from keras import layers
from keras import models
model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(150, 150, 3)))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(128, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(128, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Flatten())
model.add(layers.Dense(512, activation='relu'))
model.add(layers.Dense(1177, activation='softmax'))
from keras import optimizers
model.compile(loss='categorical_crossentropy',
optimizer=optimizers.RMSprop(lr=1e-4),
metrics=['acc'])
from keras.preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(rescale=1./255)
test_datagen = ImageDataGenerator(rescale=1./255)
train_generator = train_datagen.flow_from_directory(NEW_DATA_DIR, target_size=(150, 150), batch_size=10,class_mode='categorical')
history = model.fit_generator(
train_generator,
steps_per_epoch=100,
epochs=30)
然后我得到这个错误
WARNING:tensorflow:From /home/mimus/anaconda3/envs/tf_gpu/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py:3066: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.cast instead.
Epoch 1/30
---------------------------------------------------------------------------
UnknownError Traceback (most recent call last)
<ipython-input-7-380fa4b50355> in <module>
2 train_generator,
3 steps_per_epoch=100,
----> 4 epochs=30)
~/anaconda3/envs/tf_gpu/lib/python3.6/site-packages/keras/legacy/interfaces.py in wrapper(*args, **kwargs)
89 warnings.warn('Update your `' + object_name + '` call to the ' +
90 'Keras 2 API: ' + signature, stacklevel=2)
---> 91 return func(*args, **kwargs)
92 wrapper._original_function = func
93 return wrapper
~/anaconda3/envs/tf_gpu/lib/python3.6/site-packages/keras/engine/training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
1416 use_multiprocessing=use_multiprocessing,
1417 shuffle=shuffle,
-> 1418 initial_epoch=initial_epoch)
1419
1420 @interfaces.legacy_generator_methods_support
~/anaconda3/envs/tf_gpu/lib/python3.6/site-packages/keras/engine/training_generator.py in fit_generator(model, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
215 outs = model.train_on_batch(x, y,
216 sample_weight=sample_weight,
--> 217 class_weight=class_weight)
218
219 outs = to_list(outs)
~/anaconda3/envs/tf_gpu/lib/python3.6/site-packages/keras/engine/training.py in train_on_batch(self, x, y, sample_weight, class_weight)
1215 ins = x + y + sample_weights
1216 self._make_train_function()
-> 1217 outputs = self.train_function(ins)
1218 return unpack_singleton(outputs)
1219
~/anaconda3/envs/tf_gpu/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py in __call__(self, inputs)
2713 return self._legacy_call(inputs)
2714
-> 2715 return self._call(inputs)
2716 else:
2717 if py_any(is_tensor(x) for x in inputs):
~/anaconda3/envs/tf_gpu/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py in _call(self, inputs)
2673 fetched = self._callable_fn(*array_vals, run_metadata=self.run_metadata)
2674 else:
-> 2675 fetched = self._callable_fn(*array_vals)
2676 return fetched[:len(self.outputs)]
2677
~/anaconda3/envs/tf_gpu/lib/python3.6/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/tf_gpu/lib/python3.6/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_1/convolution}}]]
[[{{node loss/mul}}]]
我使用python 3.6，tensorflowgpu 1.13.1，kerasgpu 2.2.4，cudatoolkit 10.0.130，cudnn 7.3.1，numpy 1.16.5。我真的希望您能帮助我解决这个问题，谢谢您
编辑：
使用nvidia-smi我得到了
NVIDIA-SMI 430.26 Driver Version: 430.26 CUDA Version: 10.2 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 GeForce RTX 2060 Off | 00000000:01:00.0 On | N/A |
| 0% 52C P8 19W / 170W | 5895MiB / 5931MiB | 24% Default |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: GPU Memory |
| GPU PID Type Process name Usage |
|=============================================================================|
| 0 1305 G /usr/lib/xorg/Xorg 20MiB |
| 0 1356 G /usr/bin/gnome-shell 51MiB |
| 0 1556 G /usr/lib/xorg/Xorg 123MiB |
| 0 1703 G /usr/bin/gnome-shell 74MiB |
| 0 2816 G /usr/lib/firefox/firefox 3MiB |
| 0 10133 G /usr/lib/firefox/firefox 3MiB |
| 0 18578 C .../mimus/anaconda3/envs/tf_gpu/bin/python 5605MiB |
+-----------------------------------------------------------------------------+
答案 0 :(得分：0)
问题是我的GPU没有足够的内存来应对网络的复杂性，这可以通过尝试使用更小的模型来解决，谢谢大家