socret360 / object-detection-in-keras Goto Github PK

I am trying to use SSD300 to train on my own dataset and I don't know from where to start to train the model. Can you guide on how to train the model

While training, loss is nan on the custom dataset.

Here is the error which is displayed:
1/562 [..............................] - ETA: 1:39:05 - loss: nanBatch 0: Invalid loss, terminating training
/home/user/Shared Tasks/proj/Self_driving_cars/object-detection-in-keras/utils/bbox_utils/iou.py:31: RuntimeWarning: divide by zero encountered in true_divide
res = intersect / union
562/562 [==============================] - 51s 73ms/step - loss: nan - val_loss: nan

To reproduce the environment requirements.txt file or env.yml file is needed. Please add !

Hi,

I'm dealing with an issue in a code but when I'm trying to connect my VGG16 train by myself to your ssd300. During the training, an error kill the process. It's about a problem of shape in the loss function. For more precision i give you the exact text show in terminal :

tensorflow.python.framework.errors_impl.InvalidArgumentError:  Incompatible shapes: [1,8732,4] vs. [1,10,0]
	 [[node compute/sub_1 (defined at /losses/smooth_l1_loss.py:22) ]] [Op:__inference_train_function_6041]

Errors may have originated from an input operation.
Input Source operations connected to node compute/sub_1:
 compute/strided_slice_2 (defined at /losses/ssd_loss.py:43)	
 compute/strided_slice_3 (defined at /losses/ssd_loss.py:44)

the two lines mention in ssd_loss are :

bbox_true = y_true[:, :, -12:-8]
bbox_pred = y_pred[:, :, -12:-8]

A little precison about my vgg16, I'm using a binary vgg16 to detect just one class.
if you have an idea about this problem it's will be very helpful. Thank you for your project who is very clear and complete.

I believe "split_file=args.training_split" should be "split_file=args.validation_split". FYI.