search

xggIoU / centernet_tensorflow_wilderface_voc

This is the unofficial implementation of the "CenterNet:Objects as Points".Just a simple try with self-modified shufflenetv2 and yolov3.If you want better results, you need more experiments.
MIT License
111 stars 25 forks source link

How to Convert WIDER_Face to .tfrecord? #2

Open CWF-999 opened 5 years ago

CWF-999 commented 5 years ago

features = {"img_raw_b": tf.FixedLenFeature([], tf.string), # 定长特征解析 "img_raw_g": tf.FixedLenFeature([], tf.string), "img_raw_r": tf.FixedLenFeature([], tf.string), "label": tf.FixedLenFeature([],tf.string), "width": tf.FixedLenFeature([], tf.int64), "height": tf.FixedLenFeature([], tf.int64)} How are the parameters of these features calculated? Can you share the conversion file, thank you

xggIoU commented 5 years ago

These days, I will update the data production after I go home. If you can't wait, you can make it in the following way：imagedata classid xmin ymin xmax ymax. if you detect face,classid is 0.

CWF-999 commented 5 years ago

Ok, thanks again，i will try it.

------------------ 原始邮件 ------------------ 发件人: "xggIoU"notifications@github.com; 发送时间: 2019年6月12日(星期三) 中午11:22 收件人: "xggIoU/centernet_tensorflow_wilderface_voc"centernet_tensorflow_wilderface_voc@noreply.github.com; 抄送: "陈文峰"961403391@qq.com;"Author"author@noreply.github.com; 主题: Re: [xggIoU/centernet_tensorflow_wilderface_voc] How to ConvertWIDER_Face to .tfrecord? (#2)

These days, I will update the data production after I go home. If you can't wait, you can make it in the following way：imagedata classid xmin ymin xmax ymax. if you detect face,classid is 0.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or mute the thread.

ZX-HUB561 commented 5 years ago

Can you share the code of how to create tfrecord? Thank you very much.

xggIoU commented 5 years ago

Sorry, I’m a little busy lately, I’ve updated the code for creating data under folder img2tfrecords_detection.

ZX-HUB561 commented 5 years ago

I have seen it. Thank you for your sharing. Best regards. Zhixiang Yin

在 2019年6月23日，上午12:22，xggIoU notifications@github.com 写道：

Sorry, I’m a little busy lately, I’ve updated the code for creating data under folder img2tfrecords_detection.

— You are receiving this because you commented. Reply to this email directly, view it on GitHub, or mute the thread.

CWF-999 commented 5 years ago

Can you share the label of WIDER_Face, the official label does not match your format?

xggIoU commented 5 years ago

I have uploaded wilderface label.

CWF-999 commented 5 years ago

Thank you so much.

CWF-999 commented 5 years ago

PS D:\pythoncode\centernet_tensorflow_wilderface_voc-master> python .\train.py WARNING:tensorflow:From D:\Python3.5\lib\site-packages\tensorflow\python\framework\op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version. Instructions for updating: Colocations handled automatically by placer. WARNING:tensorflow:From D:\pythoncode\centernet_tensorflow_wilderface_voc-master\shufflenetv2_centernet.py:80: conv2d (from tensorflow.python.layers.convolutional) is deprecated and will be removed in a future version. Instructions for updating: Use keras.layers.conv2d instead. WARNING:tensorflow:From D:\Python3.5\lib\site-packages\tensorflow\python\ops\math_ops.py:3066: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use tf.cast instead. 2019-06-24 16:24:15.608201: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 2019-06-24 16:24:15.851322: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1433] Found device 0 with properties: name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.733 pciBusID: 0000:01:00.0 totalMemory: 6.00GiB freeMemory: 4.97GiB 2019-06-24 16:24:15.859099: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1512] Adding visible gpu devices: 0 2019-06-24 16:24:16.248122: I tensorflow/core/common_runtime/gpu/gpu_device.cc:984] Device interconnect StreamExecutor with strength 1 edge matrix: 2019-06-24 16:24:16.252627: I tensorflow/core/common_runtime/gpu/gpu_device.cc:990] 0 2019-06-24 16:24:16.255085: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1003] 0: N 2019-06-24 16:24:16.258433: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4714 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1) PS D:\pythoncode\centernet_tensorflow_wilderface_voc-master>

When I run train.py, the program quits without error, could you help me?