I'm building cnn model for skin disease classification using keras and tensorflow, i tried to implement a modified verision of efficientnet-b4 model that it is used in this paper A Deep Learning Based Framework for Diagnosing Multiple Skin Diseases in a Clinical Environment. from what i understand the authors add 7 auxiliary classifiers at the end of each intermediate layer then used argmax operation to find most likely classification of the input image the formula: formula
I have two questions:
First, I dont understand what how they implement argmax operation, did they used it after the training is done or they add argmax as final layer that take the sum of 7 auxiliary classifiers + final classifier?
second, here is my implementation of the model without adding argmax as final layer
classes = 7
base_model = keras.applications.EfficientNetB4(weights="imagenet",include_top=False, input_shape=(380,380,3))
avg = keras.layers.GlobalAveragePooling2D()(base_model.output)
cal_layer = keras.layers.Dense(classes, activation="softmax")(avg)
def auxilary_classifier(input, n):
x = keras.layers.AveragePooling2D(pool_size=(5,5), strides=3)(input)
x = keras.layers.Conv2D(128, kernel_size=1, padding='same', activation='relu')(x)
x = keras.layers.Flatten()(x)
x = keras.layers.BatchNormalization()(x)
x = keras.layers.Dense(1024, activation='relu')(x)
x = keras.layers.Dense(n, activation='softmax')(x)
return x
# auxiliary classifier 1
block1 = base_model.get_layer('block1b_add').output
aux_head_1 = auxilary_classifier(block1, classes)
# auxiliary classifier 2
block2 = base_model.get_layer('block2d_add').output
aux_head_2 = auxilary_classifier(block2, classes)
# auxiliary classifier 3
block3 = base_model.get_layer('block3d_add').output
aux_head_3 = auxilary_classifier(block3, classes)
# auxiliary classifier 4
block4 = base_model.get_layer('block4f_add').output
aux_head_4 = auxilary_classifier(block4, classes)
# auxiliary classifier 5
block5 = base_model.get_layer('block5f_add').output
aux_head_5 = auxilary_classifier(block5, classes)
# auxiliary classifier 6
block6 = base_model.get_layer('block6h_add').output
aux_head_6 = auxilary_classifier(block6, classes)
# auxiliary classifier 7
block7 = base_model.get_layer('block7b_add').output
aux_head_7 = auxilary_classifier(block7, classes)
sum_final = keras.layers.Add()([cal_layer,aux_head_1,aux_head_2,aux_head_3,aux_head_4,aux_head_5,aux_head_6,aux_head_7])
model = keras.Model(base_model.input, sum_final)
optimizer = keras.optimizers.Nadam(learning_rate=0.01)
model.compile(loss="sparse_categorical_crossentropy",optimizer=optimizer,metrics=["accuracy"])
history = model.fit(train, validation_data=valid, epochs=30, verbose=2, batch_size=30)
after i run it i recieve this error which i dont understand
Epoch 1/30
---------------------------------------------------------------------------
ResourceExhaustedError Traceback (most recent call last)
<ipython-input-9-91732b783ef6> in <cell line: 6>()
4 optimizer = keras.optimizers.Nadam(learning_rate=0.01)
5 model.compile(loss="sparse_categorical_crossentropy",optimizer=optimizer,metrics=["accuracy"])
----> 6 history = model.fit(train, validation_data=valid, epochs=30, verbose=2, batch_size=30, callbacks=[reduce_lr])
1 frames
/usr/local/lib/python3.9/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/python3.9/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:
ResourceExhaustedError: Graph execution error:
Detected at node 'model_1/block2a_expand_conv/Conv2D' defined at (most recent call last):
File "/usr/lib/python3.9/runpy.py", line 197, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/usr/lib/python3.9/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/usr/local/lib/python3.9/dist-packages/ipykernel_launcher.py", line 16, in <module>
app.launch_new_instance()
File "/usr/local/lib/python3.9/dist-packages/traitlets/config/application.py", line 992, in launch_instance
app.start()
File "/usr/local/lib/python3.9/dist-packages/ipykernel/kernelapp.py", line 619, in start
self.io_loop.start()
File "/usr/local/lib/python3.9/dist-packages/tornado/platform/asyncio.py", line 215, in start
self.asyncio_loop.run_forever()
File "/usr/lib/python3.9/asyncio/base_events.py", line 601, in run_forever
self._run_once()
File "/usr/lib/python3.9/asyncio/base_events.py", line 1905, in _run_once
handle._run()
File "/usr/lib/python3.9/asyncio/events.py", line 80, in _run
self._context.run(self._callback, *self._args)
File "/usr/local/lib/python3.9/dist-packages/tornado/ioloop.py", line 687, in <lambda>
lambda f: self._run_callback(functools.partial(callback, future))
File "/usr/local/lib/python3.9/dist-packages/tornado/ioloop.py", line 740, in _run_callback
ret = callback()
File "/usr/local/lib/python3.9/dist-packages/tornado/gen.py", line 821, in inner
self.ctx_run(self.run)
File "/usr/local/lib/python3.9/dist-packages/tornado/gen.py", line 782, in run
yielded = self.gen.send(value)
File "/usr/local/lib/python3.9/dist-packages/ipykernel/kernelbase.py", line 361, in process_one
yield gen.maybe_future(dispatch(*args))
File "/usr/local/lib/python3.9/dist-packages/tornado/gen.py", line 234, in wrapper
yielded = ctx_run(next, result)
File "/usr/local/lib/python3.9/dist-packages/ipykernel/kernelbase.py", line 261, in dispatch_shell
yield gen.maybe_future(handler(stream, idents, msg))
File "/usr/local/lib/python3.9/dist-packages/tornado/gen.py", line 234, in wrapper
yielded = ctx_run(next, result)
File "/usr/local/lib/python3.9/dist-packages/ipykernel/kernelbase.py", line 539, in execute_request
self.do_execute(
File "/usr/local/lib/python3.9/dist-packages/tornado/gen.py", line 234, in wrapper
yielded = ctx_run(next, result)
File "/usr/local/lib/python3.9/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/python3.9/dist-packages/ipykernel/zmqshell.py", line 539, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "/usr/local/lib/python3.9/dist-packages/IPython/core/interactiveshell.py", line 2975, in run_cell
result = self._run_cell(
File "/usr/local/lib/python3.9/dist-packages/IPython/core/interactiveshell.py", line 3030, in _run_cell
return runner(coro)
File "/usr/local/lib/python3.9/dist-packages/IPython/core/async_helpers.py", line 78, in _pseudo_sync_runner
coro.send(None)
File "/usr/local/lib/python3.9/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/python3.9/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/python3.9/dist-packages/IPython/core/interactiveshell.py", line 3553, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-9-91732b783ef6>", line 6, in <cell line: 6>
history = model.fit(train, validation_data=valid, epochs=30, verbose=2, batch_size=30, callbacks=[reduce_lr])
File "/usr/local/lib/python3.9/dist-packages/keras/utils/traceback_utils.py", line 65, in error_handler
return fn(*args, **kwargs)
File "/usr/local/lib/python3.9/dist-packages/keras/engine/training.py", line 1685, in fit
tmp_logs = self.train_function(iterator)
File "/usr/local/lib/python3.9/dist-packages/keras/engine/training.py", line 1284, in train_function
return step_function(self, iterator)
File "/usr/local/lib/python3.9/dist-packages/keras/engine/training.py", line 1268, in step_function
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/usr/local/lib/python3.9/dist-packages/keras/engine/training.py", line 1249, in run_step
outputs = model.train_step(data)
File "/usr/local/lib/python3.9/dist-packages/keras/engine/training.py", line 1050, in train_step
y_pred = self(x, training=True)
File "/usr/local/lib/python3.9/dist-packages/keras/utils/traceback_utils.py", line 65, in error_handler
return fn(*args, **kwargs)
File "/usr/local/lib/python3.9/dist-packages/keras/engine/training.py", line 558, in __call__
return super().__call__(*args, **kwargs)
File "/usr/local/lib/python3.9/dist-packages/keras/utils/traceback_utils.py", line 65, in error_handler
return fn(*args, **kwargs)
File "/usr/local/lib/python3.9/dist-packages/keras/engine/base_layer.py", line 1145, in __call__
outputs = call_fn(inputs, *args, **kwargs)
File "/usr/local/lib/python3.9/dist-packages/keras/utils/traceback_utils.py", line 96, in error_handler
return fn(*args, **kwargs)
File "/usr/local/lib/python3.9/dist-packages/keras/engine/functional.py", line 512, in call
return self._run_internal_graph(inputs, training=training, mask=mask)
File "/usr/local/lib/python3.9/dist-packages/keras/engine/functional.py", line 669, in _run_internal_graph
outputs = node.layer(*args, **kwargs)
File "/usr/local/lib/python3.9/dist-packages/keras/utils/traceback_utils.py", line 65, in error_handler
return fn(*args, **kwargs)
File "/usr/local/lib/python3.9/dist-packages/keras/engine/base_layer.py", line 1145, in __call__
outputs = call_fn(inputs, *args, **kwargs)
File "/usr/local/lib/python3.9/dist-packages/keras/utils/traceback_utils.py", line 96, in error_handler
return fn(*args, **kwargs)
File "/usr/local/lib/python3.9/dist-packages/keras/layers/convolutional/base_conv.py", line 290, in call
outputs = self.convolution_op(inputs, self.kernel)
File "/usr/local/lib/python3.9/dist-packages/keras/layers/convolutional/base_conv.py", line 262, in convolution_op
return tf.nn.convolution(
Node: 'model_1/block2a_expand_conv/Conv2D'
OOM when allocating tensor with shape[32,190,190,144] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[{{node model_1/block2a_expand_conv/Conv2D}}]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.
[Op:__inference_train_function_115485]