Index Error

[s86707]

Hi, I'm using my own Input-Data and I'm becoming the: Index Error: list out of range.

Here is the full issue:

Traceback (most recent call last):
File "dsen2cr_main.py", line 179, in
run_dsen2cr(args.predict_file, args.resume_file)
File "dsen2cr_main.py", line 160, in run_dsen2cr
max_val_sar, scale)
File "C:\Users\maria\Documents\GitHub\dsen2-cr\Code\dsen2cr_tools.py", line 169, in predict_dsen2cr
for i, (data, y) in enumerate(predict_generator):
File "C:\Users\maria\anaconda3\envs\dsen2cr\lib\site-packages\keras\utils\data_utils.py", line 372, in iter
for item in (self[i] for i in range(len(self))):
File "C:\Users\maria\anaconda3\envs\dsen2cr\lib\site-packages\keras\utils\data_utils.py", line 372, in
for item in (self[i] for i in range(len(self))):
File "C:\Users\maria\Documents\GitHub\dsen2-cr\Code\tools\dataIO.py", line 280, in getitem
self.random_crop_paramy[indexes])
File "C:\Users\maria\Documents\GitHub\dsen2-cr\Code\tools\dataIO.py", line 308, in __data_generation
random_crop_paramy_temp, data_type=3)
File "C:\Users\maria\Documents\GitHub\dsen2-cr\Code\tools\dataIO.py", line 407, in get_batch
data_image = self.get_data_image(ID, data_type, random_crop_paramx_temp[i], random_crop_paramy_temp[i])
File "C:\Users\maria\Documents\GitHub\dsen2-cr\Code\tools\dataIO.py", line 354, in get_data_image
data_path = os.path.join(self.input_data_folder, ID[data_type], ID[4]).lstrip()
IndexError: list index out of range

The output folder is also created but don't get any output images.
It wolud be very nice if someone could give me an advice for this error.

[ameraner]

Hi @s86707 , thank you for your issue. The error message points to an issue in your data .csv file (I assume that the list out-of-range error comes from the ID indexing). Are you sure that your csv file has the correct number of columns, as here https://github.com/ameraner/dsen2-cr/blob/main/Data/datasetfilelist.csv? You could also check that it is being read correctly by checking the outputs of this function:

dsen2-cr/Code/tools/dataIO.py

Line 40 in 59e81ae

return train_filelist, val_filelist, test_filelist

[s86707]

Hi ameraner, thank you for your answer. I have used the wrong checkpoint (without SAR). Now I try to run the code without GPU and get the ValueError: Dimension 0 in both shapes must be equal, but are 3 and 256. Shapes are [3,3,13,256] and [256,15,3,3]. for 'Assign' (op: 'Assign') with input shapes: [3,3,13,256], [256,15,3,3]. I checked the input formats and they are all the same (2328, 2500, 3). Also the 'channels first' line is active. Could the error appear because I set the value for the n_gpus incorrectly? If so, to what value would I need to set it? Thanks in advance and best regards Marian Am 2023-08-01 17:49, schrieb Andrea Meraner:

…

Hi @s86707 [1] , thank you for your issue. The error message points to an issue in your data .csv file (I assume that the list out-of-range error comes from the ID indexing). Are you sure that your csv file has the correct number of columns, as here https://github.com/ameraner/dsen2-cr/blob/main/Data/datasetfilelist.csv? You could also check that it is being read correctly by checking the outputs of this function: https://github.com/ameraner/dsen2-cr/blob/59e81ae0d013bcae992d078e92a1175cc4cbf257/Code/tools/dataIO.py#L40 -- Reply to this email directly, view it on GitHub [2], or unsubscribe [3]. You are receiving this because you were mentioned.Message ID: ***@***.***> Links: ------ [1] https://github.com/s86707 [2] #11 (comment) [3] https://github.com/notifications/unsubscribe-auth/A7AFQBT5UEOJAG6VJ53UZDLXTEQRDANCNFSM6AAAAAA26FWUFQ

[ameraner]

Hi @s86707 , it's a different error, but it sounds similar to what has been reported here by @CatalinVulcan #10 (comment) - maybe also for you it's a numpy version issue?

[zhaotianle123]

I had the same problem as you, can I ask how you solved it in the end?

[ameraner]

@CatalinVulcan reported that by downgrading numpy he got a bit farther, but then had other incompatibility issues. If you ever get it running, feel free to open a PR or propose changes.

[ameraner]

I'm closing this issue since the original issue is solved, and the second issue is reported in #10