Training deep learning model fail (considered addtional input raster)

[TAMTzeHuey]

Hi, 

My training deep learnng model fail when I considered additional input raster during the export training data step. How can I solve this issue? 

[DanPatterson]

What were the error message(s)?

Were you using this?

Export Training Data For Deep Learning (Image Analyst)—ArcGIS Pro | Documentation

[TAMTzeHuey]

Below is the error message:

Train Deep Learning Model
=====================
Parameters

Input Training Data 'C:\Users\Tam\Downloads\MD15032023\Test 6\Training Data\1024'
Output Model C:\Users\Tam\Downloads\MD15032023\Test 6\Training Model\1024\Deeplab_40
Max Epochs 20
Model Type DEEPLAB
Batch Size 8
Model Arguments class_balancing False;mixup False;focal_loss False;ignore_classes #;chip_size 224;monitor valid_loss
Learning Rate
Backbone Model RESNET34
Pre-trained Model
Validation % 10
Stop when model stops improving STOP_TRAINING
Output Model
Freeze Model FREEZE_MODEL
=====================
Environments

Processor Type GPU
=====================
Messages

Start Time: Tuesday, 23 May, 2023 2:17:42 PM
Traceback (most recent call last):
File "c:\program files\arcgis\pro\Resources\ArcToolbox\toolboxes\Image Analyst Tools.tbx\TrainDeepLearningModel.tool\tool.script.execute.py", line 397, in <module>
execute()
File "c:\program files\arcgis\pro\Resources\ArcToolbox\toolboxes\Image Analyst Tools.tbx\TrainDeepLearningModel.tool\tool.script.execute.py", line 341, in execute
training_model_object.fit(
File "C:\Program Files\ArcGIS\Pro\bin\Python\envs\arcgispro-py3\lib\site-packages\arcgis\learn\models\_arcgis_model.py", line 924, in fit
lr = self.lr_find(allow_plot=False)
File "C:\Program Files\ArcGIS\Pro\bin\Python\envs\arcgispro-py3\lib\site-packages\arcgis\learn\models\_arcgis_model.py", line 741, in lr_find
raise e
File "C:\Program Files\ArcGIS\Pro\bin\Python\envs\arcgispro-py3\lib\site-packages\arcgis\learn\models\_arcgis_model.py", line 738, in lr_find
self.learn.lr_find()
File "C:\Program Files\ArcGIS\Pro\bin\Python\envs\arcgispro-py3\lib\site-packages\fastai\train.py", line 41, in lr_find
learn.fit(epochs, start_lr, callbacks=[cb], wd=wd)
File "C:\Program Files\ArcGIS\Pro\bin\Python\envs\arcgispro-py3\lib\site-packages\fastai\basic_train.py", line 200, in fit
fit(epochs, self, metrics=self.metrics, callbacks=self.callbacks+callbacks)
File "C:\Program Files\ArcGIS\Pro\bin\Python\envs\arcgispro-py3\lib\site-packages\fastai\basic_train.py", line 101, in fit
loss = loss_batch(learn.model, xb, yb, learn.loss_func, learn.opt, cb_handler)
File "C:\Program Files\ArcGIS\Pro\bin\Python\envs\arcgispro-py3\lib\site-packages\fastai\basic_train.py", line 26, in loss_batch
out = model(*xb)
File "C:\Program Files\ArcGIS\Pro\bin\Python\envs\arcgispro-py3\lib\site-packages\torch\nn\modules\module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
TypeError: forward() takes 2 positional arguments but 3 were given

Failed script Train Deep Learning Model...
Failed to execute (TrainDeepLearningModel).
Failed at Tuesday, 23 May, 2023 2:17:47 PM (Elapsed Time: 4.57 seconds)

[ShivaniPathak]

Hi,

We don't use Additional Raster parameter for DeepLab model. Were you able to resolve this issue?

[TAMTzeHuey]

@ShivaniPathak Yes, I able to resolve this issue. 

[DP4KNU]

Hi @TAMTzeHuey , I currently have the same problem.

Without adding additional raster, the training progressed but when I added additional raster, the model could not train. 

Can you tell me how you solved your problem?

[ShivaniPathak]

Hi @DP4KNU, which model are you attempting to train?