jakthra / pathlosspredictionsatelliteimages Goto Github PK

Hie,
I have successfully run the generate_training_test.py and train.py files. However, I get the error in the image below whenever I try to run the predict.py file. I have tried changing the location of the 'exps' directory but it doesn't work. Do you have any idea what I could be missing?

g

when i run generate_training_test.py,it triggers this issue...can ypu help me?
D:\zhang\biyesheji\git\PathLossPredictionSatelliteImages>python ./generate_training_test.py
Traceback (most recent call last):
File "D:\git\PathLossPredictionSatelliteImages\generate_training_test.py", line 10, in
file_generator = fileGen(FEATURE_PATH, OUTPUT_PATH)
File "D:\git\PathLossPredictionSatelliteImages\utils\fileGen.py", line 15, in init
self.create_dataset()
File "D:\git\PathLossPredictionSatelliteImages\utils\fileGen.py", line 26, in create_dataset
self.__construct_training_test()
File "D:\git\PathLossPredictionSatelliteImages\utils\fileGen.py", line 36, in __construct_training_test
self.X_df_train, self.Y_df_train, self.X_df_test, self.Y_df_test = get_training_test_data(self.X_df, self.Y_df, draw=self.draw)
File "D:\git\PathLossPredictionSatelliteImages\utils\drive_test_route_journal.py", line 142, in get_training_test_data
X_df_test, Y_df_test = get_samples_test_route(X_df, Y_df, route)
File "D:\git\PathLossPredictionSatelliteImages\utils\drive_test_route_journal.py", line 110, in get_samples_test_route
geo_df = gp.GeoDataFrame(X_df, geometry=ss)
File "C:\Python39\lib\site-packages\geopandas\geodataframe.py", line 188, in init
self.set_geometry(geometry, inplace=True, crs=crs)
File "C:\Python39\lib\site-packages\geopandas\geodataframe.py", line 347, in set_geometry
frame[geo_column_name] = level
File "C:\Python39\lib\site-packages\geopandas\geodataframe.py", line 1439, in setitem
crs = getattr(self, "crs", None)
File "C:\Python39\lib\site-packages\geopandas\geodataframe.py", line 431, in crs
return self.geometry.crs
File "C:\Python39\lib\site-packages\geopandas\geodataframe.py", line 217, in _get_geometry
geo_cols = list(self.columns[self.dtypes == "geometry"])
File "C:\Python39\lib\site-packages\pandas\core\indexes\base.py", line 5337, in getitem
key = np.asarray(key, dtype=bool)
File "C:\Python39\lib\site-packages\numpy\core_asarray.py", line 102, in asarray
return array(a, dtype, copy=False, order=order)
ValueError: invalid array_struct

Hi Jakob,
I just wanted to check your model that you used in here but when I tried to run model.py, I was first getting an error;

1- File "model.py", line 268, in plot_physics_model
train_dataset, valid_dataset , test_dataset = dataset_factory() #
ValueError: not enough values to unpack (expected 3, got 2)

then I realized when you use generate_training_test.py, we only get training and testing data so I removed valid_dataset. After I am running that it gave me another error but I do not know what to do can you check it out pls?

2- File "model.py", line 276, in plot_physics_model
model = SkynetModel(channels, num_features, image_size, out_channels, rsrp_mu = rsrp_mu, rsrp_std = rsrp_std)
TypeError: init() takes 2 positional arguments but 5 were given

I tried to run your train.py aswell and the code has also issues. That would be nice if you could check all of it. Also, could you to do me a favor and show me your model's summary? That would be very helpful,

Thanks in advance,
Mustafa BAL