there is some error for the code #1
Description
hi is there something haven't been done?
i tried MNIST and CIFAR 10,and both of them had an error.
python mnist.py Using TensorFlow backend. I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcublas.so.8.0 locally I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcudnn.so.5 locally I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcufft.so.8.0 locally I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcuda.so.1 locally I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcurand.so.8.0 locally 5923 X (100, 28, 28, 1) 6742 X (100, 28, 28, 1) 5958 X (100, 28, 28, 1) 6131 X (100, 28, 28, 1) 5842 X (100, 28, 28, 1) 5421 X (100, 28, 28, 1) 5918 X (100, 28, 28, 1) 6265 X (100, 28, 28, 1) 5851 X (100, 28, 28, 1) 5949 X (100, 28, 28, 1) (1000, 28, 28, 1) (1000,) x_train shape: (1000, 28, 28, 1) 1000 train samples 10000 test samples (1000, 10) x_train shape: (1000, 28, 28, 1) 1000 train samples 10000 test samples mnist.py:132: UserWarning: Update yourConv2Dcall to the Keras 2 API:Conv2D(64, (5, 5), input_shape=(28, 28, 1..., padding="same", strides=(2, 2), kernel_regularizer=<keras.reg...)Convolution2D(64, 5, 5, border_mode='same',subsample=(2, 2), W_regularizer=regularizers.l2(0.01), input_shape=input_shape), mnist.py:136: UserWarning: Update yourConv2Dcall to the Keras 2 API:Conv2D(128, (5, 5), padding="same", strides=(2, 2), kernel_regularizer=<keras.reg...)Convolution2D(128, 5, 5, border_mode='same', subsample=(2,2), W_regularizer=regularizers.l2(0.01)), mnist.py:153: UserWarning: Update yourDensecall to the Keras 2 API:Dense(10, activation="softmax", kernel_regularizer=<keras.reg..., name="fc_layer2")Dense(num_classes, activation='softmax', W_regularizer=regularizers.l2(0.01), name='fc_layer2') W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE3 instructions, but these are available on your machine and could speed up CPU computations. W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations. W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations. W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations. I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:910] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero I tensorflow/core/common_runtime/gpu/gpu_device.cc:885] Found device 0 with properties: name: GeForce GTX 1070 major: 6 minor: 1 memoryClockRate (GHz) 1.835 pciBusID 0000:01:00.0 Total memory: 7.92GiB Free memory: 7.23GiB I tensorflow/core/common_runtime/gpu/gpu_device.cc:906] DMA: 0 I tensorflow/core/common_runtime/gpu/gpu_device.cc:916] 0: Y I tensorflow/core/common_runtime/gpu/gpu_device.cc:975] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 1070, pci bus id: 0000:01:00.0) Model Compilation successful /home/lunasdejavu/anaconda2/lib/python2.7/site-packages/keras/models.py:833: UserWarning: Thenb_epochargument infithas been renamedepochs. warnings.warn('The nb_epochargument infit' Traceback (most recent call last): File "mnist.py", line 195, in <module> verbose=1, validation_data=(X_test, Y_test)) File "/home/lunasdejavu/anaconda2/lib/python2.7/site-packages/keras/models.py", line 852, in fit initial_epoch=initial_epoch) File "/home/lunasdejavu/anaconda2/lib/python2.7/site-packages/keras/engine/training.py", line 1405, in fit batch_size=batch_size) File "/home/lunasdejavu/anaconda2/lib/python2.7/site-packages/keras/engine/training.py", line 1307, in _standardize_user_data _check_array_lengths(x, y, sample_weights) File "/home/lunasdejavu/anaconda2/lib/python2.7/site-packages/keras/engine/training.py", line 229, in _check_array_lengths 'and ' + str(list(set_y)[0]) + ' target samples.') ValueError: Input arrays should have the same number of samples as target arrays. Found 1000 input samples and 10000 target samples.' like thispython mnist_gan.py --mode generate --batch_size 64 --nice
Using TensorFlow backend.
I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcublas.so.8.0 locally
I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcudnn.so.5 locally
I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcufft.so.8.0 locally
I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcuda.so.1 locally
I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcurand.so.8.0 locally
mnist_gan.py:36: UserWarning: Update your Dense call to the Keras 2 API: Dense(units=1024, kernel_initializer="normal", input_dim=100)
model.add(Dense(input_dim=100, output_dim=1024, init='normal'))
mnist_gan.py:44: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(64, (5, 5), padding="same")
model.add(Convolution2D(64, 5, 5, border_mode='same'))
mnist_gan.py:48: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(1, (5, 5), padding="same")
model.add(Convolution2D(1, 5, 5, border_mode='same'))
Layer (type) Output Shape Param #
dense_1 (Dense) (None, 1024) 103424
batch_normalization_1 (Batch (None, 1024) 4096
activation_1 (Activation) (None, 1024) 0
dense_2 (Dense) (None, 6272) 6428800
batch_normalization_2 (Batch (None, 6272) 25088
activation_2 (Activation) (None, 6272) 0
reshape_1 (Reshape) (None, 7, 7, 128) 0
up_sampling2d_1 (UpSampling2 (None, 14, 14, 128) 0
conv2d_1 (Conv2D) (None, 14, 14, 64) 204864
batch_normalization_3 (Batch (None, 14, 14, 64) 256
activation_3 (Activation) (None, 14, 14, 64) 0
up_sampling2d_2 (UpSampling2 (None, 28, 28, 64) 0
conv2d_2 (Conv2D) (None, 28, 28, 1) 1601
activation_4 (Activation) (None, 28, 28, 1) 0
Total params: 6,768,129
Trainable params: 6,753,409
Non-trainable params: 14,720
None
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE3 instructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:910] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
I tensorflow/core/common_runtime/gpu/gpu_device.cc:885] Found device 0 with properties:
name: GeForce GTX 1070
major: 6 minor: 1 memoryClockRate (GHz) 1.835
pciBusID 0000:01:00.0
Total memory: 7.92GiB
Free memory: 7.25GiB
I tensorflow/core/common_runtime/gpu/gpu_device.cc:906] DMA: 0
I tensorflow/core/common_runtime/gpu/gpu_device.cc:916] 0: Y
I tensorflow/core/common_runtime/gpu/gpu_device.cc:975] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 1070, pci bus id: 0000:01:00.0)
mnist_gan.py:60: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(64, (5, 5), padding="same", strides=(2, 2), input_shape=(28, 28, 1...)
model.add(Convolution2D(64, 5, 5, border_mode='same',subsample=(2, 2), input_shape=input_shape))
mnist_gan.py:64: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(128, (5, 5), padding="same", strides=(2, 2))
model.add(Convolution2D(128, 5, 5, border_mode='same', subsample=(2,2)))
Layer (type) Output Shape Param #
conv2d_3 (Conv2D) (None, 14, 14, 64) 1664
activation_5 (Activation) (None, 14, 14, 64) 0
conv2d_4 (Conv2D) (None, 7, 7, 128) 204928
activation_6 (Activation) (None, 7, 7, 128) 0
flatten_1 (Flatten) (None, 6272) 0
dense_3 (Dense) (None, 1024) 6423552
activation_7 (Activation) (None, 1024) 0
dense_4 (Dense) (None, 1) 1025
activation_8 (Activation) (None, 1) 0
Total params: 6,631,169
Trainable params: 6,631,169
Non-trainable params: 0
None
960/1280 [=====================>........] - `
can you help me I am just a beginner:(