lucky-xu-1994

Results 9 comments of lucky-xu-1994

> when converting the CenterNet-FPN_R50_1x > [03/20 10:56:30 d2.data.common]: Serializing 5000 elements to byte tensors and concatenating them all ... > [03/20 10:56:30 d2.data.common]: Serialized dataset takes 19.10 MiB >...

> @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。

> @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)...

> 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) >...

> Hi, I was checking the pb file converted from ckpt file provided in this repository. > **./summarize_graph --in_graph=ssd300_frozen_graph.pb** > No inputs spotted. > No variables spotted. > Found 1...

> do you know the input_node_name of ssd_300_vgg Hi,I am struggling in this problem, have you sovled this? please help!