balancap/SSD-Tensorflow

Issues

• how many epochs ?

  #396 opened 3 years ago by riyaj8888
  1

• checkpoint loading error

  #397 opened 3 years ago by riyaj8888
  0

• loss can't converge and all detect results are 15(person)

  #355 opened 6 years ago by maxlchina
  2

• How to prepare my own training data

  #390 opened 4 years ago by ArtlyStyles
  2

• > 根据前面人的提示，在代码中注释掉关于checkpoint就可以运行了。

  #394 opened 4 years ago by qipengh
  0

• 运行train_ssd_network时报错

  #393 opened 4 years ago by MA000LLAIN
  1

• ssd_notebook.ipynb运行错误 求大佬帮忙解决

  #373 opened 5 years ago by chde222
  1

• How to transfer the .ckpt to .pb?

  #389 opened 4 years ago by lucky-xu-1994
  9

• tfrecords no such file or directory

  #359 opened 5 years ago by slavakung
  3

• ValueError: Dimension 0 in both shapes must be equal, but are 412776 and 34928. Shapes are [412776] and [34928]. for 'ssd_losses/Select' (op: 'Select') with input shapes: [34928], [412776], [34928].

  #388 opened 5 years ago by BieberZhang
  2

• can webcam demo or video demo be supplied?

  #392 opened 4 years ago by futureflsl
  0

• ValueError:"Can't load save_path when it is None."

  #358 opened 6 years ago by yuye-img
  1

• loss and map

  #391 opened 4 years ago by world2025
  0

• why the result of label is the same answer?

  #387 opened 5 years ago by lu-meng-zhe
  1

• SSD能训练png图片，但不能测试png图片吗？

  #377 opened 5 years ago by dongzi19941026
  4

• The loss is not convergent and the test result is poor. It is recommended to use other versions.The loss is not convergent and the test result is poor. It is recommended to use other versions.

  #378 opened 5 years ago by dongzi19941026
  2

• more than 21 classes

  #386 opened 5 years ago by flthibau
  0

• Optimizer epsilon default value too high

  #385 opened 5 years ago by anishchopra
  0

• ValueError: Cannot reshape a tensor with 3881472 elements to shape [32,84,38,4,21] (8580096 elements) for 'ssd_300_vgg/block4_box/Reshape_1'

  #384 opened 5 years ago by Davdi
  0

• Clarification: TFE =/= TFX?

  #383 opened 5 years ago by mythrandire
  0

• Train with 224*224*3 Input

  #382 opened 5 years ago by parth1595
  0

• I0313 15:10:55.695348 140095594268544 learning.py:507] global step 2290: loss = 24.0642 (4.784 sec/step)

  #381 opened 5 years ago by haobabuhaoba
  0

• I modified the loss function to get good results.

  #366 opened 5 years ago by hccho2
  2

• You must supply the dataset directory with --dataset_dir

  #380 opened 5 years ago by chenjjjjuu
  0

• NotFoundError: NewRandomAccessFile failed to Create/Open

  #379 opened 5 years ago by gongyu0217
  0

• import question, why the model trained by train_ssd_network.py，at last, we can not get anythings after inference?

  #349 opened 6 years ago by zmhik
  1

• Train your own dataset to report an error, run train_ssd_network to report an error

  #376 opened 5 years ago by liu978079474
  2

• tensorflow:Caught OutOfRangeError. Stopping Training. FIFOQueue '_5_prefetch_queue/fifo_queue' is closed and has insufficient elements

  #375 opened 5 years ago by ZZZ951008
  0

• input data type

  #374 opened 5 years ago by ylqi007
  0

• coco dataset problem

  #372 opened 5 years ago by zyz111
  0

• Inference speed is slow?

  #371 opened 5 years ago by kunalgoyal9
  0

• Mobilenet SSD?

  #370 opened 5 years ago by kunalgoyal9
  0

• version problem

  #369 opened 5 years ago by VolleyballBird
  0

• Hello,sir. Can you write the SSD in tensorflow1.13 or newer?

  #367 opened 5 years ago by spooms11
  1

• Fine-tuning a network trained on ImageNet doesn't work

  #368 opened 5 years ago by spooms11
  0

• Unstable loss, extremely low map

  #361 opened 5 years ago by chenaifang
  5

• This code is not reproducible. Why there are so many stars? If you load it from vgg16, the effect of map is poor.

  #365 opened 5 years ago by navy63
  1

• How can use model inception_v3 instead of ssd_300_vgg?

  #364 opened 5 years ago by cjaai
  0

• UnknownError (see above for traceback): Failed to get convolution algorithm

  #348 opened 6 years ago by CWF-999
  1

• coordinator.py:219] Error reported to Coordinator: You must feed a value for placeholder tensor...

  #363 opened 5 years ago by niumeng07
  0

• Is the coordinate position of the detection box upper left corner, lower right corner or upper left corner with width and height?

  #362 opened 5 years ago by AndyHon
  0

• cannot import name 'pascalvoc to tfrecords'

  #360 opened 5 years ago by Pepe-Chen
  0

• Is there something wrong in ssd_vgg_preprocessing.py while preprocess_for_train

  #357 opened 6 years ago by kingrain213
  1

• not a valid checkpoint

  #356 opened 6 years ago by Jnyle
  0

• How can i read the tensorboard output

  #354 opened 6 years ago by AishuaiYao
  0

• low map with ssd-300-voc2017

  #347 opened 6 years ago by zmhik
  1

• How to add earlystopping to this project?

  #353 opened 6 years ago by leavewave
  0

• a curious phenomenon about inference time on different image size

  #352 opened 6 years ago by kagurua
  0

• How is your loss performance

  #351 opened 6 years ago by Rayholle
  0

• Training a single class detection model

  #350 opened 6 years ago by satyajithj
  1