Program getting terminated after a particular error about object-localization HOT 1 OPEN

Hi Srinath,

example_1 and example_2 are easy to understand, but will often produce really bad results. example_3 and example_4 are much better (even for single object recognition) since they are based on actual papers. For example, I used example_1 for OCR and also got bad results but with example_4 I obtained >85% IoU.

If you still want to use example_1, try setting trainable=True and/or adding some Conv2D layers. The screenshot you sent is actually showing that the network is improving. You can see that val_mse is initially 141 and then goes down to 120, but the improvements are not big enough.

If you configured TensorFlow correctly, the GPU will be used automatically. Check tf.test.is_gpu_available().

-- Lars

from object-localization.