seasonyang

the loss converge so slow

9

I am training my own data based on pre-trained checkpoint vgg16.chkp. My dataset is 1500 pictures，two classes contain 0：background and 1：myObject，my batch=50 **why loss converge so slow？！** `INFO:tensorflow:Recording summary at...

when will be the train stop？

9

I have trained my own dataset（they are 60 images of 4 classes） as fllow： 1、commd： DATASET_DIR=./tfrecords/voc2007 TRAIN_DIR=./logs/ CHECKPOINT_PATH=./checkpoints/ssd_300_vgg.ckpt python2 train_ssd_network.py \ --train_dir=${TRAIN_DIR} \ --dataset_dir=${DATASET_DIR} \ --dataset_name=pascalvoc_2007 \ --dataset_split_name=train \ --model_name=ssd_300_vgg...

How can I Speed up the modle

10

The speed is very slow, and imges delay to the camera. How to optimize it to speed up it's speed?

Clone this project and download weight from: https://1drv.ms/u/s!AuG441T6ysq5g1DHKEY4DJGkJh-c?e=i9nFph

3

cannot down load weight and test data.