'\n')
print('done')
from ssd-tensorflow.
import tensorflow as tf
import os
model_dir = './out/'
ckpt='F:/SSD/SSD-Tensorflow/train_model/model.ckpt-750'
with tf.Session() as sess:
saver = tf.train.import_meta_graph(ckpt +'.meta', clear_devices=True)
graph_def = tf.get_default_graph().as_graph_def(add_shapes=True)
node_list = [n.name for n in graph_def.node]
result_file = os.path.join(model_dir,'result1.txt')
with open(result_file,'w+') as f:
for node in node_list:
#print("node_name", node)
f.write(node+'\n')
print('done')
代码格式是这样的吧
from ssd-tensorflow.
import tensorflow as tf
import os
model_dir = './out/'
ckpt='F:/SSD/SSD-Tensorflow/train_model/model.ckpt-750'
with tf.Session() as sess:
saver = tf.train.import_meta_graph(ckpt +'.meta', clear_devices=True)
graph_def = tf.get_default_graph().as_graph_def(add_shapes=True)
node_list = [n.name for n in graph_def.node]
result_file = os.path.join(model_dir,'result1.txt')
with open(result_file,'w+') as f:
for node in node_list:
#print("node_name", node)
f.write(node+'\n')
print('done')代码格式是这样的吧
你把session下面的代码都放在会话结构中,然后仔细看一下网络的定义,找一下softmax输出
具体你可以参照 https://blog.csdn.net/guyuealian/article/details/82218092
以及https://blog.csdn.net/zkgoup/article/details/105657577?utm_medium=distribute.pc_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-1.nonecase&depth_1-utm_source=distribute.pc_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-1.nonecase
from ssd-tensorflow.
好的,谢谢
from ssd-tensorflow.
你好,我又来麻烦你了,哈哈,我找到的是六个特征图的输出节点,每个特征图输出一个分类和位置回归,例如:第一个特征图是“ssd_512_vgg/softmax/Softmax”(分类),"ssd_512_vgg/block4_box/Reshape"(位置回归),要是想得到最终的结果,需要将所有层的输出综合一起做非极大值抑制,具体可以参考工程文件中的notebooks/ssd_notebook.ipynb,
输入节点是一个队列输入,如果想要方便测试单张图片,可以在冻结模型时通过输入占位符进行冻结。
根据你之前说的,我现在也是得到了输入输出节点,现在是我想弄成可以发布服务的那种,那模型的输出就得是做过后处理的,请问一下如果将所有层的输出综合一起做非极大值抑制,我看了下那个推理文件,这个好像是得到6个输出节点后再进行后处理
from ssd-tensorflow.
Related Issues (20)
- SSD能训练png图片,但不能测试png图片吗? HOT 4
- The loss is not convergent and the test result is poor. It is recommended to use other versions.The loss is not convergent and the test result is poor. It is recommended to use other versions. HOT 2
- NotFoundError: NewRandomAccessFile failed to Create/Open
- You must supply the dataset directory with --dataset_dir
- I0313 15:10:55.695348 140095594268544 learning.py:507] global step 2290: loss = 24.0642 (4.784 sec/step)
- Train with 224*224*3 Input
- Clarification: TFE =/= TFX?
- ValueError: Cannot reshape a tensor with 3881472 elements to shape [32,84,38,4,21] (8580096 elements) for 'ssd_300_vgg/block4_box/Reshape_1'
- Optimizer epsilon default value too high
- more than 21 classes
- why the result of label is the same answer? HOT 1
- ValueError: Dimension 0 in both shapes must be equal, but are 412776 and 34928. Shapes are [412776] and [34928]. for 'ssd_losses/Select' (op: 'Select') with input shapes: [34928], [412776], [34928]. HOT 2
- How to prepare my own training data HOT 2
- loss and map
- can webcam demo or video demo be supplied?
- 运行train_ssd_network时报错 HOT 1
- > 根据前面人的提示,在代码中注释掉关于checkpoint就可以运行了。
- how many epochs ? HOT 1
- checkpoint loading error
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ssd-tensorflow.