其他分享
首页 > 其他分享> > TensorFlow2 models

TensorFlow2 models

作者:互联网

TensorFlow2  models

git clone https://github.com/tensorflow/models.git

(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project$ git clone https://github.com/tensorflow/models.git
Cloning into 'models'...
remote: Enumerating objects: 72952, done.
remote: Counting objects: 100% (129/129), done.
remote: Compressing objects: 100% (78/78), done.
remote: Total 72952 (delta 63), reused 107 (delta 49), pack-reused 72823
Receiving objects: 100% (72952/72952), 579.33 MiB | 7.95 MiB/s, done.
Resolving deltas: 100% (51631/51631), done.
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project$ 
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project$ 
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project$ 

 

1、sudo apt install docker.io

(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models_20220517/research$ 
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models_20220517/research$ sudo apt install docker.io
Reading package lists... Done
Building dependency tree       
Reading state information... Done
The following packages were automatically installed and are no longer required:
  libcbor0.6 libfido2-1
Use 'sudo apt autoremove' to remove them.
The following additional packages will be installed:
  bridge-utils containerd git git-man liberror-perl pigz runc ubuntu-fan
Suggested packages:
  ifupdown aufs-tools btrfs-progs cgroupfs-mount | cgroup-lite debootstrap docker-doc rinse zfs-fuse | zfsutils git-daemon-run | git-daemon-sysvinit git-doc git-el git-email git-gui gitk gitweb git-cvs git-mediawiki git-svn
The following NEW packages will be installed:
  bridge-utils containerd docker.io git git-man liberror-perl pigz runc ubuntu-fan
0 upgraded, 9 newly installed, 0 to remove and 92 not upgraded.
Need to get 79.6 MB of archives.
After this operation, 398 MB of additional disk space will be used.
Do you want to continue? [Y/n] y
Get:1 http://security.ubuntu.com/ubuntu focal-security/main amd64 runc amd64 1.0.0~rc95-0ubuntu1~20.04.2 [4,087 kB]
Get:2 http://cn.archive.ubuntu.com/ubuntu focal/universe amd64 pigz amd64 2.4-1 [57.4 kB]
Get:3 http://cn.archive.ubuntu.com/ubuntu focal/main amd64 bridge-utils amd64 1.6-2ubuntu1 [30.5 kB]
Get:4 http://cn.archive.ubuntu.com/ubuntu focal/main amd64 liberror-perl all 0.17029-1 [26.5 kB]
Get:5 http://cn.archive.ubuntu.com/ubuntu focal/main amd64 ubuntu-fan all 0.12.13 [34.5 kB]
Get:6 http://security.ubuntu.com/ubuntu focal-security/main amd64 containerd amd64 1.5.5-0ubuntu3~20.04.2 [33.0 MB]
Get:7 http://security.ubuntu.com/ubuntu focal-security/universe amd64 docker.io amd64 20.10.7-0ubuntu5~20.04.2 [36.9 MB]                                                                                                                        
Get:8 http://security.ubuntu.com/ubuntu focal-security/main amd64 git-man all 1:2.25.1-1ubuntu3.4 [885 kB]                                                                                                                                      
Get:9 http://security.ubuntu.com/ubuntu focal-security/main amd64 git amd64 1:2.25.1-1ubuntu3.4 [4,560 kB]                                                                                                                                      
Fetched 79.6 MB in 12s (6,714 kB/s)                                                                                                                                                                                                             
Preconfiguring packages ...
Selecting previously unselected package pigz.
(Reading database ... 153110 files and directories currently installed.)
Preparing to unpack .../0-pigz_2.4-1_amd64.deb ...
Unpacking pigz (2.4-1) ...
Selecting previously unselected package bridge-utils.
Preparing to unpack .../1-bridge-utils_1.6-2ubuntu1_amd64.deb ...
Unpacking bridge-utils (1.6-2ubuntu1) ...
Selecting previously unselected package runc.
Preparing to unpack .../2-runc_1.0.0~rc95-0ubuntu1~20.04.2_amd64.deb ...
Unpacking runc (1.0.0~rc95-0ubuntu1~20.04.2) ...
Selecting previously unselected package containerd.
Preparing to unpack .../3-containerd_1.5.5-0ubuntu3~20.04.2_amd64.deb ...
Unpacking containerd (1.5.5-0ubuntu3~20.04.2) ...
Selecting previously unselected package docker.io.
Preparing to unpack .../4-docker.io_20.10.7-0ubuntu5~20.04.2_amd64.deb ...
Unpacking docker.io (20.10.7-0ubuntu5~20.04.2) ...
Selecting previously unselected package liberror-perl.
Preparing to unpack .../5-liberror-perl_0.17029-1_all.deb ...
Unpacking liberror-perl (0.17029-1) ...
Selecting previously unselected package git-man.
Preparing to unpack .../6-git-man_1%3a2.25.1-1ubuntu3.4_all.deb ...
Unpacking git-man (1:2.25.1-1ubuntu3.4) ...
Selecting previously unselected package git.
Preparing to unpack .../7-git_1%3a2.25.1-1ubuntu3.4_amd64.deb ...
Unpacking git (1:2.25.1-1ubuntu3.4) ...
Selecting previously unselected package ubuntu-fan.
Preparing to unpack .../8-ubuntu-fan_0.12.13_all.deb ...
Unpacking ubuntu-fan (0.12.13) ...
Setting up runc (1.0.0~rc95-0ubuntu1~20.04.2) ...
Setting up liberror-perl (0.17029-1) ...
Setting up bridge-utils (1.6-2ubuntu1) ...
Setting up pigz (2.4-1) ...
Setting up git-man (1:2.25.1-1ubuntu3.4) ...
Setting up containerd (1.5.5-0ubuntu3~20.04.2) ...
Created symlink /etc/systemd/system/multi-user.target.wants/containerd.service → /lib/systemd/system/containerd.service.
Setting up ubuntu-fan (0.12.13) ...
Created symlink /etc/systemd/system/multi-user.target.wants/ubuntu-fan.service → /lib/systemd/system/ubuntu-fan.service.
Setting up docker.io (20.10.7-0ubuntu5~20.04.2) ...
Adding group `docker' (GID 135) ...
Done.
Created symlink /etc/systemd/system/multi-user.target.wants/docker.service → /lib/systemd/system/docker.service.
Created symlink /etc/systemd/system/sockets.target.wants/docker.socket → /lib/systemd/system/docker.socket.
Setting up git (1:2.25.1-1ubuntu3.4) ...
Processing triggers for man-db (2.9.1-1) ...
Processing triggers for systemd (245.4-4ubuntu3.15) ...
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models_20220517/research$ 
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models_20220517/research$ 
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models_20220517/research$ 
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models_20220517/research$ 
View Code

 

2、sudo docker build -f research/object_detection/dockerfiles/tf2/Dockerfile -t od .

(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models$ 
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models$ sudo docker build -f research/object_detection/dockerfiles/tf2/Dockerfile -t od .
Sending build context to Docker daemon  673.6MB
Step 1/15 : FROM tensorflow/tensorflow:2.2.0-gpu
2.2.0-gpu: Pulling from tensorflow/tensorflow
7ddbc47eeb70: Pull complete 
c1bbdc448b72: Pull complete 
8c3b70e39044: Pull complete 
45d437916d57: Pull complete 
d8f1569ddae6: Pull complete 
85386706b020: Pull complete 
ee9b457b77d0: Pull complete 
ba76dd394d58: Pull complete 
257975142b4d: Pull complete 
f41a1fbb4940: Pull complete 
fdb48ae01855: Pull complete 
7be34d8326b1: Pull complete 
07e47fcee106: Pull complete 
d1aa47ec9c67: Pull complete 
9bfed42b7d3e: Pull complete 
52a5fe293ce3: Pull complete 
Digest: sha256:3f8f06cdfbc09c54568f191bbc54419b348ecc08dc5e031a53c22c6bba0a252e
Status: Downloaded newer image for tensorflow/tensorflow:2.2.0-gpu
 ---> f5ba7a196d56
Step 2/15 : ARG DEBIAN_FRONTEND=noninteractive
 ---> Running in 7823c560f901
Removing intermediate container 7823c560f901
 ---> 1bef854da142
Step 3/15 : RUN apt-get update && apt-get install -y     git     gpg-agent     python3-cairocffi     protobuf-compiler     python3-pil     python3-lxml     python3-tk     wget
 ---> Running in 2ad952efb0c0
Get:1 https://developer.download.nvidia.cn/compute/cuda/repos/ubuntu1804/x86_64  InRelease [1581 B]
Err:1 https://developer.download.nvidia.cn/compute/cuda/repos/ubuntu1804/x86_64  InRelease
  The following signatures couldn't be verified because the public key is not available: NO_PUBKEY A4B469963BF863CC
Hit:3 http://archive.ubuntu.com/ubuntu bionic InRelease
Get:4 http://security.ubuntu.com/ubuntu bionic-security InRelease [88.7 kB]
Ign:2 https://developer.download.nvidia.cn/compute/machine-learning/repos/ubuntu1804/x86_64  InRelease
Get:5 https://developer.download.nvidia.cn/compute/machine-learning/repos/ubuntu1804/x86_64  Release [564 B]
Get:6 https://developer.download.nvidia.cn/compute/machine-learning/repos/ubuntu1804/x86_64  Release.gpg [833 B]
Get:7 http://archive.ubuntu.com/ubuntu bionic-updates InRelease [88.7 kB]
Get:8 https://developer.download.nvidia.cn/compute/machine-learning/repos/ubuntu1804/x86_64  Packages [73.8 kB]
Get:9 http://archive.ubuntu.com/ubuntu bionic-backports InRelease [74.6 kB]
Get:10 http://security.ubuntu.com/ubuntu bionic-security/multiverse amd64 Packages [21.1 kB]
Get:11 http://archive.ubuntu.com/ubuntu bionic-updates/multiverse amd64 Packages [29.8 kB]
Get:12 http://security.ubuntu.com/ubuntu bionic-security/restricted amd64 Packages [932 kB]
Get:13 http://archive.ubuntu.com/ubuntu bionic-updates/universe amd64 Packages [2277 kB]
Get:14 http://security.ubuntu.com/ubuntu bionic-security/main amd64 Packages [2763 kB]
Get:15 http://archive.ubuntu.com/ubuntu bionic-updates/restricted amd64 Packages [966 kB]
Get:16 http://archive.ubuntu.com/ubuntu bionic-updates/main amd64 Packages [3197 kB]
Get:17 http://security.ubuntu.com/ubuntu bionic-security/universe amd64 Packages [1503 kB]
Get:18 http://archive.ubuntu.com/ubuntu bionic-backports/universe amd64 Packages [12.9 kB]
Get:19 http://archive.ubuntu.com/ubuntu bionic-backports/main amd64 Packages [12.2 kB]
Reading package lists...
W: GPG error: https://developer.download.nvidia.cn/compute/cuda/repos/ubuntu1804/x86_64  InRelease: The following signatures couldn't be verified because the public key is not available: NO_PUBKEY A4B469963BF863CC
E: The repository 'https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64  InRelease' is no longer signed.
The command '/bin/bash -c apt-get update && apt-get install -y     git     gpg-agent     python3-cairocffi     protobuf-compiler     python3-pil     python3-lxml     python3-tk     wget' returned a non-zero code: 100
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models$ 
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models$ 
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models$ 
View Code

 

3、cd research

(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models$ 
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models$ cd research
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models/research$ 
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models/research$ 

 

4、protoc object_detection/protos/*.proto --python_out=.

 

5、cp object_detection/packages/tf2/setup.py .

 

6、python -m pip install --use-feature=2020-resolver .

(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models/research$ 
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models/research$ python -m pip install --use-feature=2020-resolver .
WARNING: --use-feature=2020-resolver no longer has any effect, since it is now the default dependency resolver in pip. This will become an error in pip 21.0.
Processing /home/bim/tensorflow_project/models/research
  DEPRECATION: A future pip version will change local packages to be built in-place without first copying to a temporary directory. We recommend you use --use-feature=in-tree-build to test your packages with this new behavior before it becomes the default.
   pip 21.3 will remove support for this functionality. You can find discussion regarding this at https://github.com/pypa/pip/issues/7555.
Collecting avro-python3
  Downloading avro-python3-1.10.2.tar.gz (38 kB)
Collecting apache-beam
  Downloading apache_beam-2.38.0-cp37-cp37m-manylinux2010_x86_64.whl (10.2 MB)
     |████████████████████████████████| 10.2 MB 8.2 MB/s 
Requirement already satisfied: pillow in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from object-detection==0.1) (9.1.0)
Collecting lxml
  Using cached lxml-4.8.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl (6.4 MB)
Requirement already satisfied: matplotlib in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from object-detection==0.1) (3.5.2)
Collecting Cython
  Using cached Cython-0.29.29-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl (1.9 MB)
Collecting contextlib2
  Using cached contextlib2-21.6.0-py2.py3-none-any.whl (13 kB)
Collecting tf-slim
  Using cached tf_slim-1.1.0-py2.py3-none-any.whl (352 kB)
Requirement already satisfied: six in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from object-detection==0.1) (1.16.0)
Requirement already satisfied: pycocotools in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from object-detection==0.1) (2.0.4)
Collecting lvis
  Downloading lvis-0.5.3-py3-none-any.whl (14 kB)
Requirement already satisfied: scipy in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from object-detection==0.1) (1.4.1)
Collecting pandas
  Using cached pandas-1.1.5-cp37-cp37m-manylinux1_x86_64.whl (9.5 MB)
Collecting tf-models-official>=2.5.1
  Using cached tf_models_official-2.8.0-py2.py3-none-any.whl (2.2 MB)
Collecting tensorflow_io
  Downloading tensorflow_io-0.25.0-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (23.4 MB)
     |████████████████████████████████| 23.4 MB 8.8 MB/s 
Requirement already satisfied: keras in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from object-detection==0.1) (2.3.1)
Requirement already satisfied: opencv-python-headless in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from tf-models-official>=2.5.1->object-detection==0.1) (4.5.5.64)
Collecting oauth2client
  Using cached oauth2client-4.1.3-py2.py3-none-any.whl (98 kB)
Collecting tensorflow-datasets
  Using cached tensorflow_datasets-4.5.2-py3-none-any.whl (4.2 MB)
Collecting py-cpuinfo>=3.3.0
  Using cached py_cpuinfo-8.0.0-py3-none-any.whl
Collecting sacrebleu
  Using cached sacrebleu-2.0.0-py3-none-any.whl (90 kB)
Collecting kaggle>=1.3.9
  Using cached kaggle-1.5.12-py3-none-any.whl
Collecting tensorflow-hub>=0.6.0
  Using cached tensorflow_hub-0.12.0-py2.py3-none-any.whl (108 kB)
Collecting seqeval
  Using cached seqeval-1.2.2-py3-none-any.whl
Collecting gin-config
  Using cached gin_config-0.5.0-py3-none-any.whl (61 kB)
Collecting google-api-python-client>=1.6.7
  Downloading google_api_python_client-2.48.0-py2.py3-none-any.whl (8.5 MB)
     |████████████████████████████████| 8.5 MB 9.3 MB/s 
Collecting tensorflow-text~=2.8.0
  Using cached tensorflow_text-2.8.2-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (4.9 MB)
Requirement already satisfied: numpy>=1.15.4 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from tf-models-official>=2.5.1->object-detection==0.1) (1.18.5)
Collecting psutil>=5.4.3
  Using cached psutil-5.9.0-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (280 kB)
Collecting sentencepiece
  Using cached sentencepiece-0.1.96-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.2 MB)
Collecting tensorflow-addons
  Using cached tensorflow_addons-0.16.1-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (1.1 MB)
Collecting tensorflow~=2.8.0
  Using cached tensorflow-2.8.1-cp37-cp37m-manylinux2010_x86_64.whl (497.9 MB)
Collecting tensorflow-model-optimization>=0.4.1
  Using cached tensorflow_model_optimization-0.7.2-py2.py3-none-any.whl (237 kB)
Collecting pyyaml<6.0,>=5.1
  Using cached PyYAML-5.4.1-cp37-cp37m-manylinux1_x86_64.whl (636 kB)
Collecting google-api-core!=2.0.*,!=2.1.*,!=2.2.*,!=2.3.0,<3.0.0dev,>=1.31.5
  Using cached google_api_core-2.7.3-py3-none-any.whl (114 kB)
Collecting google-auth-httplib2>=0.1.0
  Using cached google_auth_httplib2-0.1.0-py2.py3-none-any.whl (9.3 kB)
Collecting uritemplate<5,>=3.0.1
  Using cached uritemplate-4.1.1-py2.py3-none-any.whl (10 kB)
Collecting httplib2<1dev,>=0.15.0
  Using cached httplib2-0.20.4-py3-none-any.whl (96 kB)
Requirement already satisfied: google-auth<3.0.0dev,>=1.16.0 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from google-api-python-client>=1.6.7->tf-models-official>=2.5.1->object-detection==0.1) (1.35.0)
Requirement already satisfied: requests<3.0.0dev,>=2.18.0 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from google-api-core!=2.0.*,!=2.1.*,!=2.2.*,!=2.3.0,<3.0.0dev,>=1.31.5->google-api-python-client>=1.6.7->tf-models-official>=2.5.1->object-detection==0.1) (2.27.1)
Collecting googleapis-common-protos<2.0dev,>=1.52.0
  Using cached googleapis_common_protos-1.56.1-py2.py3-none-any.whl (211 kB)
Requirement already satisfied: protobuf>=3.12.0 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from google-api-core!=2.0.*,!=2.1.*,!=2.2.*,!=2.3.0,<3.0.0dev,>=1.31.5->google-api-python-client>=1.6.7->tf-models-official>=2.5.1->object-detection==0.1) (3.20.1)
Requirement already satisfied: pyasn1-modules>=0.2.1 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from google-auth<3.0.0dev,>=1.16.0->google-api-python-client>=1.6.7->tf-models-official>=2.5.1->object-detection==0.1) (0.2.8)
Requirement already satisfied: rsa<5,>=3.1.4 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from google-auth<3.0.0dev,>=1.16.0->google-api-python-client>=1.6.7->tf-models-official>=2.5.1->object-detection==0.1) (4.8)
Requirement already satisfied: cachetools<5.0,>=2.0.0 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from google-auth<3.0.0dev,>=1.16.0->google-api-python-client>=1.6.7->tf-models-official>=2.5.1->object-detection==0.1) (4.2.4)
Requirement already satisfied: setuptools>=40.3.0 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from google-auth<3.0.0dev,>=1.16.0->google-api-python-client>=1.6.7->tf-models-official>=2.5.1->object-detection==0.1) (61.2.0)
Requirement already satisfied: pyparsing!=3.0.0,!=3.0.1,!=3.0.2,!=3.0.3,<4,>=2.4.2 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from httplib2<1dev,>=0.15.0->google-api-python-client>=1.6.7->tf-models-official>=2.5.1->object-detection==0.1) (3.0.9)
Requirement already satisfied: urllib3 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from kaggle>=1.3.9->tf-models-official>=2.5.1->object-detection==0.1) (1.26.9)
Collecting python-slugify
  Using cached python_slugify-6.1.2-py2.py3-none-any.whl (9.4 kB)
Collecting tqdm
  Using cached tqdm-4.64.0-py2.py3-none-any.whl (78 kB)
Requirement already satisfied: python-dateutil in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from kaggle>=1.3.9->tf-models-official>=2.5.1->object-detection==0.1) (2.8.2)
Requirement already satisfied: certifi in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from kaggle>=1.3.9->tf-models-official>=2.5.1->object-detection==0.1) (2021.10.8)
Collecting pytz>=2017.2
  Using cached pytz-2022.1-py2.py3-none-any.whl (503 kB)
Requirement already satisfied: pyasn1<0.5.0,>=0.4.6 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from pyasn1-modules>=0.2.1->google-auth<3.0.0dev,>=1.16.0->google-api-python-client>=1.6.7->tf-models-official>=2.5.1->object-detection==0.1) (0.4.8)
Requirement already satisfied: charset-normalizer~=2.0.0 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from requests<3.0.0dev,>=2.18.0->google-api-core!=2.0.*,!=2.1.*,!=2.2.*,!=2.3.0,<3.0.0dev,>=1.31.5->google-api-python-client>=1.6.7->tf-models-official>=2.5.1->object-detection==0.1) (2.0.12)
Requirement already satisfied: idna<4,>=2.5 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from requests<3.0.0dev,>=2.18.0->google-api-core!=2.0.*,!=2.1.*,!=2.2.*,!=2.3.0,<3.0.0dev,>=1.31.5->google-api-python-client>=1.6.7->tf-models-official>=2.5.1->object-detection==0.1) (3.3)
Requirement already satisfied: google-pasta>=0.1.1 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from tensorflow~=2.8.0->tf-models-official>=2.5.1->object-detection==0.1) (0.2.0)
Requirement already satisfied: h5py>=2.9.0 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from tensorflow~=2.8.0->tf-models-official>=2.5.1->object-detection==0.1) (2.10.0)
Collecting tensorboard<2.9,>=2.8
  Using cached tensorboard-2.8.0-py3-none-any.whl (5.8 MB)
Collecting libclang>=9.0.1
  Using cached libclang-14.0.1-py2.py3-none-manylinux1_x86_64.whl (14.5 MB)
Requirement already satisfied: grpcio<2.0,>=1.24.3 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from tensorflow~=2.8.0->tf-models-official>=2.5.1->object-detection==0.1) (1.46.1)
Requirement already satisfied: gast>=0.2.1 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from tensorflow~=2.8.0->tf-models-official>=2.5.1->object-detection==0.1) (0.3.3)
Requirement already satisfied: termcolor>=1.1.0 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from tensorflow~=2.8.0->tf-models-official>=2.5.1->object-detection==0.1) (1.1.0)
Collecting tensorflow-io-gcs-filesystem>=0.23.1
  Using cached tensorflow_io_gcs_filesystem-0.25.0-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (2.1 MB)
Collecting numpy>=1.15.4
  Using cached numpy-1.21.6-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (15.7 MB)
Requirement already satisfied: wrapt>=1.11.0 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from tensorflow~=2.8.0->tf-models-official>=2.5.1->object-detection==0.1) (1.14.1)
Requirement already satisfied: astunparse>=1.6.0 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from tensorflow~=2.8.0->tf-models-official>=2.5.1->object-detection==0.1) (1.6.3)
Collecting tensorflow-estimator<2.9,>=2.8
  Using cached tensorflow_estimator-2.8.0-py2.py3-none-any.whl (462 kB)
Collecting flatbuffers>=1.12
  Using cached flatbuffers-2.0-py2.py3-none-any.whl (26 kB)
Requirement already satisfied: typing-extensions>=3.6.6 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from tensorflow~=2.8.0->tf-models-official>=2.5.1->object-detection==0.1) (4.2.0)
Collecting keras
  Using cached keras-2.8.0-py2.py3-none-any.whl (1.4 MB)
Requirement already satisfied: keras-preprocessing>=1.1.1 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from tensorflow~=2.8.0->tf-models-official>=2.5.1->object-detection==0.1) (1.1.2)
Requirement already satisfied: opt-einsum>=2.3.2 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from tensorflow~=2.8.0->tf-models-official>=2.5.1->object-detection==0.1) (3.3.0)
Requirement already satisfied: absl-py>=0.4.0 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from tensorflow~=2.8.0->tf-models-official>=2.5.1->object-detection==0.1) (1.0.0)
Requirement already satisfied: wheel<1.0,>=0.23.0 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from astunparse>=1.6.0->tensorflow~=2.8.0->tf-models-official>=2.5.1->object-detection==0.1) (0.37.1)
Requirement already satisfied: tensorboard-plugin-wit>=1.6.0 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from tensorboard<2.9,>=2.8->tensorflow~=2.8.0->tf-models-official>=2.5.1->object-detection==0.1) (1.8.1)
Requirement already satisfied: markdown>=2.6.8 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from tensorboard<2.9,>=2.8->tensorflow~=2.8.0->tf-models-official>=2.5.1->object-detection==0.1) (3.3.7)
Requirement already satisfied: google-auth-oauthlib<0.5,>=0.4.1 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from tensorboard<2.9,>=2.8->tensorflow~=2.8.0->tf-models-official>=2.5.1->object-detection==0.1) (0.4.6)
Requirement already satisfied: werkzeug>=0.11.15 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from tensorboard<2.9,>=2.8->tensorflow~=2.8.0->tf-models-official>=2.5.1->object-detection==0.1) (2.1.2)
Requirement already satisfied: tensorboard-data-server<0.7.0,>=0.6.0 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from tensorboard<2.9,>=2.8->tensorflow~=2.8.0->tf-models-official>=2.5.1->object-detection==0.1) (0.6.1)
Requirement already satisfied: requests-oauthlib>=0.7.0 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from google-auth-oauthlib<0.5,>=0.4.1->tensorboard<2.9,>=2.8->tensorflow~=2.8.0->tf-models-official>=2.5.1->object-detection==0.1) (1.3.1)
Requirement already satisfied: importlib-metadata>=4.4 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from markdown>=2.6.8->tensorboard<2.9,>=2.8->tensorflow~=2.8.0->tf-models-official>=2.5.1->object-detection==0.1) (4.11.3)
Requirement already satisfied: zipp>=0.5 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from importlib-metadata>=4.4->markdown>=2.6.8->tensorboard<2.9,>=2.8->tensorflow~=2.8.0->tf-models-official>=2.5.1->object-detection==0.1) (3.8.0)
Requirement already satisfied: oauthlib>=3.0.0 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<0.5,>=0.4.1->tensorboard<2.9,>=2.8->tensorflow~=2.8.0->tf-models-official>=2.5.1->object-detection==0.1) (3.2.0)
Collecting dm-tree~=0.1.1
  Using cached dm_tree-0.1.7-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (143 kB)
Collecting pydot<2,>=1.2.0
  Downloading pydot-1.4.2-py2.py3-none-any.whl (21 kB)
Collecting hdfs<3.0.0,>=2.1.0
  Downloading hdfs-2.7.0-py3-none-any.whl (34 kB)
Collecting dill<0.3.2,>=0.3.1.1
  Downloading dill-0.3.1.1.tar.gz (151 kB)
     |████████████████████████████████| 151 kB 11.7 MB/s 
Collecting crcmod<2.0,>=1.7
  Downloading crcmod-1.7.tar.gz (89 kB)
     |████████████████████████████████| 89 kB 9.6 MB/s 
Collecting fastavro<2,>=0.23.6
  Downloading fastavro-1.4.11-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.3 MB)
     |████████████████████████████████| 2.3 MB 10.7 MB/s 
Collecting pymongo<4.0.0,>=3.8.0
  Downloading pymongo-3.12.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (508 kB)
     |████████████████████████████████| 508 kB 10.8 MB/s 
Collecting orjson<4.0
  Downloading orjson-3.6.8-cp37-cp37m-manylinux_2_24_x86_64.whl (253 kB)
     |████████████████████████████████| 253 kB 11.1 MB/s 
Collecting cloudpickle<3,>=2.0.0
  Downloading cloudpickle-2.0.0-py3-none-any.whl (25 kB)
Collecting proto-plus<2,>=1.7.1
  Downloading proto_plus-1.20.3-py3-none-any.whl (46 kB)
     |████████████████████████████████| 46 kB 7.6 MB/s 
Collecting httplib2<1dev,>=0.15.0
  Downloading httplib2-0.19.1-py3-none-any.whl (95 kB)
     |████████████████████████████████| 95 kB 7.7 MB/s 
Collecting pyarrow<7.0.0,>=0.15.1
  Downloading pyarrow-6.0.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (25.6 MB)
     |████████████████████████████████| 25.6 MB 10.2 MB/s 
Collecting docopt
  Downloading docopt-0.6.2.tar.gz (25 kB)
Collecting pyparsing!=3.0.0,!=3.0.1,!=3.0.2,!=3.0.3,<4,>=2.4.2
  Downloading pyparsing-2.4.7-py2.py3-none-any.whl (67 kB)
     |████████████████████████████████| 67 kB 9.1 MB/s 
Requirement already satisfied: cycler>=0.10.0 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from lvis->object-detection==0.1) (0.11.0)
Collecting opencv-python>=4.1.0.25
  Using cached opencv_python-4.5.5.64-cp36-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (60.5 MB)
Requirement already satisfied: kiwisolver>=1.1.0 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from lvis->object-detection==0.1) (1.4.2)
Requirement already satisfied: packaging>=20.0 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from matplotlib->object-detection==0.1) (21.3)
Requirement already satisfied: fonttools>=4.22.0 in /home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages (from matplotlib->object-detection==0.1) (4.33.3)
Collecting text-unidecode>=1.3
  Using cached text_unidecode-1.3-py2.py3-none-any.whl (78 kB)
Collecting regex
  Using cached regex-2022.4.24-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (749 kB)
Collecting colorama
  Using cached colorama-0.4.4-py2.py3-none-any.whl (16 kB)
Collecting portalocker
  Using cached portalocker-2.4.0-py2.py3-none-any.whl (16 kB)
Collecting tabulate>=0.8.9
  Using cached tabulate-0.8.9-py3-none-any.whl (25 kB)
Collecting scikit-learn>=0.21.3
  Using cached scikit_learn-1.0.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (24.8 MB)
Collecting joblib>=0.11
  Using cached joblib-1.1.0-py2.py3-none-any.whl (306 kB)
Collecting threadpoolctl>=2.0.0
  Using cached threadpoolctl-3.1.0-py3-none-any.whl (14 kB)
Collecting typeguard>=2.7
  Using cached typeguard-2.13.3-py3-none-any.whl (17 kB)
Collecting promise
  Using cached promise-2.3-py3-none-any.whl
Collecting importlib-resources
  Using cached importlib_resources-5.7.1-py3-none-any.whl (28 kB)
Collecting tensorflow-metadata
  Using cached tensorflow_metadata-1.8.0-py3-none-any.whl (50 kB)
Building wheels for collected packages: object-detection, crcmod, dill, avro-python3, docopt
  Building wheel for object-detection (setup.py) ... done
  Created wheel for object-detection: filename=object_detection-0.1-py3-none-any.whl size=1692779 sha256=252c460d6aa8af993b732a8e7c16cb9f55a516036e5a7162047f5b375032dff5
  Stored in directory: /tmp/pip-ephem-wheel-cache-ze6g6e9r/wheels/d2/5b/9b/31a226de26ad14983f55d580dbf1b14906b40546b281ba0de9
  Building wheel for crcmod (setup.py) ... done
  Created wheel for crcmod: filename=crcmod-1.7-cp37-cp37m-linux_x86_64.whl size=37164 sha256=5e7429baa2328d03abcabfbc62511cfc101802f37ff5146162f01c46857ae559
  Stored in directory: /home/bim/.cache/pip/wheels/dc/9a/e9/49e627353476cec8484343c4ab656f1e0d783ee77b9dde2d1f
  Building wheel for dill (setup.py) ... done
  Created wheel for dill: filename=dill-0.3.1.1-py3-none-any.whl size=78544 sha256=08ed3efab795c29524114d7157ad50ba819a2f32d26c4858d875192be0634d22
  Stored in directory: /home/bim/.cache/pip/wheels/a4/61/fd/c57e374e580aa78a45ed78d5859b3a44436af17e22ca53284f
  Building wheel for avro-python3 (setup.py) ... done
  Created wheel for avro-python3: filename=avro_python3-1.10.2-py3-none-any.whl size=44010 sha256=ab5645b997c71ec15ba310aafebf02f029c40c0f9f5a8e7cd18b71f967aa50ff
  Stored in directory: /home/bim/.cache/pip/wheels/d6/e5/b1/6b151d9b535ee50aaa6ab27d145a0104b6df02e5636f0376da
  Building wheel for docopt (setup.py) ... done
  Created wheel for docopt: filename=docopt-0.6.2-py2.py3-none-any.whl size=13723 sha256=c4af585107d285112df8e15faab4f9bfee60d45ca29d998ebf5121c4b8fdedeb
  Stored in directory: /home/bim/.cache/pip/wheels/72/b0/3f/1d95f96ff986c7dfffe46ce2be4062f38ebd04b506c77c81b9
Successfully built object-detection crcmod dill avro-python3 docopt
Installing collected packages: pyparsing, numpy, threadpoolctl, text-unidecode, tensorflow-io-gcs-filesystem, tensorflow-estimator, tensorboard, libclang, keras, joblib, httplib2, googleapis-common-protos, flatbuffers, uritemplate, typeguard, tqdm, tensorflow-metadata, tensorflow-hub, tensorflow, tabulate, scikit-learn, regex, pytz, python-slugify, promise, portalocker, importlib-resources, google-auth-httplib2, google-api-core, docopt, dm-tree, dill, colorama, tf-slim, tensorflow-text, tensorflow-model-optimization, tensorflow-datasets, tensorflow-addons, seqeval, sentencepiece, sacrebleu, pyyaml, pymongo, pydot, pyarrow, py-cpuinfo, psutil, proto-plus, pandas, orjson, opencv-python, oauth2client, kaggle, hdfs, google-api-python-client, gin-config, fastavro, Cython, crcmod, cloudpickle, tf-models-official, tensorflow-io, lxml, lvis, contextlib2, avro-python3, apache-beam, object-detection
  Attempting uninstall: pyparsing
    Found existing installation: pyparsing 3.0.9
    Uninstalling pyparsing-3.0.9:
      Successfully uninstalled pyparsing-3.0.9
  Attempting uninstall: numpy
    Found existing installation: numpy 1.18.5
    Uninstalling numpy-1.18.5:
      Successfully uninstalled numpy-1.18.5
  Attempting uninstall: tensorflow-estimator
    Found existing installation: tensorflow-estimator 2.2.0
    Uninstalling tensorflow-estimator-2.2.0:
      Successfully uninstalled tensorflow-estimator-2.2.0
  Attempting uninstall: tensorboard
    Found existing installation: tensorboard 2.2.2
    Uninstalling tensorboard-2.2.2:
      Successfully uninstalled tensorboard-2.2.2
  Attempting uninstall: keras
    Found existing installation: Keras 2.3.1
    Uninstalling Keras-2.3.1:
      Successfully uninstalled Keras-2.3.1
  Attempting uninstall: pyyaml
    Found existing installation: PyYAML 6.0
    Uninstalling PyYAML-6.0:
      Successfully uninstalled PyYAML-6.0
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
tensorflow-gpu 2.2.0 requires tensorboard<2.3.0,>=2.2.0, but you have tensorboard 2.8.0 which is incompatible.
tensorflow-gpu 2.2.0 requires tensorflow-estimator<2.3.0,>=2.2.0, but you have tensorflow-estimator 2.8.0 which is incompatible.
Successfully installed Cython-0.29.29 apache-beam-2.38.0 avro-python3-1.10.2 cloudpickle-2.0.0 colorama-0.4.4 contextlib2-21.6.0 crcmod-1.7 dill-0.3.1.1 dm-tree-0.1.7 docopt-0.6.2 fastavro-1.4.11 flatbuffers-2.0 gin-config-0.5.0 google-api-core-2.7.3 google-api-python-client-2.48.0 google-auth-httplib2-0.1.0 googleapis-common-protos-1.56.1 hdfs-2.7.0 httplib2-0.19.1 importlib-resources-5.7.1 joblib-1.1.0 kaggle-1.5.12 keras-2.8.0 libclang-14.0.1 lvis-0.5.3 lxml-4.8.0 numpy-1.21.6 oauth2client-4.1.3 object-detection-0.1 opencv-python-4.5.5.64 orjson-3.6.8 pandas-1.1.5 portalocker-2.4.0 promise-2.3 proto-plus-1.20.3 psutil-5.9.0 py-cpuinfo-8.0.0 pyarrow-6.0.1 pydot-1.4.2 pymongo-3.12.3 pyparsing-2.4.7 python-slugify-6.1.2 pytz-2022.1 pyyaml-5.4.1 regex-2022.4.24 sacrebleu-2.0.0 scikit-learn-1.0.2 sentencepiece-0.1.96 seqeval-1.2.2 tabulate-0.8.9 tensorboard-2.8.0 tensorflow-2.8.1 tensorflow-addons-0.16.1 tensorflow-datasets-4.5.2 tensorflow-estimator-2.8.0 tensorflow-hub-0.12.0 tensorflow-io-0.25.0 tensorflow-io-gcs-filesystem-0.25.0 tensorflow-metadata-1.8.0 tensorflow-model-optimization-0.7.2 tensorflow-text-2.8.2 text-unidecode-1.3 tf-models-official-2.8.0 tf-slim-1.1.0 threadpoolctl-3.1.0 tqdm-4.64.0 typeguard-2.13.3 uritemplate-4.1.1
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models/research$ 
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models/research$ 
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models/research$ 
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models/research$ 
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models/research$ 
View Code

 

 

7、python object_detection/builders/model_builder_tf2_test.py

(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models/research$ 
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models/research$ 
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models/research$ python object_detection/builders/model_builder_tf2_test.py

Running tests under Python 3.7.0: /home/bim/anaconda3/envs/mask_rcnn_tf2/bin/python
[ RUN      ] ModelBuilderTF2Test.test_create_center_net_deepmac
2022-05-17 23:34:49.186294: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2022-05-17 23:34:50.464346: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 11310 MB memory:  -> device: 0, name: Tesla P100-PCIE-12GB, pci bus id: 0000:04:00.0, compute capability: 6.0
2022-05-17 23:34:50.465429: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:1 with 11310 MB memory:  -> device: 1, name: Tesla P100-PCIE-12GB, pci bus id: 0000:82:00.0, compute capability: 6.0
/home/bim/anaconda3/envs/mask_rcnn_tf2/lib/python3.7/site-packages/object_detection/builders/model_builder.py:1102: DeprecationWarning: The 'warn' function is deprecated, use 'warning' instead
  logging.warn(('Building experimental DeepMAC meta-arch.'
W0517 23:34:50.927976 139768308746048 model_builder.py:1102] Building experimental DeepMAC meta-arch. Some features may be omitted.
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_center_net_deepmac): 2.13s
I0517 23:34:51.307853 139768308746048 test_util.py:2374] time(__main__.ModelBuilderTF2Test.test_create_center_net_deepmac): 2.13s
[       OK ] ModelBuilderTF2Test.test_create_center_net_deepmac
[ RUN      ] ModelBuilderTF2Test.test_create_center_net_model0 (customize_head_params=True)
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_center_net_model0 (customize_head_params=True)): 0.6s
I0517 23:34:51.904957 139768308746048 test_util.py:2374] time(__main__.ModelBuilderTF2Test.test_create_center_net_model0 (customize_head_params=True)): 0.6s
[       OK ] ModelBuilderTF2Test.test_create_center_net_model0 (customize_head_params=True)
[ RUN      ] ModelBuilderTF2Test.test_create_center_net_model1 (customize_head_params=False)
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_center_net_model1 (customize_head_params=False)): 0.29s
I0517 23:34:52.197024 139768308746048 test_util.py:2374] time(__main__.ModelBuilderTF2Test.test_create_center_net_model1 (customize_head_params=False)): 0.29s
[       OK ] ModelBuilderTF2Test.test_create_center_net_model1 (customize_head_params=False)
[ RUN      ] ModelBuilderTF2Test.test_create_center_net_model_from_keypoints
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_center_net_model_from_keypoints): 0.27s
I0517 23:34:52.470333 139768308746048 test_util.py:2374] time(__main__.ModelBuilderTF2Test.test_create_center_net_model_from_keypoints): 0.27s
[       OK ] ModelBuilderTF2Test.test_create_center_net_model_from_keypoints
[ RUN      ] ModelBuilderTF2Test.test_create_center_net_model_mobilenet
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_center_net_model_mobilenet): 1.72s
I0517 23:34:54.193345 139768308746048 test_util.py:2374] time(__main__.ModelBuilderTF2Test.test_create_center_net_model_mobilenet): 1.72s
[       OK ] ModelBuilderTF2Test.test_create_center_net_model_mobilenet
[ RUN      ] ModelBuilderTF2Test.test_create_experimental_model
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_experimental_model): 0.0s
I0517 23:34:54.194301 139768308746048 test_util.py:2374] time(__main__.ModelBuilderTF2Test.test_create_experimental_model): 0.0s
[       OK ] ModelBuilderTF2Test.test_create_experimental_model
[ RUN      ] ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature0 (True)
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature0 (True)): 0.02s
I0517 23:34:54.217289 139768308746048 test_util.py:2374] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature0 (True)): 0.02s
[       OK ] ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature0 (True)
[ RUN      ] ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature1 (False)
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature1 (False)): 0.01s
I0517 23:34:54.232109 139768308746048 test_util.py:2374] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature1 (False)): 0.01s
[       OK ] ModelBuilderTF2Test.test_create_faster_rcnn_from_config_with_crop_feature1 (False)
[ RUN      ] ModelBuilderTF2Test.test_create_faster_rcnn_model_from_config_with_example_miner
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_model_from_config_with_example_miner): 0.02s
I0517 23:34:54.247494 139768308746048 test_util.py:2374] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_model_from_config_with_example_miner): 0.02s
[       OK ] ModelBuilderTF2Test.test_create_faster_rcnn_model_from_config_with_example_miner
[ RUN      ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_with_matmul
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_with_matmul): 0.1s
I0517 23:34:54.348064 139768308746048 test_util.py:2374] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_with_matmul): 0.1s
[       OK ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_with_matmul
[ RUN      ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_without_matmul
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_without_matmul): 0.1s
I0517 23:34:54.447457 139768308746048 test_util.py:2374] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_without_matmul): 0.1s
[       OK ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_faster_rcnn_without_matmul
[ RUN      ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_with_matmul
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_with_matmul): 0.11s
I0517 23:34:54.553356 139768308746048 test_util.py:2374] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_with_matmul): 0.11s
[       OK ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_with_matmul
[ RUN      ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_without_matmul
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_without_matmul): 0.1s
I0517 23:34:54.656839 139768308746048 test_util.py:2374] time(__main__.ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_without_matmul): 0.1s
[       OK ] ModelBuilderTF2Test.test_create_faster_rcnn_models_from_config_mask_rcnn_without_matmul
[ RUN      ] ModelBuilderTF2Test.test_create_rfcn_model_from_config
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_rfcn_model_from_config): 0.1s
I0517 23:34:54.755601 139768308746048 test_util.py:2374] time(__main__.ModelBuilderTF2Test.test_create_rfcn_model_from_config): 0.1s
[       OK ] ModelBuilderTF2Test.test_create_rfcn_model_from_config
[ RUN      ] ModelBuilderTF2Test.test_create_ssd_fpn_model_from_config
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_ssd_fpn_model_from_config): 0.03s
I0517 23:34:54.783532 139768308746048 test_util.py:2374] time(__main__.ModelBuilderTF2Test.test_create_ssd_fpn_model_from_config): 0.03s
[       OK ] ModelBuilderTF2Test.test_create_ssd_fpn_model_from_config
[ RUN      ] ModelBuilderTF2Test.test_create_ssd_models_from_config
I0517 23:34:54.970504 139768308746048 ssd_efficientnet_bifpn_feature_extractor.py:146] EfficientDet EfficientNet backbone version: efficientnet-b0
I0517 23:34:54.970600 139768308746048 ssd_efficientnet_bifpn_feature_extractor.py:147] EfficientDet BiFPN num filters: 64
I0517 23:34:54.970665 139768308746048 ssd_efficientnet_bifpn_feature_extractor.py:149] EfficientDet BiFPN num iterations: 3
I0517 23:34:54.973101 139768308746048 efficientnet_model.py:144] round_filter input=32 output=32
I0517 23:34:54.988750 139768308746048 efficientnet_model.py:144] round_filter input=32 output=32
I0517 23:34:54.988843 139768308746048 efficientnet_model.py:144] round_filter input=16 output=16
I0517 23:34:55.045492 139768308746048 efficientnet_model.py:144] round_filter input=16 output=16
I0517 23:34:55.045587 139768308746048 efficientnet_model.py:144] round_filter input=24 output=24
I0517 23:34:55.193310 139768308746048 efficientnet_model.py:144] round_filter input=24 output=24
I0517 23:34:55.193407 139768308746048 efficientnet_model.py:144] round_filter input=40 output=40
I0517 23:34:55.339695 139768308746048 efficientnet_model.py:144] round_filter input=40 output=40
I0517 23:34:55.339791 139768308746048 efficientnet_model.py:144] round_filter input=80 output=80
I0517 23:34:55.560731 139768308746048 efficientnet_model.py:144] round_filter input=80 output=80
I0517 23:34:55.560828 139768308746048 efficientnet_model.py:144] round_filter input=112 output=112
I0517 23:34:55.781611 139768308746048 efficientnet_model.py:144] round_filter input=112 output=112
I0517 23:34:55.781708 139768308746048 efficientnet_model.py:144] round_filter input=192 output=192
I0517 23:34:56.077639 139768308746048 efficientnet_model.py:144] round_filter input=192 output=192
I0517 23:34:56.077737 139768308746048 efficientnet_model.py:144] round_filter input=320 output=320
I0517 23:34:56.149844 139768308746048 efficientnet_model.py:144] round_filter input=1280 output=1280
I0517 23:34:56.179338 139768308746048 efficientnet_model.py:454] Building model efficientnet with params ModelConfig(width_coefficient=1.0, depth_coefficient=1.0, resolution=224, dropout_rate=0.2, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')
I0517 23:34:56.230762 139768308746048 ssd_efficientnet_bifpn_feature_extractor.py:146] EfficientDet EfficientNet backbone version: efficientnet-b1
I0517 23:34:56.230856 139768308746048 ssd_efficientnet_bifpn_feature_extractor.py:147] EfficientDet BiFPN num filters: 88
I0517 23:34:56.230921 139768308746048 ssd_efficientnet_bifpn_feature_extractor.py:149] EfficientDet BiFPN num iterations: 4
I0517 23:34:56.232542 139768308746048 efficientnet_model.py:144] round_filter input=32 output=32
I0517 23:34:56.247062 139768308746048 efficientnet_model.py:144] round_filter input=32 output=32
I0517 23:34:56.247162 139768308746048 efficientnet_model.py:144] round_filter input=16 output=16
I0517 23:34:56.364234 139768308746048 efficientnet_model.py:144] round_filter input=16 output=16
I0517 23:34:56.364330 139768308746048 efficientnet_model.py:144] round_filter input=24 output=24
I0517 23:34:56.721792 139768308746048 efficientnet_model.py:144] round_filter input=24 output=24
I0517 23:34:56.721943 139768308746048 efficientnet_model.py:144] round_filter input=40 output=40
I0517 23:34:56.947825 139768308746048 efficientnet_model.py:144] round_filter input=40 output=40
I0517 23:34:56.947923 139768308746048 efficientnet_model.py:144] round_filter input=80 output=80
I0517 23:34:57.250524 139768308746048 efficientnet_model.py:144] round_filter input=80 output=80
I0517 23:34:57.250624 139768308746048 efficientnet_model.py:144] round_filter input=112 output=112
I0517 23:34:57.549314 139768308746048 efficientnet_model.py:144] round_filter input=112 output=112
I0517 23:34:57.549412 139768308746048 efficientnet_model.py:144] round_filter input=192 output=192
I0517 23:34:57.920807 139768308746048 efficientnet_model.py:144] round_filter input=192 output=192
I0517 23:34:57.920905 139768308746048 efficientnet_model.py:144] round_filter input=320 output=320
I0517 23:34:58.068431 139768308746048 efficientnet_model.py:144] round_filter input=1280 output=1280
I0517 23:34:58.096064 139768308746048 efficientnet_model.py:454] Building model efficientnet with params ModelConfig(width_coefficient=1.0, depth_coefficient=1.1, resolution=240, dropout_rate=0.2, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')
I0517 23:34:58.156941 139768308746048 ssd_efficientnet_bifpn_feature_extractor.py:146] EfficientDet EfficientNet backbone version: efficientnet-b2
I0517 23:34:58.157036 139768308746048 ssd_efficientnet_bifpn_feature_extractor.py:147] EfficientDet BiFPN num filters: 112
I0517 23:34:58.157101 139768308746048 ssd_efficientnet_bifpn_feature_extractor.py:149] EfficientDet BiFPN num iterations: 5
I0517 23:34:58.158683 139768308746048 efficientnet_model.py:144] round_filter input=32 output=32
I0517 23:34:58.173460 139768308746048 efficientnet_model.py:144] round_filter input=32 output=32
I0517 23:34:58.173552 139768308746048 efficientnet_model.py:144] round_filter input=16 output=16
I0517 23:34:58.290623 139768308746048 efficientnet_model.py:144] round_filter input=16 output=16
I0517 23:34:58.290720 139768308746048 efficientnet_model.py:144] round_filter input=24 output=24
I0517 23:34:58.511953 139768308746048 efficientnet_model.py:144] round_filter input=24 output=24
I0517 23:34:58.512052 139768308746048 efficientnet_model.py:144] round_filter input=40 output=48
I0517 23:34:58.733304 139768308746048 efficientnet_model.py:144] round_filter input=40 output=48
I0517 23:34:58.733401 139768308746048 efficientnet_model.py:144] round_filter input=80 output=88
I0517 23:34:59.028852 139768308746048 efficientnet_model.py:144] round_filter input=80 output=88
I0517 23:34:59.028950 139768308746048 efficientnet_model.py:144] round_filter input=112 output=120
I0517 23:34:59.324784 139768308746048 efficientnet_model.py:144] round_filter input=112 output=120
I0517 23:34:59.324882 139768308746048 efficientnet_model.py:144] round_filter input=192 output=208
I0517 23:34:59.695096 139768308746048 efficientnet_model.py:144] round_filter input=192 output=208
I0517 23:34:59.695210 139768308746048 efficientnet_model.py:144] round_filter input=320 output=352
I0517 23:34:59.840678 139768308746048 efficientnet_model.py:144] round_filter input=1280 output=1408
I0517 23:34:59.869396 139768308746048 efficientnet_model.py:454] Building model efficientnet with params ModelConfig(width_coefficient=1.1, depth_coefficient=1.2, resolution=260, dropout_rate=0.3, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')
I0517 23:34:59.929939 139768308746048 ssd_efficientnet_bifpn_feature_extractor.py:146] EfficientDet EfficientNet backbone version: efficientnet-b3
I0517 23:34:59.930034 139768308746048 ssd_efficientnet_bifpn_feature_extractor.py:147] EfficientDet BiFPN num filters: 160
I0517 23:34:59.930104 139768308746048 ssd_efficientnet_bifpn_feature_extractor.py:149] EfficientDet BiFPN num iterations: 6
I0517 23:34:59.931786 139768308746048 efficientnet_model.py:144] round_filter input=32 output=40
I0517 23:34:59.946818 139768308746048 efficientnet_model.py:144] round_filter input=32 output=40
I0517 23:34:59.946909 139768308746048 efficientnet_model.py:144] round_filter input=16 output=24
I0517 23:35:00.065110 139768308746048 efficientnet_model.py:144] round_filter input=16 output=24
I0517 23:35:00.065207 139768308746048 efficientnet_model.py:144] round_filter input=24 output=32
I0517 23:35:00.288161 139768308746048 efficientnet_model.py:144] round_filter input=24 output=32
I0517 23:35:00.288258 139768308746048 efficientnet_model.py:144] round_filter input=40 output=48
I0517 23:35:00.508904 139768308746048 efficientnet_model.py:144] round_filter input=40 output=48
I0517 23:35:00.509001 139768308746048 efficientnet_model.py:144] round_filter input=80 output=96
I0517 23:35:01.059887 139768308746048 efficientnet_model.py:144] round_filter input=80 output=96
I0517 23:35:01.060048 139768308746048 efficientnet_model.py:144] round_filter input=112 output=136
I0517 23:35:01.435779 139768308746048 efficientnet_model.py:144] round_filter input=112 output=136
I0517 23:35:01.435877 139768308746048 efficientnet_model.py:144] round_filter input=192 output=232
I0517 23:35:01.888062 139768308746048 efficientnet_model.py:144] round_filter input=192 output=232
I0517 23:35:01.888161 139768308746048 efficientnet_model.py:144] round_filter input=320 output=384
I0517 23:35:02.035060 139768308746048 efficientnet_model.py:144] round_filter input=1280 output=1536
I0517 23:35:02.064120 139768308746048 efficientnet_model.py:454] Building model efficientnet with params ModelConfig(width_coefficient=1.2, depth_coefficient=1.4, resolution=300, dropout_rate=0.3, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')
I0517 23:35:02.130040 139768308746048 ssd_efficientnet_bifpn_feature_extractor.py:146] EfficientDet EfficientNet backbone version: efficientnet-b4
I0517 23:35:02.130141 139768308746048 ssd_efficientnet_bifpn_feature_extractor.py:147] EfficientDet BiFPN num filters: 224
I0517 23:35:02.130210 139768308746048 ssd_efficientnet_bifpn_feature_extractor.py:149] EfficientDet BiFPN num iterations: 7
I0517 23:35:02.131837 139768308746048 efficientnet_model.py:144] round_filter input=32 output=48
I0517 23:35:02.146931 139768308746048 efficientnet_model.py:144] round_filter input=32 output=48
I0517 23:35:02.147025 139768308746048 efficientnet_model.py:144] round_filter input=16 output=24
I0517 23:35:02.269019 139768308746048 efficientnet_model.py:144] round_filter input=16 output=24
I0517 23:35:02.269229 139768308746048 efficientnet_model.py:144] round_filter input=24 output=32
I0517 23:35:02.565363 139768308746048 efficientnet_model.py:144] round_filter input=24 output=32
I0517 23:35:02.565469 139768308746048 efficientnet_model.py:144] round_filter input=40 output=56
I0517 23:35:02.861112 139768308746048 efficientnet_model.py:144] round_filter input=40 output=56
I0517 23:35:02.861209 139768308746048 efficientnet_model.py:144] round_filter input=80 output=112
I0517 23:35:03.308875 139768308746048 efficientnet_model.py:144] round_filter input=80 output=112
I0517 23:35:03.308972 139768308746048 efficientnet_model.py:144] round_filter input=112 output=160
I0517 23:35:03.757671 139768308746048 efficientnet_model.py:144] round_filter input=112 output=160
I0517 23:35:03.757819 139768308746048 efficientnet_model.py:144] round_filter input=192 output=272
I0517 23:35:04.354326 139768308746048 efficientnet_model.py:144] round_filter input=192 output=272
I0517 23:35:04.354423 139768308746048 efficientnet_model.py:144] round_filter input=320 output=448
I0517 23:35:04.500522 139768308746048 efficientnet_model.py:144] round_filter input=1280 output=1792
I0517 23:35:04.528745 139768308746048 efficientnet_model.py:454] Building model efficientnet with params ModelConfig(width_coefficient=1.4, depth_coefficient=1.8, resolution=380, dropout_rate=0.4, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')
I0517 23:35:04.606383 139768308746048 ssd_efficientnet_bifpn_feature_extractor.py:146] EfficientDet EfficientNet backbone version: efficientnet-b5
I0517 23:35:04.606479 139768308746048 ssd_efficientnet_bifpn_feature_extractor.py:147] EfficientDet BiFPN num filters: 288
I0517 23:35:04.606549 139768308746048 ssd_efficientnet_bifpn_feature_extractor.py:149] EfficientDet BiFPN num iterations: 7
I0517 23:35:04.608230 139768308746048 efficientnet_model.py:144] round_filter input=32 output=48
I0517 23:35:04.622859 139768308746048 efficientnet_model.py:144] round_filter input=32 output=48
I0517 23:35:04.622951 139768308746048 efficientnet_model.py:144] round_filter input=16 output=24
I0517 23:35:04.799619 139768308746048 efficientnet_model.py:144] round_filter input=16 output=24
I0517 23:35:04.799716 139768308746048 efficientnet_model.py:144] round_filter input=24 output=40
I0517 23:35:05.408220 139768308746048 efficientnet_model.py:144] round_filter input=24 output=40
I0517 23:35:05.408376 139768308746048 efficientnet_model.py:144] round_filter input=40 output=64
I0517 23:35:05.787838 139768308746048 efficientnet_model.py:144] round_filter input=40 output=64
I0517 23:35:05.787938 139768308746048 efficientnet_model.py:144] round_filter input=80 output=128
I0517 23:35:06.318999 139768308746048 efficientnet_model.py:144] round_filter input=80 output=128
I0517 23:35:06.319097 139768308746048 efficientnet_model.py:144] round_filter input=112 output=176
I0517 23:35:06.844926 139768308746048 efficientnet_model.py:144] round_filter input=112 output=176
I0517 23:35:06.845024 139768308746048 efficientnet_model.py:144] round_filter input=192 output=304
I0517 23:35:07.519382 139768308746048 efficientnet_model.py:144] round_filter input=192 output=304
I0517 23:35:07.519480 139768308746048 efficientnet_model.py:144] round_filter input=320 output=512
I0517 23:35:07.740797 139768308746048 efficientnet_model.py:144] round_filter input=1280 output=2048
I0517 23:35:07.768867 139768308746048 efficientnet_model.py:454] Building model efficientnet with params ModelConfig(width_coefficient=1.6, depth_coefficient=2.2, resolution=456, dropout_rate=0.4, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')
I0517 23:35:07.856589 139768308746048 ssd_efficientnet_bifpn_feature_extractor.py:146] EfficientDet EfficientNet backbone version: efficientnet-b6
I0517 23:35:07.856685 139768308746048 ssd_efficientnet_bifpn_feature_extractor.py:147] EfficientDet BiFPN num filters: 384
I0517 23:35:07.856755 139768308746048 ssd_efficientnet_bifpn_feature_extractor.py:149] EfficientDet BiFPN num iterations: 8
I0517 23:35:07.858352 139768308746048 efficientnet_model.py:144] round_filter input=32 output=56
I0517 23:35:07.873084 139768308746048 efficientnet_model.py:144] round_filter input=32 output=56
I0517 23:35:07.873175 139768308746048 efficientnet_model.py:144] round_filter input=16 output=32
I0517 23:35:08.058420 139768308746048 efficientnet_model.py:144] round_filter input=16 output=32
I0517 23:35:08.058643 139768308746048 efficientnet_model.py:144] round_filter input=24 output=40
I0517 23:35:08.504442 139768308746048 efficientnet_model.py:144] round_filter input=24 output=40
I0517 23:35:08.504544 139768308746048 efficientnet_model.py:144] round_filter input=40 output=72
I0517 23:35:08.949102 139768308746048 efficientnet_model.py:144] round_filter input=40 output=72
I0517 23:35:08.949200 139768308746048 efficientnet_model.py:144] round_filter input=80 output=144
I0517 23:35:09.544441 139768308746048 efficientnet_model.py:144] round_filter input=80 output=144
I0517 23:35:09.544538 139768308746048 efficientnet_model.py:144] round_filter input=112 output=200
I0517 23:35:10.378255 139768308746048 efficientnet_model.py:144] round_filter input=112 output=200
I0517 23:35:10.378421 139768308746048 efficientnet_model.py:144] round_filter input=192 output=344
I0517 23:35:11.211799 139768308746048 efficientnet_model.py:144] round_filter input=192 output=344
I0517 23:35:11.211900 139768308746048 efficientnet_model.py:144] round_filter input=320 output=576
I0517 23:35:11.436795 139768308746048 efficientnet_model.py:144] round_filter input=1280 output=2304
I0517 23:35:11.465676 139768308746048 efficientnet_model.py:454] Building model efficientnet with params ModelConfig(width_coefficient=1.8, depth_coefficient=2.6, resolution=528, dropout_rate=0.5, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')
I0517 23:35:11.567351 139768308746048 ssd_efficientnet_bifpn_feature_extractor.py:146] EfficientDet EfficientNet backbone version: efficientnet-b7
I0517 23:35:11.567447 139768308746048 ssd_efficientnet_bifpn_feature_extractor.py:147] EfficientDet BiFPN num filters: 384
I0517 23:35:11.567523 139768308746048 ssd_efficientnet_bifpn_feature_extractor.py:149] EfficientDet BiFPN num iterations: 8
I0517 23:35:11.569143 139768308746048 efficientnet_model.py:144] round_filter input=32 output=64
I0517 23:35:11.584109 139768308746048 efficientnet_model.py:144] round_filter input=32 output=64
I0517 23:35:11.584201 139768308746048 efficientnet_model.py:144] round_filter input=16 output=32
I0517 23:35:11.822027 139768308746048 efficientnet_model.py:144] round_filter input=16 output=32
I0517 23:35:11.822124 139768308746048 efficientnet_model.py:144] round_filter input=24 output=48
I0517 23:35:12.344686 139768308746048 efficientnet_model.py:144] round_filter input=24 output=48
I0517 23:35:12.344783 139768308746048 efficientnet_model.py:144] round_filter input=40 output=80
I0517 23:35:12.865347 139768308746048 efficientnet_model.py:144] round_filter input=40 output=80
I0517 23:35:12.865444 139768308746048 efficientnet_model.py:144] round_filter input=80 output=160
I0517 23:35:13.612893 139768308746048 efficientnet_model.py:144] round_filter input=80 output=160
I0517 23:35:13.612998 139768308746048 efficientnet_model.py:144] round_filter input=112 output=224
I0517 23:35:14.360021 139768308746048 efficientnet_model.py:144] round_filter input=112 output=224
I0517 23:35:14.360119 139768308746048 efficientnet_model.py:144] round_filter input=192 output=384
I0517 23:35:15.592784 139768308746048 efficientnet_model.py:144] round_filter input=192 output=384
I0517 23:35:15.592942 139768308746048 efficientnet_model.py:144] round_filter input=320 output=640
I0517 23:35:15.894242 139768308746048 efficientnet_model.py:144] round_filter input=1280 output=2560
I0517 23:35:15.924339 139768308746048 efficientnet_model.py:454] Building model efficientnet with params ModelConfig(width_coefficient=2.0, depth_coefficient=3.1, resolution=600, dropout_rate=0.5, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32')
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_create_ssd_models_from_config): 21.26s
I0517 23:35:16.043067 139768308746048 test_util.py:2374] time(__main__.ModelBuilderTF2Test.test_create_ssd_models_from_config): 21.26s
[       OK ] ModelBuilderTF2Test.test_create_ssd_models_from_config
[ RUN      ] ModelBuilderTF2Test.test_invalid_faster_rcnn_batchnorm_update
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_invalid_faster_rcnn_batchnorm_update): 0.0s
I0517 23:35:16.051289 139768308746048 test_util.py:2374] time(__main__.ModelBuilderTF2Test.test_invalid_faster_rcnn_batchnorm_update): 0.0s
[       OK ] ModelBuilderTF2Test.test_invalid_faster_rcnn_batchnorm_update
[ RUN      ] ModelBuilderTF2Test.test_invalid_first_stage_nms_iou_threshold
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_invalid_first_stage_nms_iou_threshold): 0.0s
I0517 23:35:16.052858 139768308746048 test_util.py:2374] time(__main__.ModelBuilderTF2Test.test_invalid_first_stage_nms_iou_threshold): 0.0s
[       OK ] ModelBuilderTF2Test.test_invalid_first_stage_nms_iou_threshold
[ RUN      ] ModelBuilderTF2Test.test_invalid_model_config_proto
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_invalid_model_config_proto): 0.0s
I0517 23:35:16.053276 139768308746048 test_util.py:2374] time(__main__.ModelBuilderTF2Test.test_invalid_model_config_proto): 0.0s
[       OK ] ModelBuilderTF2Test.test_invalid_model_config_proto
[ RUN      ] ModelBuilderTF2Test.test_invalid_second_stage_batch_size
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_invalid_second_stage_batch_size): 0.0s
I0517 23:35:16.054775 139768308746048 test_util.py:2374] time(__main__.ModelBuilderTF2Test.test_invalid_second_stage_batch_size): 0.0s
[       OK ] ModelBuilderTF2Test.test_invalid_second_stage_batch_size
[ RUN      ] ModelBuilderTF2Test.test_session
[  SKIPPED ] ModelBuilderTF2Test.test_session
[ RUN      ] ModelBuilderTF2Test.test_unknown_faster_rcnn_feature_extractor
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_unknown_faster_rcnn_feature_extractor): 0.0s
I0517 23:35:16.056132 139768308746048 test_util.py:2374] time(__main__.ModelBuilderTF2Test.test_unknown_faster_rcnn_feature_extractor): 0.0s
[       OK ] ModelBuilderTF2Test.test_unknown_faster_rcnn_feature_extractor
[ RUN      ] ModelBuilderTF2Test.test_unknown_meta_architecture
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_unknown_meta_architecture): 0.0s
I0517 23:35:16.056501 139768308746048 test_util.py:2374] time(__main__.ModelBuilderTF2Test.test_unknown_meta_architecture): 0.0s
[       OK ] ModelBuilderTF2Test.test_unknown_meta_architecture
[ RUN      ] ModelBuilderTF2Test.test_unknown_ssd_feature_extractor
INFO:tensorflow:time(__main__.ModelBuilderTF2Test.test_unknown_ssd_feature_extractor): 0.0s
I0517 23:35:16.057491 139768308746048 test_util.py:2374] time(__main__.ModelBuilderTF2Test.test_unknown_ssd_feature_extractor): 0.0s
[       OK ] ModelBuilderTF2Test.test_unknown_ssd_feature_extractor
----------------------------------------------------------------------
Ran 24 tests in 26.876s

OK (skipped=1)
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models/research$ 
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models/research$ 
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models/research$ 
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models/research$ 
(mask_rcnn_tf2) bim@bim-PowerEdge-R730:~/tensorflow_project/models/research$ 
View Code

 

 

 

 

 

 

 

 

 

 

 

 

 

参考:https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf2.md

########################

标签:TensorFlow2,23,models,py,output,input,model,efficientnet
来源: https://www.cnblogs.com/herd/p/16282963.html