mahmoodul
commented
2 years ago Hi, When I am running the command "python3 train.py euroc euroc_model_trained_by_me.hdf5" I am getting the following error
Model: "model"
Layer (type) Output Shape Param # Connected to
x1 (InputLayer) [(None, 200, 3)] 0 []
x2 (InputLayer) [(None, 200, 3)] 0 []
conv1d (Conv1D) (None, 190, 128) 4352 ['x1[0][0]']
conv1d_2 (Conv1D) (None, 190, 128) 4352 ['x2[0][0]']
conv1d_1 (Conv1D) (None, 180, 128) 180352 ['conv1d[0][0]']
conv1d_3 (Conv1D) (None, 180, 128) 180352 ['conv1d_2[0][0]']
max_pooling1d (MaxPooling1D) (None, 60, 128) 0 ['conv1d_1[0][0]']
max_pooling1d_1 (MaxPooling1D) (None, 60, 128) 0 ['conv1d_3[0][0]']
concatenate (Concatenate) (None, 60, 256) 0 ['max_pooling1d[0][0]',
'max_pooling1d_1[0][0]']
bidirectional (Bidirectional) (None, 60, 256) 395264 ['concatenate[0][0]']
dropout (Dropout) (None, 60, 256) 0 ['bidirectional[0][0]']
bidirectional_1 (Bidirectional (None, 256) 395264 ['dropout[0][0]']
)
dropout_1 (Dropout) (None, 256) 0 ['bidirectional_1[0][0]']
dense (Dense) (None, 3) 771 ['dropout_1[0][0]']
dense_1 (Dense) (None, 4) 1028 ['dropout_1[0][0]']
================================================================================================== Total params: 1,161,735 Trainable params: 1,161,735 Non-trainable params: 0
Model: "model_1"
Layer (type) Output Shape Param # Connected to
x1 (InputLayer) [(None, 200, 3)] 0 []
x2 (InputLayer) [(None, 200, 3)] 0 []
y1_true (InputLayer) [(None, 3)] 0 []
y2_true (InputLayer) [(None, 4)] 0 []
model (Functional) [(None, 3), 1161735 ['x1[0][0]',
(None, 4)] 'x2[0][0]']
custom_multi_loss_layer (Custo (None, 14) 2 ['y1_true[0][0]',
mMultiLossLayer) 'y2_true[0][0]',
'model[0][0]',
'model[0][1]']
================================================================================================== Total params: 1,161,737 Trainable params: 1,161,737 Non-trainable params: 0
WARNING:tensorflow:Model failed to serialize as JSON. Ignoring...
Layer CustomMultiLossLayer has arguments ['self', 'nb_outputs']
in __init__ and therefore must override get_config().
Example:
class CustomLayer(keras.layers.Layer): def init(self, arg1, arg2): super().init() self.arg1 = arg1 self.arg2 = arg2
def get_config(self):
config = super().get_config()
config.update({
"arg1": self.arg1,
"arg2": self.arg2,
})
return configEpoch 1/500
2021-12-19 23:46:32.084681: I tensorflow/stream_executor/cuda/cuda_dnn.cc:366] Loaded cuDNN version 8301
411/411 [==============================] - ETA: 0s - loss: 0.0422
Epoch 00001: val_loss improved from inf to -0.05318, saving model to model_checkpoint.hdf5
Traceback (most recent call last):
File "train.py", line 137, in __init__ and therefore must override get_config().
Example:
class CustomLayer(keras.layers.Layer): def init(self, arg1, arg2): super().init() self.arg1 = arg1 self.arg2 = arg2
def get_config(self):
config = super().get_config()
config.update({
"arg1": self.arg1,
"arg2": self.arg2,
})
return config
jpsml
Hi, When I am running the command "python3 train.py euroc euroc_model_trained_by_me.hdf5" I am getting the following error
Traceback (most recent call last): File "train.py", line 137, in
main()
File "train.py", line 114, in main
train_model = create_train_model_6d_quat(pred_model, window_size)
File "/mah/AI/6-DOF-Inertial-Odometry-master/model.py", line 115, in create_train_model_6d_quat
out = CustomMultiLossLayer(nb_outputs=2)([y1_true, y2_true, y1_pred, y2_pred])
File "/home/aisl/.local/lib/python3.8/site-packages/keras/utils/traceback_utils.py", line 67, in error_handler
raise e.with_traceback(filtered_tb) from None
File "/home/aisl/.local/lib/python3.8/site-packages/tensorflow/python/autograph/impl/api.py", line 699, in wrapper
raise e.ag_error_metadata.to_exception(e)
TypeError: Exception encountered when calling layer "custom_multi_loss_layer" (type CustomMultiLossLayer).
in user code:
Call arguments received: • inputs=['tf.Tensor(shape=(None, 3), dtype=float32)', 'tf.Tensor(shape=(None, 4), dtype=float32)', 'tf.Tensor(shape=(None, 3), dtype=float32)', 'tf.Tensor(shape=(None, 4), dtype=float32)']