I'm trying to make a convolution neural network to analyze Microsoft's cats and dogs dataset. I am using tensorflow-gpu 1.12.0, jupyter notebook, and anaconda on Windows 10. My GPU is a GTX 1080. I installed CUDA and cuDNN and I'm pretty sure I set it up correctly. I've checked the versions. Here is my code (I have it in different cells in jupyter).
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Activation, Flatten, Conv2D, MaxPooling2D
import pickle
import sys
print(sys.executable)
print(tf.__version__)
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction = 0.4)
session = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
print('GPU Settings set')
X = pickle.load(open('X.pickle','rb')) # Brings in the "pictures" of the training set
y = pickle.load(open('y.pickle','rb')) # Brings in the answers
X = X/255.0 # Normalizes the model so each number is between 0 and 1
print('Data Loaded')
model = Sequential()
model.add(Conv2D(64, (3,3), input_shape = X.shape[1:]))
model.add(Activation("relu"))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Conv2D(64, (3,3)))
model.add(Activation("relu"))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Flatten())
model.add(Dense(64))
model.add(Dense(1))
model.add(Activation('sigmoid'))
model.compile(loss="binary_crossentropy", optimizer='adam', metrics = ['accuracy'])
model.fit(X, y, batch_size=25, epochs=3, validation_split=0.1)
and I get this error:
Train on 22451 samples, validate on 2495 samples
Epoch 1/3
---------------------------------------------------------------------------
UnknownError Traceback (most recent call last)
<ipython-input-6-9cef6147c3c5> in <module>
17 model.compile(loss="binary_crossentropy", optimizer='adam', metrics = ['accuracy'])
18
---> 19 model.fit(X, y, batch_size=25, epochs=3, validation_split=0.1)
~\Anaconda3\envs\learning\lib\site-packages\tensorflow\python\keras\engine\training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, max_queue_size, workers, use_multiprocessing, **kwargs)
1637 initial_epoch=initial_epoch,
1638 steps_per_epoch=steps_per_epoch,
-> 1639 validation_steps=validation_steps)
1640
1641 def evaluate(self,
~\Anaconda3\envs\learning\lib\site-packages\tensorflow\python\keras\engine\training_arrays.py in fit_loop(model, inputs, targets, sample_weights, batch_size, epochs, verbose, callbacks, val_inputs, val_targets, val_sample_weights, shuffle, initial_epoch, steps_per_epoch, validation_steps)
213 ins_batch[i] = ins_batch[i].toarray()
214
--> 215 outs = f(ins_batch)
216 if not isinstance(outs, list):
217 outs = [outs]
~\Anaconda3\envs\learning\lib\site-packages\tensorflow\python\keras\backend.py in __call__(self, inputs)
2984
2985 fetched = self._callable_fn(*array_vals,
-> 2986 run_metadata=self.run_metadata)
2987 self._call_fetch_callbacks(fetched[-len(self._fetches):])
2988 return fetched[:len(self.outputs)]
~\Anaconda3\envs\learning\lib\site-packages\tensorflow\python\client\session.py in __call__(self, *args, **kwargs)
1437 ret = tf_session.TF_SessionRunCallable(
1438 self._session._session, self._handle, args, status,
-> 1439 run_metadata_ptr)
1440 if run_metadata:
1441 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
~\Anaconda3\envs\learning\lib\site-packages\tensorflow\python\framework\errors_impl.py in __exit__(self, type_arg, value_arg, traceback_arg)
526 None, None,
527 compat.as_text(c_api.TF_Message(self.status.status)),
--> 528 c_api.TF_GetCode(self.status.status))
529 # Delete the underlying status object from memory otherwise it stays alive
530 # as there is a reference to status from this from the traceback due to
UnknownError: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above.
[[{{node conv2d_3/Conv2D}} = Conv2D[T=DT_FLOAT, _class=["loc:@training_2/Adam/gradients/conv2d_3/Conv2D_grad/Conv2DBackpropFilter"], data_format="NCHW", dilations=[1, 1, 1, 1], padding="VALID", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:GPU:0"](training_2/Adam/gradients/conv2d_3/Conv2D_grad/Conv2DBackpropFilter-0-TransposeNHWCToNCHW-LayoutOptimizer, conv2d_3/Conv2D/ReadVariableOp)]]
[[{{node loss_2/activation_7_loss/broadcast_weights/assert_broadcastable/AssertGuard/Assert/Switch/_329}} = _Recv[client_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_321_l...ert/Switch", tensor_type=DT_BOOL, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]
