Я установил Тензор потока GPU с помощью команды conda create --name tf_gpu tensorflow-gpu. Это установило версию tenorflow 2.1.0. Вот информация о драйверах с версией cuda и cudnn: 
Когда я запускаю следующий код:
import os
import sys
import random
import numpy as np
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras.models import Model, load_model, save_model
from tensorflow.keras.layers import Input,Dropout,BatchNormalization,Activation,Add,Flatten,Dense,Reshape
from tensorflow.keras.layers import Conv2D, Conv2DTranspose, LeakyReLU
from tensorflow.keras.layers import MaxPooling2D
from tensorflow.keras.layers import concatenate
from tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint, ReduceLROnPlateau
from tensorflow.keras import backend as K
from tensorflow.keras import optimizers
from tensorflow.keras.preprocessing.image import array_to_img, img_to_array, load_img#,save_img
tr = np.load("midshot.npy")
ti = np.load("ti.npy")
def down_block(x, filters, kernel_size=(3, 3), padding="same", strides=1):
c = keras.layers.Conv2D(filters, kernel_size, padding=padding, strides=strides, activation="relu")(x)
c = keras.layers.Conv2D(filters, kernel_size, padding=padding, strides=strides, activation="relu")(c)
p = keras.layers.MaxPool2D((2, 2), (2, 2))(c)
return c, p
def up_block(x, skip, filters, kernel_size=(3, 3), padding="same", strides=1):
us = keras.layers.UpSampling2D((2, 2))(x)
concat = keras.layers.Concatenate()([us, skip])
c = keras.layers.Conv2D(filters, kernel_size, padding=padding, strides=strides, activation="relu")(concat)
c = keras.layers.Conv2D(filters, kernel_size, padding=padding, strides=strides, activation="relu")(c)
return c
def bottleneck(x, filters, kernel_size=(3, 3), padding="same", strides=1):
c = keras.layers.Conv2D(filters, kernel_size, padding=padding, strides=strides, activation="relu")(x)
c = keras.layers.Conv2D(filters, kernel_size, padding=padding, strides=strides, activation="relu")(c)
return c
def UNet():
f = [16, 32, 64, 128, 256]
inputs = keras.layers.Input((502, 200, 1))
#Matching Dimensions
m1 = keras.layers.Conv2D(1, (3, 1), padding = "same", strides = 1)(inputs)
m1 = keras.layers.MaxPool2D((2, 1), (2, 1))(m1)
m2 = keras.layers.Conv2D(1, (5, 1), padding = "same", strides = 1)(m1)
m2 = keras.layers.MaxPool2D((2, 2), (2, 2))(m2)
m3 = Conv2DTranspose(1, (2, 10), strides=(1, 1), padding="valid")(m2)
m4 = Conv2DTranspose(1, (2, 10), strides=(1, 1), padding="valid")(m3)
m5 = Conv2DTranspose(1, (2, 11), strides=(1, 1), padding="valid")(m4)
p0 = m5
c1, p1 = down_block(p0, f[0]) #128 -> 64
c2, p2 = down_block(p1, f[1]) #64 -> 32
c3, p3 = down_block(p2, f[2]) #32 -> 16
c4, p4 = down_block(p3, f[3]) #16->8
bn = bottleneck(p4, f[4])
u1 = up_block(bn, c4, f[3]) #8 -> 16
u2 = up_block(u1, c3, f[2]) #16 -> 32
u3 = up_block(u2, c2, f[1]) #32 -> 64
u4 = up_block(u3, c1, f[0]) #64 -> 128
u5 = Conv2DTranspose(8, (7, 7), strides=(2, 2), padding="valid")(u4)
u6 = Conv2DTranspose(4, (7, 7), strides=(1, 1), padding="valid")(u5)
u7 = Conv2DTranspose(2, (34, 34), strides=(1, 1), padding="valid")(u6)
outputs = keras.layers.Conv2D(1, (1, 1), padding="same", activation="relu")(u7)
model = keras.models.Model(inputs, outputs)
return model
model = UNet()
model.compile(optimizer="adam", loss="mean_squared_error", metrics=['mse'])
model.summary()
#Fitting
history = model.fit(x=tr, y=ti, batch_size=32, epochs=50, verbose=1, callbacks=None,
validation_split=0.1, validation_data=None, shuffle=True, class_weight=None,
sample_weight=None, initial_epoch=0, steps_per_epoch=None, validation_steps=None)
После запуска model.fit я получаю следующую ошибку:
Train on 4500 samples, validate on 500 samples
Epoch 1/50
32/4500 [..............................] - ETA: 2:47
---------------------------------------------------------------------------
UnknownError Traceback (most recent call last)
<ipython-input-22-607fd43b87e4> in <module>
5 history = model.fit(x=tr, y=ti, batch_size=32, epochs=50, verbose=1, callbacks=None,
6 validation_split=0.1, validation_data=None, shuffle=True, class_weight=None,
----> 7 sample_weight=None, initial_epoch=0, steps_per_epoch=None, validation_steps=None)
~/anaconda3/envs/tf_gpu/lib/python3.7/site-packages/tensorflow_core/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, validation_freq, max_queue_size, workers, use_multiprocessing, **kwargs)
817 max_queue_size=max_queue_size,
818 workers=workers,
--> 819 use_multiprocessing=use_multiprocessing)
820
821 def evaluate(self,
~/anaconda3/envs/tf_gpu/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2.py in fit(self, model, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, max_queue_size, workers, use_multiprocessing, **kwargs)
340 mode=ModeKeys.TRAIN,
341 training_context=training_context,
--> 342 total_epochs=epochs)
343 cbks.make_logs(model, epoch_logs, training_result, ModeKeys.TRAIN)
344
~/anaconda3/envs/tf_gpu/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2.py in run_one_epoch(model, iterator, execution_function, dataset_size, batch_size, strategy, steps_per_epoch, num_samples, mode, training_context, total_epochs)
126 step=step, mode=mode, size=current_batch_size) as batch_logs:
127 try:
--> 128 batch_outs = execution_function(iterator)
129 except (StopIteration, errors.OutOfRangeError):
130 # TODO(kaftan): File bug about tf function and errors.OutOfRangeError?
~/anaconda3/envs/tf_gpu/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2_utils.py in execution_function(input_fn)
96 # `numpy` translates Tensors to values in Eager mode.
97 return nest.map_structure(_non_none_constant_value,
---> 98 distributed_function(input_fn))
99
100 return execution_function
~/anaconda3/envs/tf_gpu/lib/python3.7/site-packages/tensorflow_core/python/eager/def_function.py in __call__(self, *args, **kwds)
566 xla_context.Exit()
567 else:
--> 568 result = self._call(*args, **kwds)
569
570 if tracing_count == self._get_tracing_count():
~/anaconda3/envs/tf_gpu/lib/python3.7/site-packages/tensorflow_core/python/eager/def_function.py in _call(self, *args, **kwds)
630 # Lifting succeeded, so variables are initialized and we can run the
631 # stateless function.
--> 632 return self._stateless_fn(*args, **kwds)
633 else:
634 canon_args, canon_kwds = \
~/anaconda3/envs/tf_gpu/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in __call__(self, *args, **kwargs)
2361 with self._lock:
2362 graph_function, args, kwargs = self._maybe_define_function(args, kwargs)
-> 2363 return graph_function._filtered_call(args, kwargs) # pylint: disable=protected-access
2364
2365 @property
~/anaconda3/envs/tf_gpu/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in _filtered_call(self, args, kwargs)
1609 if isinstance(t, (ops.Tensor,
1610 resource_variable_ops.BaseResourceVariable))),
-> 1611 self.captured_inputs)
1612
1613 def _call_flat(self, args, captured_inputs, cancellation_manager=None):
~/anaconda3/envs/tf_gpu/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in _call_flat(self, args, captured_inputs, cancellation_manager)
1690 # No tape is watching; skip to running the function.
1691 return self._build_call_outputs(self._inference_function.call(
-> 1692 ctx, args, cancellation_manager=cancellation_manager))
1693 forward_backward = self._select_forward_and_backward_functions(
1694 args,
~/anaconda3/envs/tf_gpu/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in call(self, ctx, args, cancellation_manager)
543 inputs=args,
544 attrs=("executor_type", executor_type, "config_proto", config),
--> 545 ctx=ctx)
546 else:
547 outputs = execute.execute_with_cancellation(
~/anaconda3/envs/tf_gpu/lib/python3.7/site-packages/tensorflow_core/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
65 else:
66 message = e.message
---> 67 six.raise_from(core._status_to_exception(e.code, message), None)
68 except TypeError as e:
69 keras_symbolic_tensors = [
~/anaconda3/envs/tf_gpu/lib/python3.7/site-packages/six.py in raise_from(value, from_value)
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 model_1/conv2d_21/Conv2D (defined at <ipython-input-22-607fd43b87e4>:7) ]] [Op:__inference_distributed_function_7357]
Function call stack:
distributed_function
Я пробовал несколько вещей, таких как понижение версии tf или версии cuda, но ничего не работает. Я не могу понять, почему это происходит. Я надеюсь, что кто-то может мне помочь.
Спасибо