DANN class giving error for multiclass classification problems

[sunilnag]

when i am executing the following code in colab following error is popping up (as given below

def my_feature_ext(input_shape=(1000,1)):
model = Sequential()
model.add(Conv1D(10, kernel_size=3,input_shape=input_shape))
model.add(Dropout(0.5))
model.add(Conv1D(10, kernel_size=3))
model.add(Dropout(0.5))
model.add(Conv1D(10, kernel_size=3))
model.add(Dropout(0.5))
model.add(Flatten())
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
return model

def my_classifier():
model = Sequential()
model.add(Dense(256, activation='relu'))
model.add(Dense(4, activation='softmax'))
return model

def my_discriminator():
model = Sequential()
model.add(Dense(512, activation='relu'))
model.add(Dense(2, activation='softmax'))
return model

model_dann = DANN(my_feature_ext(), my_classifier(), my_discriminator(), metrics=["acc"],optimizer=Adam(0.001),lambda_=0., random_state=0)
model_dann.fit(data_source, label_source, data_target, epochs=100,verbose=1);
%%%%%%%%%%%%%%%%ERROR messages%%%%%%%%%%%%%
Epoch 1/100

InvalidArgumentError Traceback (most recent call last)
in <cell line: 2>()
1 model_dann = DANN(my_feature_ext(), my_classifier(), my_discriminator(), metrics=["acc"],optimizer=Adam(0.001),lambda_=0., random_state=0)
----> 2 model_dann.fit(data_src_fft, label_src, data_tgt_fft_up, epochs=100,verbose=1);

2 frames
/usr/local/lib/python3.10/dist-packages/adapt/base.py in fit(self, X, y, Xt, yt, domains, **fit_params)
1156 self.pretrain_ = False
1157
-> 1158 hist = super().fit(dataset, validation_data=validation_data, **fit_params)
1159
1160 for k, v in hist.history.items():

/usr/local/lib/python3.10/dist-packages/keras/utils/traceback_utils.py in error_handler(*args, **kwargs)
68 # To get the full stack trace, call:
69 # tf.debugging.disable_traceback_filtering()
---> 70 raise e.with_traceback(filtered_tb) from None
71 finally:
72 del filtered_tb

/usr/local/lib/python3.10/dist-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
50 try:
51 ctx.ensure_initialized()
---> 52 tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
53 inputs, attrs, num_outputs)
54 except core._NotOkStatusException as e:

InvalidArgumentError: Graph execution error:

Detected at node 'Reshape' defined at (most recent call last):
File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/usr/lib/python3.10/runpy.py", line 86, in _run_code
exec(code, run_globals)
File "/usr/local/lib/python3.10/dist-packages/colab_kernel_launcher.py", line 37, in
ColabKernelApp.launch_instance()
File "/usr/local/lib/python3.10/dist-packages/traitlets/config/application.py", line 992, in launch_instance
app.start()
File "/usr/local/lib/python3.10/dist-packages/ipykernel/kernelapp.py", line 619, in start
self.io_loop.start()
File "/usr/local/lib/python3.10/dist-packages/tornado/platform/asyncio.py", line 195, in start
self.asyncio_loop.run_forever()
File "/usr/lib/python3.10/asyncio/base_events.py", line 603, in run_forever
self._run_once()
File "/usr/lib/python3.10/asyncio/base_events.py", line 1909, in _run_once
handle._run()
File "/usr/lib/python3.10/asyncio/events.py", line 80, in _run
self._context.run(self._callback, *self._args)
File "/usr/local/lib/python3.10/dist-packages/tornado/ioloop.py", line 685, in
lambda f: self._run_callback(functools.partial(callback, future))
File "/usr/local/lib/python3.10/dist-packages/tornado/ioloop.py", line 738, in _run_callback
ret = callback()
File "/usr/local/lib/python3.10/dist-packages/tornado/gen.py", line 825, in inner
self.ctx_run(self.run)
File "/usr/local/lib/python3.10/dist-packages/tornado/gen.py", line 786, in run
yielded = self.gen.send(value)
File "/usr/local/lib/python3.10/dist-packages/ipykernel/kernelbase.py", line 361, in process_one
yield gen.maybe_future(dispatch(*args))
File "/usr/local/lib/python3.10/dist-packages/tornado/gen.py", line 234, in wrapper
yielded = ctx_run(next, result)
File "/usr/local/lib/python3.10/dist-packages/ipykernel/kernelbase.py", line 261, in dispatch_shell
yield gen.maybe_future(handler(stream, idents, msg))
File "/usr/local/lib/python3.10/dist-packages/tornado/gen.py", line 234, in wrapper
yielded = ctx_run(next, result)
File "/usr/local/lib/python3.10/dist-packages/ipykernel/kernelbase.py", line 539, in execute_request
self.do_execute(
File "/usr/local/lib/python3.10/dist-packages/tornado/gen.py", line 234, in wrapper
yielded = ctx_run(next, result)
File "/usr/local/lib/python3.10/dist-packages/ipykernel/ipkernel.py", line 302, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File "/usr/local/lib/python3.10/dist-packages/ipykernel/zmqshell.py", line 539, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/IPython/core/interactiveshell.py", line 2975, in run_cell
result = self._run_cell(
File "/usr/local/lib/python3.10/dist-packages/IPython/core/interactiveshell.py", line 3030, in _run_cell
return runner(coro)
File "/usr/local/lib/python3.10/dist-packages/IPython/core/async_helpers.py", line 78, in pseudo_sync_runner
coro.send(None)
File "/usr/local/lib/python3.10/dist-packages/IPython/core/interactiveshell.py", line 3257, in run_cell_async
has_raised = await self.run_ast_nodes(code_ast.body, cell_name,
File "/usr/local/lib/python3.10/dist-packages/IPython/core/interactiveshell.py", line 3473, in run_ast_nodes
if (await self.run_code(code, result, async=asy)):
File "/usr/local/lib/python3.10/dist-packages/IPython/core/interactiveshell.py", line 3553, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "", line 2, in <cell line: 2>
model_dann.fit(data_src_fft, label_src, data_tgt_fft_up, epochs=100,verbose=1);
File "/usr/local/lib/python3.10/dist-packages/adapt/base.py", line 1158, in fit
hist = super().fit(dataset, validation_data=validation_data, **fit_params)
File "/usr/local/lib/python3.10/dist-packages/keras/utils/traceback_utils.py", line 65, in error_handler
return fn(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/keras/engine/training.py", line 1650, in fit
tmp_logs = self.train_function(iterator)
File "/usr/local/lib/python3.10/dist-packages/keras/engine/training.py", line 1249, in train_function
return step_function(self, iterator)
File "/usr/local/lib/python3.10/dist-packages/keras/engine/training.py", line 1233, in step_function
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/usr/local/lib/python3.10/dist-packages/keras/engine/training.py", line 1222, in run_step
outputs = model.train_step(data)
File "/usr/local/lib/python3.10/dist-packages/adapt/feature_based/_dann.py", line 140, in train_step
ys_pred = tf.reshape(ys_pred, tf.shape(ys))
Node: 'Reshape'
Input to reshape is a tensor with 128 values, but the requested shape has 32
[[{{node Reshape}}]] [Op:__inference_train_function_9015]

[antoinedemathelin]

Hi @sunilnag,
Thank you for your interest in the Adapt library!

I think your issue comes from the fact that label_source in your case is a 1D vector of shape (n,) with n the number of data. You should use tf.one_hot on it to provide a "Onehot" encoded matrix of shape (n, 4).

Moreover, I notice that you use the softmax activation for the discriminator. However, you should use the sigmoid activation with 1 neuron for the output layer (as the discriminator is always a binary classifier).

Here is an example which runs fine on colab:

!pip install adapt

from adapt.feature_based import DANN
import numpy as np
import tensorflow as tf
from tensorflow.keras import Sequential
from tensorflow.keras.layers import Conv1D, Dropout, Flatten, Dense

data_source = np.random.randn(300, 1000, 1)
data_target = np.random.randn(300, 1000, 1)
label_source = tf.one_hot(np.random.choice(4, 300), 4).numpy()

def my_feature_ext(input_shape=(1000,1)):
  model = Sequential()
  model.add(Conv1D(10, kernel_size=3,input_shape=input_shape))
  model.add(Dropout(0.5))
  model.add(Conv1D(10, kernel_size=3))
  model.add(Dropout(0.5))
  model.add(Conv1D(10, kernel_size=3))
  model.add(Dropout(0.5))
  model.add(Flatten())
  model.add(Dense(256, activation='relu'))
  model.add(Dropout(0.5))
  return model

def my_classifier():
  model = Sequential()
  model.add(Dense(256, activation='relu'))
  model.add(Dense(4, activation='softmax'))
  return model

def my_discriminator():
  model = Sequential()
  model.add(Dense(512, activation='relu'))
  model.add(Dense(1, activation='sigmoid'))
  return model

model_dann = DANN(my_feature_ext(), my_classifier(), my_discriminator(), metrics=["acc"],optimizer=tf.keras.optimizers.legacy.Adam(0.001),lambda_=0., random_state=0)
model_dann.fit(data_source, label_source, data_target, epochs=100,verbose=1);

(By the way, from my own experience, the Adam optimizer provides worse performance than SGD for DANN in general...)

I hope it helps...
Best,

[sunilnag]

thank you for the prompt reply it worked nicely