loss: nan - acc: nan - val_loss: nan - val_acc: nan Why

[qq191513]

trafficstars

python train.py --save_weights_path=weights/ex1 --train_images="data/dataset1/images_prepped_train/" --train_annotations="data/dataset1/annotations_prepped_train/" --val_images="data/dataset1/images_prepped_test/" --val_annotations="data/dataset1/annotations_prepped_test/" --n_classes=10 --input_height=320 --input_width=640 --model_name="vgg_segnet"

i follow what the tutorial,but the result is this: Model output shape (None, 51200, 10) Epoch 1/1 Epoch 1/1 512/512 [==============================] - 127s 247ms/step - loss: nan - acc: nan - val_loss: nan - val_acc: nan Epoch 1/1 512/512 [==============================] - 127s 248ms/step - loss: nan - acc: nan - val_loss: 51200.0000 - val_acc: 0.0000e+00 Epoch 1/1 512/512 [==============================] - 127s 247ms/step - loss: nan - acc: nan - val_loss: nan - val_acc: nan Epoch 1/1 512/512 [==============================] - 127s 248ms/step - loss: nan - acc: nan - val_loss: nan - val_acc: nan Epoch 1/1 512/512 [==============================] - 127s 248ms/step - loss: nan - acc: nan - val_loss: 51200.0000 - val_acc: 0.0000e+00

[divamgupta]

Could you share the data for which you see this? Maybe the dataset is very imbalanced.