When I was training FPGA power data, an unknown error occurred！

[zzulb]

Hello, when I use the following command line to train FPGA power data, if -pr defaults to 1, the following error will be reported.

1. python3 new_train.py -i /DLSCA/TinyPower/fpga/FPGA1_K1_200k.npz -o /DLSCA/TinyPower/fpga -m /DLSCA/TinyPower/fpga -e 100 -tb 2 -lm ID -tn 10000 -aw 1800_2800 -rp /DLSCA/TinyPower/MiniDrop/Score_Algo -CP TRUE -CPP /DLSCA/TinyPower/MiniDrop/Score_Algo

use the self-defined attack window
training with 10000 traces
trace data shape is: (10000, 0)
[0, 0, 0, 0, 0, 0, 0]
Traceback (most recent call last):
File "new_train.py", line 197, in
train(opts)
File "new_train.py", line 172, in train
model_pruned= model_zoo.cnn_best(input_shape, r, emb_size=emb_size, classification=True)
File "/DLSCA/TinyPower/MiniDrop/utils/model_zoo.py", line 96, in cnn_best
x = Conv1D(int(64*r[0]), 11, strides=2, activation='relu', padding='same', name='block1_conv1')(inp)
File "/usr/local/lib/python3.8/dist-packages/keras/src/dtensor/utils.py", line 96, in _wrap_function
init_method(layer_instance, *args, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/keras/src/layers/convolutional/conv1d.py", line 156, in init
super().init(
File "/usr/local/lib/python3.8/dist-packages/keras/src/layers/convolutional/base_conv.py", line 129, in init
raise ValueError(
ValueError: Invalid value for argument filters. Expected a strictly positive value. Received filters=0.

2. When I set -pr to 0, there is still an error.
   python3 new_train.py -i /DLSCA/TinyPower/fpga/FPGA1_K1_200k.npz -o /DLSCA/TinyPower/fpga -m /DLSCA/TinyPower/fpga -e 100 -tb 2 -lm ID -tn 10000 -aw 1800_2800 -pr 0 -rp /DLSCA/TinyPower/MiniDrop/Score_Algo -CP TRUE -CPP /DLSCA/TinyPower/MiniDrop/Score_Algo

use the self-defined attack window
training with 10000 traces
trace data shape is: (10000, 0)
[1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0]
[log] --- finish construct the cnn2 model
Traceback (most recent call last):
File "new_train.py", line 197, in
train(opts)
File "new_train.py", line 173, in train
model = load_model(model_file)
File "/usr/local/lib/python3.8/dist-packages/keras/src/saving/saving_api.py", line 238, in load_model
return legacy_sm_saving_lib.load_model(
File "/usr/local/lib/python3.8/dist-packages/keras/src/utils/traceback_utils.py", line 70, in error_handler
raise e.with_traceback(filtered_tb) from None
File "/usr/local/lib/python3.8/dist-packages/keras/src/saving/legacy/save.py", line 234, in load_model
raise IOError(
OSError: No file or directory found at /DLSCA/TinyPower/fpga/model/best_model.h5

May I ask how to modify the command line and configuration if training FPGA power data. Additionally, how can the above errors be resolved.