pierluigiferrari/ssd_keras

Issues

• Changes make the code work in 2023

  #393 opened a year ago by PTN407
  2

• Urgent!! Invalid Loss

  #384 opened 3 years ago by jc-barreto
  4

• error while training with custom dataset in COCO format

  #395 opened a year ago by Avaneesh-S
  0

• custom SSD300 model

  #394 opened a year ago by Avaneesh-S
  0

• TypeError: Expected any non-tensor type, got a tensor instead.

  #392 opened a year ago by hnushrat
  0

• ValueError: Layer model expects 1 input(s), but it received 2 input tensors. Inputs received: [<tf.Tensor 'IteratorGetNext:0' shape=(None, None, None, None) dtype=uint8>, <tf.Tensor 'IteratorGetNext:1' shape=(None, None, None) dtype=float32>]

  #380 opened 3 years ago by suprateembanerjee
  23

• Label error during Coco Training

  #391 opened 2 years ago by hamzakhalil798
  1

• Dimension must be equal error.

  #361 opened 4 years ago by hiren-2911
  1

• The device being used is CPU while capturing image from webcam. How do I use my GPU for processing instead?

  #390 opened 2 years ago by GabrielRiente
  0

• Pascal VOC Training Person Detection

  #388 opened 2 years ago by aidansmyth95
  0

• What are the requirements to run this code?.

  #386 opened 2 years ago by myasser63
  1

• Parameters of the model

  #381 opened 3 years ago by maoyuanpeng
  1

• Bouding boxes predictions are concentrated in left top corner

  #382 opened 3 years ago by toschilt
  1

• Ambiguous dimension while trying to load weights.

  #383 opened 3 years ago by federicoAntosiano
  0

• missing requirement.txt

  #350 opened 4 years ago by DhDeepLIT
  2

• How to calculate accuracy during training?

  #366 opened 4 years ago by sachinkmohan
  2

• ValueError: An operation has `None` for gradient. Please make sure that all of your ops have a gradient defined (i.e. are differentiable). Common ops without gradient: K.argmax, K.round, K.eval.

  #379 opened 3 years ago by gbinduo
  0

• Error: InvalidArgumentError: All dimensions except 2 must match... (on concatenating)

  #355 opened 4 years ago by babak-abad
  2

• While training I got training terminate error . Epoch 00001: LearningRateScheduler setting learning rate to 0.001. 1/10 [==>...........................] - ETA: 4:08 - loss: nanBatch 0: Invalid loss, terminating training Epoch 00001: saving model to ssd512_URPC2018_epoch-01.h5 Process finished with exit code 0

  #378 opened 3 years ago by rupalandge
  0

• ValueError: Error when checking input: expected input_3 to have 4 dimensions, but got array with shape

  #377 opened 3 years ago by jhaggle
  0

• load weight

  #376 opened 3 years ago by spy001s
  0

• WARNING:tensorflow:Gradients do not exist for variables ['conv4_3/bias:0',...] when minimizing the loss.

  #374 opened 3 years ago by jessicametzger
  1

• "Invalid argument: Index out of range using input dim 0; input has only 0 dims" during ssd300 model training

  #375 opened 3 years ago by jessicametzger
  0

• InvalidArgumentError when compiling model with ssd_loss

  #372 opened 3 years ago by jessicametzger
  1

• Requirements Versioning not working with python3.8

  #370 opened 3 years ago by TheSeriousProgrammer
  0

• Error while loading model

  #367 opened 3 years ago by cktboy
  1

• KeyError cumulative_true_positives[class_id]

  #368 opened 3 years ago by d-simple
  1

• How to set the param seems like intensity_mean、min_scale 、 aspect_ratios and scales?

  #369 opened 3 years ago by liguilan1227
  0

• Help needed!!!

  #359 opened 4 years ago by hiren-2911
  43

• An operation has `None` for gradient. Please make sure that all of your ops have a gradient defined (i.e. are differentiable). Common ops without gradient: K.argmax, K.round, K.eval.

  #363 opened 4 years ago by pucha48
  2

• ValueError: None values not supported.

  #364 opened 4 years ago by pucha48
  1

• How to detect the speed of the model?

  #360 opened 4 years ago by liguilan1227
  6

• TypeError: a bytes-like object is required, not 'str'

  #365 opened 4 years ago by sachinkmohan
  1

• acc and val_acc are good but there is no prediction

  #352 opened 4 years ago by mouad47
  2

• Hi, can you help me out in implementing ssd 300 on my custom dataset and training it from scratch. I am not that much skilled with object detection coding myself but I want to use your implementation in my research project. So if you can help me out by guiding how i can use this repo for my custom dataset rather than voc07 and voc12, that'll be really helpful. Thanks in advance.

  #362 opened 4 years ago by code-demoe
  0

• Cant set attributes!

  #358 opened 4 years ago by hiren-2911
  0

• Dimensions unmatch when I was loading pretrained model weight

  #357 opened 4 years ago by SYH0568
  1

• Opencv readnetfromTensorflow error

  #356 opened 4 years ago by Zrufy
  1

• Error: AttributeError: 'Conv2D' object has no attribute 'inbound_nodes'

  #354 opened 4 years ago by babak-abad
  1

• Transfer Learning tutorial incomplete

  #341 opened 4 years ago by JoaoGranzotti
  2

• Error running the fit_generator method

  #353 opened 4 years ago by Sri-user
  1

• Error in transfer learning part

  #351 opened 4 years ago by Monster-Gaming-Studios
  5

• "list index out of range" loss function issue when running with tf.keras

  #348 opened 4 years ago by jessicametzger
  2

• hello

  #349 opened 4 years ago by liuxiiang
  1

• Weights for ssd7 trained over Udacity dataset

  #343 opened 4 years ago by sdabhi23
  2

• TypeError: __call__() missing 1 required positional argument: 'labels'

  #346 opened 4 years ago by leonel11
  5

• Is there a paper behind SSD7?

  #347 opened 4 years ago by AlyShmahell
  1

• Stop iteration

  #345 opened 4 years ago by rd20karim
  4

• Expected Training Speed?

  #344 opened 4 years ago by Tomiha
  5

• Small objects detection

  #342 opened 4 years ago by JoaoGranzotti
  1