kongsea / fpn_tensorflow Goto Github PK

View Code? Open in Web Editor NEW

70.0 70.0 26.0 1.38 MB

A easy-to-use FPN modified from https://github.com/yangxue0827/FPN_Tensorflow.

Python 99.56% Shell 0.44%

fpn_tensorflow's Issues

Have you tried the VGg network? I have been trying to change the network, modify C2, C3, C4 and C5. There has been a mistake. Can you give me some advice?

生成classes.txt出现问题

我想使用pascal voc2007数据集进行训练，数据集本身有Anonotions，tfrecords文件，那么我该怎样生成classes.txt文件呢

我的错误和您提示得一样，可是按照修改提示修改之后还是会报错。

TypeError: cond() got an unexpected keyword argument 'true_fn'

hello,when i run python train.py, it occured:
Traceback (most recent call last):
File "train.py", line 230, in
train()
File "train.py", line 35, in train
is_training=True)
File "../data/io/read_tfrecord.py", line 83, in next_batch
is_training=is_training)
File "../data/io/read_tfrecord.py", line 57, in read_and_prepocess_single_img
target_shortside_len=shortside_len)
File "../data/io/image_preprocess.py", line 27, in short_side_resize
false_fn=lambda: (target_shortside_len * h//w, target_shortside_len))
TypeError: cond() got an unexpected keyword argument 'true_fn'

How to use the pre-trained model?

When I trained my model with pretrained-model, the variables are zeros like this :

model restore from pretrained mode, path is : /home/..//data/pretrained_weights/resnet_50.ckpt
resnet_v1_50/conv1/weights:0
resnet_v1_50/conv1/BatchNorm/gamma:0
resnet_v1_50/conv1/BatchNorm/beta:0
resnet_v1_50/conv1/BatchNorm/moving_mean:0
resnet_v1_50/conv1/BatchNorm/moving_variance:0
resnet_v1_50/block1/unit_1/bottleneck_v1/shortcut/weights:0
resnet_v1_50/block1/unit_1/bottleneck_v1/shortcut/BatchNorm/gamma:0
resnet_v1_50/block1/unit_1/bottleneck_v1/shortcut/BatchNorm/beta:0
resnet_v1_50/block1/unit_1/bottleneck_v1/shortcut/BatchNorm/moving_mean:0
resnet_v1_50/block1/unit_1/bottleneck_v1/shortcut/BatchNorm/moving_variance:0
resnet_v1_50/block1/unit_1/bottleneck_v1/conv1/weights:0
resnet_v1_50/block1/unit_1/bottleneck_v1/conv1/BatchNorm/gamma:0
resnet_v1_50/block1/unit_1/bottleneck_v1/conv1/BatchNorm/beta:0
resnet_v1_50/block1/unit_1/bottleneck_v1/conv1/BatchNorm/moving_mean:0
resnet_v1_50/block1/unit_1/bottleneck_v1/conv1/BatchNorm/moving_variance:0
resnet_v1_50/block1/unit_1/bottleneck_v1/conv2/weights:0
resnet_v1_50/block1/unit_1/bottleneck_v1/conv2/BatchNorm/gamma:0
resnet_v1_50/block1/unit_1/bottleneck_v1/conv2/BatchNorm/beta:0
resnet_v1_50/block1/unit_1/bottleneck_v1/conv2/BatchNorm/moving_mean:0
resnet_v1_50/block1/unit_1/bottleneck_v1/conv2/BatchNorm/moving_variance:0
resnet_v1_50/block1/unit_1/bottleneck_v1/conv3/weights:0
resnet_v1_50/block1/unit_1/bottleneck_v1/conv3/BatchNorm/gamma:0
resnet_v1_50/block1/unit_1/bottleneck_v1/conv3/BatchNorm/beta:0
resnet_v1_50/block1/unit_1/bottleneck_v1/conv3/BatchNorm/moving_mean:0
resnet_v1_50/block1/unit_1/bottleneck_v1/conv3/BatchNorm/moving_variance:0
resnet_v1_50/block1/unit_2/bottleneck_v1/conv1/weights:0
resnet_v1_50/block1/unit_2/bottleneck_v1/conv1/BatchNorm/gamma:0
resnet_v1_50/block1/unit_2/bottleneck_v1/conv1/BatchNorm/beta:0
resnet_v1_50/block1/unit_2/bottleneck_v1/conv1/BatchNorm/moving_mean:0
resnet_v1_50/block1/unit_2/bottleneck_v1/conv1/BatchNorm/moving_variance:0
resnet_v1_50/block1/unit_2/bottleneck_v1/conv2/weights:0
resnet_v1_50/block1/unit_2/bottleneck_v1/conv2/BatchNorm/gamma:0
resnet_v1_50/block1/unit_2/bottleneck_v1/conv2/BatchNorm/beta:0
resnet_v1_50/block1/unit_2/bottleneck_v1/conv2/BatchNorm/moving_mean:0
resnet_v1_50/block1/unit_2/bottleneck_v1/conv2/BatchNorm/moving_variance:0
resnet_v1_50/block1/unit_2/bottleneck_v1/conv3/weights:0
resnet_v1_50/block1/unit_2/bottleneck_v1/conv3/BatchNorm/gamma:0
resnet_v1_50/block1/unit_2/bottleneck_v1/conv3/BatchNorm/beta:0
resnet_v1_50/block1/unit_2/bottleneck_v1/conv3/BatchNorm/moving_mean:0
resnet_v1_50/block1/unit_2/bottleneck_v1/conv3/BatchNorm/moving_variance:0
resnet_v1_50/block1/unit_3/bottleneck_v1/conv1/weights:0
resnet_v1_50/block1/unit_3/bottleneck_v1/conv1/BatchNorm/gamma:0
resnet_v1_50/block1/unit_3/bottleneck_v1/conv1/BatchNorm/beta:0
resnet_v1_50/block1/unit_3/bottleneck_v1/conv1/BatchNorm/moving_mean:0
resnet_v1_50/block1/unit_3/bottleneck_v1/conv1/BatchNorm/moving_variance:0
resnet_v1_50/block1/unit_3/bottleneck_v1/conv2/weights:0
resnet_v1_50/block1/unit_3/bottleneck_v1/conv2/BatchNorm/gamma:0
resnet_v1_50/block1/unit_3/bottleneck_v1/conv2/BatchNorm/beta:0
resnet_v1_50/block1/unit_3/bottleneck_v1/conv2/BatchNorm/moving_mean:0
resnet_v1_50/block1/unit_3/bottleneck_v1/conv2/BatchNorm/moving_variance:0
resnet_v1_50/block1/unit_3/bottleneck_v1/conv3/weights:0
resnet_v1_50/block1/unit_3/bottleneck_v1/conv3/BatchNorm/gamma:0
resnet_v1_50/block1/unit_3/bottleneck_v1/conv3/BatchNorm/beta:0
resnet_v1_50/block1/unit_3/bottleneck_v1/conv3/BatchNorm/moving_mean:0
resnet_v1_50/block1/unit_3/bottleneck_v1/conv3/BatchNorm/moving_variance:0
resnet_v1_50/block2/unit_1/bottleneck_v1/shortcut/weights:0
resnet_v1_50/block2/unit_1/bottleneck_v1/shortcut/BatchNorm/gamma:0
resnet_v1_50/block2/unit_1/bottleneck_v1/shortcut/BatchNorm/beta:0
resnet_v1_50/block2/unit_1/bottleneck_v1/shortcut/BatchNorm/moving_mean:0
resnet_v1_50/block2/unit_1/bottleneck_v1/shortcut/BatchNorm/moving_variance:0
resnet_v1_50/block2/unit_1/bottleneck_v1/conv1/weights:0
resnet_v1_50/block2/unit_1/bottleneck_v1/conv1/BatchNorm/gamma:0
resnet_v1_50/block2/unit_1/bottleneck_v1/conv1/BatchNorm/beta:0
resnet_v1_50/block2/unit_1/bottleneck_v1/conv1/BatchNorm/moving_mean:0
resnet_v1_50/block2/unit_1/bottleneck_v1/conv1/BatchNorm/moving_variance:0
resnet_v1_50/block2/unit_1/bottleneck_v1/conv2/weights:0
resnet_v1_50/block2/unit_1/bottleneck_v1/conv2/BatchNorm/gamma:0
resnet_v1_50/block2/unit_1/bottleneck_v1/conv2/BatchNorm/beta:0
resnet_v1_50/block2/unit_1/bottleneck_v1/conv2/BatchNorm/moving_mean:0
resnet_v1_50/block2/unit_1/bottleneck_v1/conv2/BatchNorm/moving_variance:0
resnet_v1_50/block2/unit_1/bottleneck_v1/conv3/weights:0
resnet_v1_50/block2/unit_1/bottleneck_v1/conv3/BatchNorm/gamma:0
resnet_v1_50/block2/unit_1/bottleneck_v1/conv3/BatchNorm/beta:0
resnet_v1_50/block2/unit_1/bottleneck_v1/conv3/BatchNorm/moving_mean:0
resnet_v1_50/block2/unit_1/bottleneck_v1/conv3/BatchNorm/moving_variance:0
resnet_v1_50/block2/unit_2/bottleneck_v1/conv1/weights:0
resnet_v1_50/block2/unit_2/bottleneck_v1/conv1/BatchNorm/gamma:0
resnet_v1_50/block2/unit_2/bottleneck_v1/conv1/BatchNorm/beta:0
resnet_v1_50/block2/unit_2/bottleneck_v1/conv1/BatchNorm/moving_mean:0
resnet_v1_50/block2/unit_2/bottleneck_v1/conv1/BatchNorm/moving_variance:0
resnet_v1_50/block2/unit_2/bottleneck_v1/conv2/weights:0
resnet_v1_50/block2/unit_2/bottleneck_v1/conv2/BatchNorm/gamma:0
resnet_v1_50/block2/unit_2/bottleneck_v1/conv2/BatchNorm/beta:0
resnet_v1_50/block2/unit_2/bottleneck_v1/conv2/BatchNorm/moving_mean:0
resnet_v1_50/block2/unit_2/bottleneck_v1/conv2/BatchNorm/moving_variance:0
resnet_v1_50/block2/unit_2/bottleneck_v1/conv3/weights:0
resnet_v1_50/block2/unit_2/bottleneck_v1/conv3/BatchNorm/gamma:0
resnet_v1_50/block2/unit_2/bottleneck_v1/conv3/BatchNorm/beta:0
resnet_v1_50/block2/unit_2/bottleneck_v1/conv3/BatchNorm/moving_mean:0
resnet_v1_50/block2/unit_2/bottleneck_v1/conv3/BatchNorm/moving_variance:0
resnet_v1_50/block2/unit_3/bottleneck_v1/conv1/weights:0
resnet_v1_50/block2/unit_3/bottleneck_v1/conv1/BatchNorm/gamma:0
resnet_v1_50/block2/unit_3/bottleneck_v1/conv1/BatchNorm/beta:0
resnet_v1_50/block2/unit_3/bottleneck_v1/conv1/BatchNorm/moving_mean:0
resnet_v1_50/block2/unit_3/bottleneck_v1/conv1/BatchNorm/moving_variance:0
resnet_v1_50/block2/unit_3/bottleneck_v1/conv2/weights:0
resnet_v1_50/block2/unit_3/bottleneck_v1/conv2/BatchNorm/gamma:0
resnet_v1_50/block2/unit_3/bottleneck_v1/conv2/BatchNorm/beta:0
...
...
...

test.py运行的图片是放在了哪里啊

想要测试的图片放在哪了啊，只看到了图片数量，没看到读取路径啊

OutOfRangeError: PaddingFIFOQueue '_2_get_batch/batch/padding_fifo_queue' is closed and has insufficient elements

Hi, I have followed your steps to convert my own tfrecord and start to train, yet there is something wrong called "OutOfRangeError: PaddingFIFOQueue '_2_get_batch/batch/padding_fifo_queue' is closed and has insufficient elements".

Do you know what might be the cause of this error?

Thanks!

为什么我训练时loss一直在上下波动并不收敛，结果也没有框出东西来，类别也是0，啥都检测不到

It seems stop when I train my data

Output is as follows ：

+ set -e
+ export PYTHONUNBUFFERED=True
+ PYTHONUNBUFFERED=True
+ GPU_ID=0
+ DATASET=cow
+ array=($@)
+ len=2
+ EXTRA_ARGS=
+ EXTRA_ARGS_SLUG=
++ date +%Y_%m_%d_%H_%M_%S
+ LOG=logs/FPN_cow.txt.2018_08_31_14_51_58
+ exec
++ tee -a logs/FPN_cow.txt.2018_08_31_14_51_58
tee: logs/FPN_cow.txt.2018_08_31_14_51_58: No such file or directory
+ echo Logging output to logs/FPN_cow.txt.2018_08_31_14_51_58
Logging output to logs/FPN_cow.txt.2018_08_31_14_51_58
+ CUDA_VISIBLE_DEVICES=0
+ python ./tools/train.py
tfrecord path is --> /home/dongpeijie/FPN_TensorFlow/data/tfrecords/cow_train*
/home/dongpeijie/miniconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/ops/gradients_impl.py:93: UserWarning: Converting sparse IndexedSlices to a dense Tensor of unknown shape. This may consume a large amount of memory.
  "Converting sparse IndexedSlices to a dense Tensor of unknown shape. "
model restore from pretrained mode, path is: data/pretrained_weights/resnet_v1_101.ckpt
2018-08-31 14:52:26.532747: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2018-08-31 14:52:26.532790: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2018-08-31 14:52:26.532798: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2018-08-31 14:52:26.532803: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2018-08-31 14:52:26.532808: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
2018-08-31 14:52:28.340651: I tensorflow/core/common_runtime/gpu/gpu_device.cc:940] Found device 0 with properties:
name: Tesla P100-PCIE-16GB
major: 6 minor: 0 memoryClockRate (GHz) 1.3285
pciBusID 0000:06:00.0
Total memory: 15.89GiB
Free memory: 15.60GiB
2018-08-31 14:52:28.340709: I tensorflow/core/common_runtime/gpu/gpu_device.cc:961] DMA: 0
2018-08-31 14:52:28.340716: I tensorflow/core/common_runtime/gpu/gpu_device.cc:971] 0:   Y
2018-08-31 14:52:28.340727: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Creating TensorFlow device (/gpu:0) -> (device: 0, name: Tesla P100-PCIE-16GB, pci bus id: 0000:06:00.0)
restore model

I have waited for a long time without other output information.

Thank you for helping me solving the problem.

您好，请问fast-r-cnn的分类损失函数是否可以更换?我在换的过程中出现了.InvalidArgumentError: tags and values not the same shape: [] != [256] (tag 'RPN_LOSS/cls_loss')这个问题，请问您是否遇到过？

谢谢~

do you have try this code on voc07+12?

I try this code on voc07/12. But it is not good at find other object but person.The car dog car can't be found in the picture.only a few car or other object can be found.

请问这个怎么调整batch_size

Can I change the value of batch-size？

Can I change the value of batch-size？If I change its value, other values need to be modified at the same time？ Thanks！!

SCALE_FACTORS = [10., 5., 1., 0.5]作用是什么。应该怎么修改

checkpoint_path error!

Hello! I run eval.sh ,it occured:
Traceback (most recent call last):
File "./tools/eval.py", line 326, in
eval_dict_convert(args)
File "./tools/eval.py", line 109, in eval_dict_convert
restorer, restore_ckpt = restore_model.get_restorer(checkpoint_path=args.weights)
TypeError: get_restorer() got an unexpected keyword argument 'checkpoint_path'

which datasets to use

Hello:
I just want to know what datasets you use in this project.I can't find any datasets about one target to train.Do I need to crate my own datasets?
Thank you!

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.