syaringan357
syaringan357
At present, I can do the best.
import tensorflow as tf in_path = "../output/mobilefacenet/frozen_graphs/MobileFaceNet.pb" out_path = "../output/mobilefacenet/tflite/MobileFaceNet.tflite" input_tensor_name = ["input"] input_tensor_shape = {"input": [2, 112, 112, 3]} classes_tensor_name = ["embeddings"] converter = tf.lite.TFLiteConverter.from_frozen_graph(in_path, input_tensor_name, classes_tensor_name, input_shapes=input_tensor_shape) tflite_model...
哦，我不是用他原来那个pb转的，用他的ckpt重新固化一个pb，再转。
import os import tensorflow as tf from nets.MobileFaceNet import inference training_checkpoint = "../output/mobilefacenet/MobileFaceNet_TF.ckpt" OUTPUT_DIR = '../output/mobilefacenet/frozen_graphs' def freeze_graph_def(sess, output_node_names): # Replace all the variables in the graph with constants of...
凑合看把 上面都是代码
我也不太清楚，我也是按报错提示改的。可能是他一些代码经过长时间修改之后对不上了。
Sorry, I'm too busy recently. I haven't paid attention to GitHub for a long time. 1. The depth map is only used in training for back propagation. 2. Laplacian is...
Please provide an email address and I'll send it to you.
为什么这个付费的还没有蓝灯免费的速度快？
不过现在两会期间lantern已经完全挂了，这个还能用，虽然还是很慢。。。