MOdel don´t fit in Colab

[luxevar]

HI,

I tried to work the example Multiclass Segmentation (Camvid) on Google Colab and the training fail with this Error:

`# train model
history = model.fit(
train_dataloader,
steps_per_epoch=len(train_dataloader),
epochs=EPOCHS,
callbacks=callbacks,
validation_data=valid_dataloader,
validation_steps=len(valid_dataloader),
)

Epoch 1/40

ValueError Traceback (most recent call last)
in ()
4 #steps_per_epoch=len(train_dataloader),
5 epochs=EPOCHS,
----> 6 callbacks=callbacks,
7 #validation_data=valid_dataloader,
8 #validation_steps=len(valid_dataloader),

10 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
971 except Exception as e: # pylint:disable=broad-except
972 if hasattr(e, "ag_error_metadata"):
--> 973 raise e.ag_error_metadata.to_exception(e)
974 else:
975 raise

ValueError: in user code:

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:806 train_function  *
    return step_function(self, iterator)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:796 step_function  **
    outputs = model.distribute_strategy.run(run_step, args=(data,))
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:1211 run
    return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2585 call_for_each_replica
    return self._call_for_each_replica(fn, args, kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2945 _call_for_each_replica
    return fn(*args, **kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:789 run_step  **
    outputs = model.train_step(data)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:757 train_step
    self.trainable_variables)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:2737 _minimize
    trainable_variables))
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/optimizer_v2/optimizer_v2.py:562 _aggregate_gradients
    filtered_grads_and_vars = _filter_grads(grads_and_vars)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/optimizer_v2/optimizer_v2.py:1271 _filter_grads
    ([v.name for _, v in grads_and_vars],))

ValueError: No gradients provided for any variable: ['stem_conv/kernel:0', 'stem_bn/gamma:0', 'stem_bn/beta:0', 'block1a_dwconv/depthwise_kernel:0', 'block1a_bn/gamma:0', 'block1a_bn/beta:0', 'block1a_se_reduce/kernel:0', 'block1a_se_reduce/bias:0', 'block1a_se_expand/kernel:0', 'block1a_se_expand/bias:0', 'block1a_project_conv/kernel:0', 'block1a_project_bn/gamma:0', 'block1a_project_bn/beta:0', 'block1b_dwconv/depthwise_kernel:0', 'block1b_bn/gamma:0', 'block1b_bn/beta:0', 'block1b_se_reduce/kernel:0', 'block1b_se_reduce/bias:0', 'block1b_se_expand/kernel:0', 'block1b_se_expand/bias:0', 'block1b_project_conv/kernel:0', 'block1b_project_bn/gamma:0', 'block1b_project_bn/beta:0', 'block2a_expand_conv/kernel:0', 'block2a_expand_bn/gamma:0', 'block2a_expand_bn/beta:0', 'block2a_dwconv/depthwise_kernel:0', 'block2a_bn/gamma:0', 'block2a_bn/beta:0', 'block2a_se_reduce/kernel:0', 'block2a_se_reduce/bias:0', 'block2a_se_expand/kernel:0', 'block2a_se_expand/bias:0', 'block2a_project_conv/kernel:0', 'block2a_project_bn/gamma:0', 'block2a_project_bn/beta:0', 'block2b_expand_conv/kernel:0', 'block2b_expand_bn/gamma:0', 'block2b_expand_bn/beta:0', 'block2b_dwconv/depthwise_kernel:0', 'block2b_bn/gamma:0', 'block2b_bn/beta:0', 'block2b_se_reduce/kernel:0', 'block2b_se_reduce/bias:0', 'block2b_se_expand/kernel:0', 'block2b_se_expand/bias:0', 'block2b_project_conv/kernel:0', 'block2b_project_bn/gamma:0', 'block2b_project_bn/beta:0', 'block2c_expand_conv/kernel:0', 'block2c_expand_bn/...`

Any idea for fix it?

[michael-0115]

change Dataloder's return from list to tuple will fix your problem.

[luxevar]

It's works!

[DeepaliVerma]

How to do that, its not work for me

[ilpapds]

How to do that, its not work for me
Check here
#412

def getitem(self, i):

    # collect batch data
    start = i * self.batch_size
    stop = (i + 1) * self.batch_size
    data = []
    for j in range(start, stop):
        data.append(self.dataset[j])
    
    # transpose list of lists
    batch = [np.stack(samples, axis=0) for samples in zip(*data)]
    
    # newer version of tf/keras want batch to be in tuple rather than list
    return tuple(batch)