1 Star 0 Fork 0

崔萌/看图说话中文版移动端

加入 Gitee
与超过 1200万 开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)
免费加入
该仓库未声明开源许可证文件(LICENSE),使用请关注具体项目描述及其代码上游依赖。
克隆/下载
toCoreMl.sh 1.16 KB
一键复制 编辑 原始数据 按行查看 历史
崔萌 提交于 2018-11-30 15:46 . ddd
# Path to checkpoint file or a directory containing checkpoint files. Passing
# a directory will only work if there is also a file named 'checkpoint' which
# lists the available checkpoints in the directory. It will not work if you
# point to a directory with just a copy of a model checkpoint: in that case,
# you will need to pass the checkpoint path explicitly.
CHECKPOINT_PATH="${PWD}/im2txt/model/train"
# Vocabulary file generated by the preprocessing script.
VOCAB_FILE="${PWD}/im2txt/data/mscoco/word_counts.txt"
# JPEG image file to caption.
#IMAGE_FILE="${PWD}/im2txt/data/mscoco/raw-data/val2014/COCO_val2014_000000224477.jpg"
IMAGE_FILE=""
#MAGE_FILE="${PWD}/im2txt/data/mscoco/raw-data/val2014/COCO_val2014_000000224477.jpg"
# Build the inference binary.
#cd research/im2txt
bazel build -c opt //im2txt:run_inference
# Ignore GPU devices (only necessary if your GPU is currently memory
# constrained, for example, by running the training script).
export CUDA_VISIBLE_DEVICES=""
# Run inference to generate captions.
bazel-bin/im2txt/run_inference \
--checkpoint_path=${CHECKPOINT_PATH} \
--vocab_file=${VOCAB_FILE} \
--input_files=${IMAGE_FILE}
python toCoreMl.py
马建仓 AI 助手
尝试更多
代码解读
代码找茬
代码优化
1
https://gitee.com/diamondcm/im2txt-chinese-mobile-end.git
[email protected]:diamondcm/im2txt-chinese-mobile-end.git
diamondcm
im2txt-chinese-mobile-end
看图说话中文版移动端
master

搜索帮助