ssd_keras

ssd_keras copied to clipboard

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.

2

### If you open a GitHub issue, here is the policy: Your issue must be about one of the following: 1. a bug, 2. a feature request, 3. a documentation...

pucha48

How to detect the speed of the model?

6

I tried this code and got a high accuracy by evaluation.Meanwhile, How could I detect the speed of the model, I mean the object about FPS eval. Could you help...

liguilan1227

output of generator should be a tuple (x, y, sample_weight) or (x, y). Found: None

8

please help me when i run ssd_training.ipynb，my data is 300*300,but have error Epoch 1/120 1/2 [==============>...............] - ETA: 4s - loss: 23.7398Exception in thread Thread-6: Traceback (most recent call last):...

RoseLii

Changes make the code work in 2023

3

Hello everyone, First of all, this is not exactly an issue, but some changes i made to the code so the project work (i tested on kaggle). I haven't test...

PTN407

When I try to fit the model, i get "TypeError: Expected any non-tensor type, got a tensor instead."

hnushrat