tensorflow的keras沒有外部可視化配置文件,需要使用netron查看模型參數(shù),或者從程序中打印出來,

打印代碼:

def get_all_layernames():"""get all layers name"""model_dir = os.path.join(ROOT_DIR, 'stru/')pb_file_path = os.path.join(ROOT_DIR, 'ModelTF/IncepV2MaskFrozen.pb')from tensorflow.python.platform import gfilesess = tf.Session()# with gfile.FastGFile(pb_file_path + 'model.pb', 'rb') as f:with gfile.FastGFile(pb_file_path, 'rb') as f:graph_def = tf.GraphDef()graph_def.ParseFromString(f.read())sess.graph.as_default()tf.import_graph_def(graph_def, name='')tensor_name_list = [tensor.name for tensor in tf.get_default_graph().as_graph_def().node]for tensor_name in tensor_name_list:print(tensor_name, '\n')""""---------------------作者：醉雨軒Y來源：CSDN原文：https: // blog.csdn.net / miao0967020148 / article / details / 89434253版權聲明：本文為博主原創(chuàng)文章，轉載請附上博文鏈接！"""return

顯示結果:

2019-05-28 14:28:50.036031: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1097] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4941 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060 6GB, pci bus id: 0000:01:00.0, compute capability: 6.1)
Const

ToFloat

Const_1

ToFloat_1

Const_2

ToFloat_2

image_tensor? #輸入層名稱

ToFloat_3

Preprocessor/map/Shape

Preprocessor/map/strided_slice/stack

Preprocessor/map/strided_slice/stack_1

......................

add_1/y

add_1

detection_boxes

detection_scores

detection_classes

num_detections

detection_masks#最后輸出層

?

?

創(chuàng)作挑戰(zhàn)賽新人創(chuàng)作獎勵來咯，堅持創(chuàng)作打卡瓜分現(xiàn)金大獎

總結

以上是生活随笔為你收集整理的CNN: 查看tensorflow Pb模型所有层的名字的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。