在我的Kubuntu(x86)升级到14.04之后,我在nthony中没有使用python 2.7:
Python 2.7.6 (default, Mar 22 2014, 22:59:38)
[GCC 4.8.2] on linux2
Type "help", "copyright", "credits" or "license" for more information.
>>> import numpy
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/home/prylipko/.local/lib/python2.7/site-packages/numpy/__init__.py", line 137, in <module>
import add_newdocs
File "/home/prylipko/.local/lib/python2.7/site-packages/numpy/add_newdocs.py", line 9, in <module>
from numpy.lib import add_newdoc
File "/home/prylipko/.local/lib/python2.7/site-packages/numpy/lib/__init__.py", line 13, in <module>
from polynomial import *
File "/home/prylipko/.local/lib/python2.7/site-packages/numpy/lib/polynomial.py", line 17, in <module>
from numpy.linalg import eigvals, lstsq
File "/home/prylipko/.local/lib/python2.7/site-packages/numpy/linalg/__init__.py", line 48, in …我有一个非常简单的问题.我有一个为分类定义的Keras模型(TF后端).我想在训练期间将训练图像转储到我的模型中以进行调试.我正在尝试创建一个自定义回调,为此写入Tensorboard图像摘要.
但是如何在回调中获得真实的训练数据呢？
目前我正在尝试这个:
class TensorboardKeras(Callback):
def __init__(self, model, log_dir, write_graph=True):
self.model = model
self.log_dir = log_dir
self.session = K.get_session()
tf.summary.image('input_image', self.model.input)
self.merged = tf.summary.merge_all()
if write_graph:
self.writer = tf.summary.FileWriter(self.log_dir, K.get_session().graph)
else:
self.writer = tf.summary.FileWriter(self.log_dir)
def on_batch_end(self, batch, logs=None):
summary = self.session.run(self.merged, feed_dict={})
self.writer.add_summary(summary, batch)
self.writer.flush()
但我收到错误:InvalidArgumentError(请参见上面的回溯):您必须为占位符张量'input_1'提供一个值,其中dtype为float和shape [？,224,224,3]
必须有办法看看哪些模型,作为输入,对吧？
或许我应该尝试另一种方式来调试它？
我正在用单个输出单元(二进制分类)编写MLP的简单实现.我需要它用于教学目的,所以我不能使用现有的实现:(
我设法创建了一个工作虚拟模型并实现了训练功能,但MLP并没有收敛.实际上,输出单元的梯度在时期上保持很高,因此其权重接近无穷大.
我的实施:
import numpy as np
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
X = np.loadtxt('synthetic.txt')
t = X[:, 2].astype(np.int)
X = X[:, 0:2]
# Sigmoid activation function for output unit
def logistic(x):
return 1/(1 + np.exp(-x))
# derivative of the tanh activation function for hidden units
def tanh_deriv(x):
return 1 - np.tanh(x)*np.tanh(x)
input_num = 2 # number of units in the input layer
hidden_num = 2 # number of units in the hidden layer
# initialize weights …我正在研究Android设备的TensorFlow git存储库中提供的示例.它使用Java接口作为C++ API的包装器.有没有我可以直接使用C++ API初始化TensorFlow,加载模型和推理等的例子？
我试图从一个非常简单的 Caffe 模型中获取权重，并将其解释为功能齐全的 Keras 模型。
这是 Caffe 中模型的原始定义，我们称之为simple.prototxt：
input: "im_data"
input_shape {
dim: 1
dim: 3
dim: 1280
dim: 1280
}
layer {
name: "conv1"
type: "Convolution"
bottom: "im_data"
top: "conv1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 96
kernel_size: 11
pad: 5
stride: 4
}
}
layer {
name: "relu1"
type: "ReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "pool1"
type: "Pooling"
bottom: "conv1"
top: "pool1" …下面的代码：
class BoxListOpsTest(unittest.TestCase):
"""Tests for common bounding box operations."""
def test_area(self):
corners = tf.constant([[0.0, 0.0, 10.0, 20.0], [1.0, 2.0, 3.0, 4.0]])
exp_output = [200.0, 4.0]
boxes = box_list.BoxList(corners)
areas = box_list_ops.area(boxes)
with tf.Session() as sess:
areas_output = sess.run(areas)
np.testing.assert_allclose(areas_output, exp_output)
if __name__ == '__main__':
unittest.main()
被解释为具有单个测试的测试用例：
.
----------------------------------------------------------------------
Ran 1 test in 0.471s
OK
但是，切换到tf.test.TestCase：
class BoxListOpsTest(tf.test.TestCase):
"""Tests for common bounding box operations."""
def test_area(self):
corners = tf.constant([[0.0, 0.0, 10.0, 20.0], [1.0, 2.0, 3.0, 4.0]])
exp_output = [200.0, …我有一个训练有素的冻结图,我试图在ARM设备上运行.基本上,我使用的是contrib/pi_examples/label_image,但使用的是我的网络而不是Inception.我的网络受到了辍学的训练,现在让我遇到麻烦:
Invalid argument: No OpKernel was registered to support Op 'Switch' with these attrs. Registered kernels:
device='CPU'; T in [DT_FLOAT]
device='CPU'; T in [DT_INT32]
device='GPU'; T in [DT_STRING]
device='GPU'; T in [DT_BOOL]
device='GPU'; T in [DT_INT32]
device='GPU'; T in [DT_FLOAT]
[[Node: l_fc1_dropout/cond/Switch = Switch[T=DT_BOOL](is_training_pl, is_training_pl)]]
我能看到的一个解决方案是构建包含相应操作的TF静态库.另一方面,从网络中消除丢失操作以使其更简单和更快可能是更好的主意.有没有办法做到这一点？
谢谢.
tensorflow ×4
python ×3
keras ×2
android ×1
arm ×1
c++ ×1
caffe ×1
numpy ×1
perceptron ×1
python-2.7 ×1
ubuntu ×1
unit-testing ×1