ganguli-lab / pathint Goto Github PK

hi, I'm trying to modify dropout rate per each task recently.

For that, I should change dropout rates of the layer, and re-compile.

However, it makes error of

'You must feed a value for placeholder tensor 'dense_1_target' with dtype float and shape [?,?]'

Additionally, when I re-compile the model without any change, it also makes same error at model.fit.

Is there a way to re-compile?

I also attach the full error at the end.

Thanks

Traceback (most recent call last):
File "train_circDrop_declare.py", line 257, in
stuffs = model.fit(training_data[tidx][0], training_data[tidx][1], batch_size, epochs_per_task, callbacks=callbacks, verbose=1)
File "C:\Users\jjh\Anaconda3\lib\site-packages\keras\engine\training.py", line 1039, in fit
validation_steps=validation_steps)
File "C:\Users\jjh\Anaconda3\lib\site-packages\keras\engine\training_arrays.py", line 199, in fit_loop
outs = f(ins_batch)
File "C:\Users\jjh\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py", line 2715, in call
return self._call(inputs)
File "C:\Users\jjh\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py", line 2675, in _call
fetched = self._callable_fn(*array_vals)
File "C:\Users\jjh\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1439, in call
run_metadata_ptr)
File "C:\Users\jjh\Anaconda3\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 528, in exit
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: You must feed a value for placeholder tensor 'dense_1_target' with dtype float and shape [?,?]
[[{{node dense_1_target}} = Placeholderdtype=DT_FLOAT, shape=[?,?], _device="/job:localhost/replica:0/task:0/device:GPU:0"]]
[[{{node loss_1/mul/_417}} = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_3655_loss_1/mul", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

Hey - one quick question. I scanned the code a bit but could not find any data augmentation on cifar 10 / cifar 100. Is that correct? The results reported in the paper on the cifar 10/100 task are achieved by training on the cifar 10 / cifar 100 without data augmentation?
Many thanks!

Need to add copyright info and give credits to where we took code from Keras