swook / GazeML

Gaze Estimation using Deep Learning, a Tensorflow-based framework.
MIT License
522 stars 140 forks source link

Train-data parameter in elg-demo file #74

Open aveenakottwani opened 3 years ago

aveenakottwani commented 3 years ago

Why is train-data parameter present in the constructor for testing the model? Since the constructor calls _build_all_models methods and builds the model during testing? Can't the model be loaded directly using weights instead of creating the model again?

Using train-data parameter gives me this error: /usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/variable_scope.py in _get_single_variable(self, name, shape, dtype, initializer, regularizer, partition_info, reuse, trainable, collections, caching_device, validate_shape, use_resource, constraint, synchronization, aggregation) 866 tb = [x for x in tb if "tensorflow/python" not in x[0]][:5] 867 raise ValueError("%s Originally defined at:\n\n%s" % --> 868 (err_msg, "".join(traceback.format_list(tb)))) 869 found_var = self._vars[name] 870 if not shape.is_compatible_with(found_var.get_shape()):

ValueError: Variable hourglass/pre/conv/kernel already exists, disallowed. Did you mean to set reuse=True or reuse=tf.AUTO_REUSE in VarScope? Originally defined at:

Could you please help me fix this error and explain why _build_all_models method in model.py is called during testing??