ssd_keras

ssd_keras copied to clipboard

I get the issue above when trying to train on a dataset of images that I have created myself. When I insted use the SVHN dataset, it works fine. Could...

jhaggle

hi when we what to train the ssd300training file, in the weight loading cell , we have error how can we solve that thank you ValueError: Cannot create group in...

spy001s

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

1

I am using ssd_keras with tensorflow2 backend to train the ssd300 model (using [this ssd_keras_tf2 repository)](https://github.com/IntranelConsulting/ssd_keras_tf2) and everything "works," except I keep running into this error when I start training:...

jessicametzger

I am using ssd_keras with tensorflow 1.15 backend (I was originally using tensorflow 2.20 but ran into [this issue](https://github.com/pierluigiferrari/ssd_keras/issues/374)) and it throws an InvalidArgumentError the moment I start the training....

jessicametzger

Looks like tensorflow==1.* is not supported in python3.8 , so the project wont work with python3.8 I actually wasted a lot of time in figuring it out, Kindly add the...

TheSeriousProgrammer

Error while loading model

1

model downloaded from provided link for model VGG_VOC0712_SSD_300x300_iter_120000.h5' tried with other model links, but getting same error **code:** model = load_model(model_path, custom_objects={'AnchorBoxes': AnchorBoxes, 'L2Normalization': L2Normalization, 'DecodeDetections': DecodeDetections, 'compute_loss': ssd_loss.compute_loss}) Error:...

cktboy

KeyError cumulative_true_positives[class_id]

1

In **ssd300_evaluation.ipynb** when running evaluation with custom/cut dataset there can be zero predictions for specific class which results in KeyError on line ``` average_precision_evaluator.py ... def compute_precision_recall(...) ... tp =...

d-simple

Thank you for your code. After your work I trained the SSD succesfully. While when I trained my own dataset rang in [480,600] by rectify the ssd7.py, I am confused...

liguilan1227

Help needed!!!

43

## Please help. - [ ] Hello @pierluigiferrari I am trying to train SSD300 model but i am not getting good results. The predictor is predicting too many bounding boxes...

hiren-2911

ValueError: None values not supported.

1

Call initializer instance with the dtype argument instead of passing it to the constructor Traceback (most recent call last): File "transfer_learning_new.py", line 477, in initial_epoch=initial_epoch) File "/usr/local/lib/python3.6/dist-packages/keras/legacy/interfaces.py", line 87, in...

pucha48