原因是你路径不对
import os
def cc(f):
print(f)
os.chdir("D:\\Chinaunicom\\learning\\python\\test")#你那个文件夹所在路径
os.remove(f)
if os.path.exists('test'):
aa = os.listdir('test')
[cc(f) for f in aa]
或者你更需要这个代码
import os
if os.path.exists('test'):
aa = os.listdir('test')
[os.remove(os.path.join(os.getcwd(), 'test',f)) for f in aa]
运行tensorflow时出现tensorflow.python.framework.errors_impl.InternalError: Blas GEMM launch failed这个错误_course
2019-10-17运行tensorflow时出现tensorflow.python.framework.errors_impl.InternalError: Blas GEMM launch failed这个错误，查了一下说是gpu被占用了，从下面这里开始出问题的： ``` 2019-10-17 09:28:49.495166: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 6382 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1070, pci bus id: 0000:01:00.0, compute capability: 6.1) (60000, 28, 28) (60000, 10) 2019-10-17 09:28:51.275415: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'cublas64_100.dll'; dlerror: cublas64_100.dll not found ```  最后显示的问题：  试了一下网上的方法，比如加代码： ``` gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.333) sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options)) ``` 但最后提示：  现在不知道要怎么解决了。新手想试下简单的数字识别，步骤也是按教程一步步来的，可能用的版本和教程不一样，我用的是刚下的：2.0tensorflow和以下：  不知道会不会有版本问题，现在紧急求助各位大佬，还有没有其它可以尝试的方法。测试程序加法运算可以执行，数字识别图片运行的时候我看了下，GPU最大占有率才0.2%，下面是完整数字图片识别代码： ``` import os import tensorflow as tf from tensorflow import keras from tensorflow.keras import layers, optimizers, datasets os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' #gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.2) #sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options)) gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.333) sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options)) (x, y), (x_val, y_val) = datasets.mnist.load_data() x = tf.convert_to_tensor(x, dtype=tf.float32) / 255. y = tf.convert_to_tensor(y, dtype=tf.int32) y = tf.one_hot(y, depth=10) print(x.shape, y.shape) train_dataset = tf.data.Dataset.from_tensor_slices((x, y)) train_dataset = train_dataset.batch(200) model = keras.Sequential([ layers.Dense(512, activation='relu'), layers.Dense(256, activation='relu'), layers.Dense(10)]) optimizer = optimizers.SGD(learning_rate=0.001) def train_epoch(epoch): # Step4.loop for step, (x, y) in enumerate(train_dataset): with tf.GradientTape() as tape: # [b, 28, 28] => [b, 784] x = tf.reshape(x, (-1, 28 * 28)) # Step1. compute output # [b, 784] => [b, 10] out = model(x) # Step2. compute loss loss = tf.reduce_sum(tf.square(out - y)) / x.shape[0] # Step3. optimize and update w1, w2, w3, b1, b2, b3 grads = tape.gradient(loss, model.trainable_variables) # w' = w - lr * grad optimizer.apply_gradients(zip(grads, model.trainable_variables)) if step % 100 == 0: print(epoch, step, 'loss:', loss.numpy()) def train(): for epoch in range(30): train_epoch(epoch) if __name__ == '__main__': train() ``` 希望能有人给下建议或解决方法，拜谢！
我没有用anaconda，下载了所有的python机器学习库。但是在下载tensorflow的时候只能安装2.2.0版本是什么情况？2.2.0版本非常奇怪_course
2020-06-12我没有用anaconda，下载了所有的python机器学习库。但是在下载tensorflow的时候只能安装2.2.0版本是什么情况？2.2.0版本非常奇怪
tensorboard报错：'tensorflow.python.estimator.api.estimator' has no attribute 'SessionRunHook'_course
2019-08-02小白刚接触tensorflow，想用tensorboard将网络可视化，但在cmd输入tensorboard时报错：'tensorflow.python.estimator.api.estimator' has no attribute 'SessionRunHook' 装有： tensorflow1.14.0 tensorboard1.14.0 tensorflow-estimator1.14.0    
tensorflow.python.framework.errors_impl.InternalError: Blas GEMM launch failed ，程序中出现anaconda错误？_course
2019-10-22在pycharm中运行python程序时，出现anaconda中的错误，如下图：  这是版本不匹配，还是程序里有调用，或者其它什么问题？有人可以帮忙看一下吗？这是教程视频里的程序，视频里可以运行出来，我的tensorflow、CUDA、cudnn是官网下的，可能比他的新一些，10.1和10.0版本，或者测试版和正式版这种差别。下面是运行的前向传播的代码： ``` import tensorflow as tf from tensorflow import keras from tensorflow.keras import datasets import os os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' # x: [60k, 28, 28], # y: [60k] (x, y), _ = datasets.mnist.load_data() # x: [0~255] => [0~1.] x = tf.convert_to_tensor(x, dtype=tf.float32) / 255. y = tf.convert_to_tensor(y, dtype=tf.int32) print(x.shape, y.shape, x.dtype, y.dtype) print(tf.reduce_min(x), tf.reduce_max(x)) print(tf.reduce_min(y), tf.reduce_max(y)) train_db = tf.data.Dataset.from_tensor_slices((x,y)).batch(128) train_iter = iter(train_db) sample = next(train_iter) print('batch:', sample[0].shape, sample[1].shape) # [b, 784] => [b, 256] => [b, 128] => [b, 10] # [dim_in, dim_out], [dim_out] w1 = tf.Variable(tf.random.truncated_normal([784, 256], stddev=0.1)) b1 = tf.Variable(tf.zeros([256])) w2 = tf.Variable(tf.random.truncated_normal([256, 128], stddev=0.1)) b2 = tf.Variable(tf.zeros([128])) w3 = tf.Variable(tf.random.truncated_normal([128, 10], stddev=0.1)) b3 = tf.Variable(tf.zeros([10])) lr = 1e-3 for epoch in range(10): # iterate db for 10 for step, (x, y) in enumerate(train_db): # for every batch # x:[128, 28, 28] # y: [128] # [b, 28, 28] => [b, 28*28] x = tf.reshape(x, [-1, 28*28]) with tf.GradientTape() as tape: # tf.Variable # x: [b, 28*28] # h1 = x@w1 + b1 # [b, 784]@[784, 256] + [256] => [b, 256] + [256] => [b, 256] + [b, 256] h1 = x@w1 + tf.broadcast_to(b1, [x.shape[0], 256]) h1 = tf.nn.relu(h1) # [b, 256] => [b, 128] h2 = h1@w2 + b2 h2 = tf.nn.relu(h2) # [b, 128] => [b, 10] out = h2@w3 + b3 # compute loss # out: [b, 10] # y: [b] => [b, 10] y_onehot = tf.one_hot(y, depth=10) # mse = mean(sum(y-out)^2) # [b, 10] loss = tf.square(y_onehot - out) # mean: scalar loss = tf.reduce_mean(loss) # compute gradients grads = tape.gradient(loss, [w1, b1, w2, b2, w3, b3]) # print(grads) # w1 = w1 - lr * w1_grad w1.assign_sub(lr * grads[0]) b1.assign_sub(lr * grads[1]) w2.assign_sub(lr * grads[2]) b2.assign_sub(lr * grads[3]) w3.assign_sub(lr * grads[4]) b3.assign_sub(lr * grads[5]) if step % 100 == 0: print(epoch, step, 'loss:', float(loss)) ```
python3.7中的tensorflow2.0模块没有的问题。_course
2019-11-17小白刚做手写字识别，遇到tensorflow导入模块的一些问题，模块ModuleNotFoundError: No module named 'tensorflow.examples.tutorials'不会解决。 import keras # 导入Keras import numpy as np from keras.datasets import mnist # 从keras中导入mnist数据集 from keras.models import Sequential # 导入序贯模型 from keras.layers import Dense # 导入全连接层 from keras.optimizers import SGD # 导入优化函数 from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets("MNIST_data", one_hot = True)  在网上找了好久，也不怎么懂，能告诉我详实点的解决办法。
请教各位大神，出现了FileNotFoundException,系统找不到指定的文件的错误_course
2014-09-04import java.io.*; public class Test15_demo { public static void main(String args) { BufferedReader b
请问tensorflow如何查看一个神经网络运行时所占用的内存大小？_course
2019-05-06tensorflow有没有专门的函数可以查看神经网络运行时所占用的内存，如果没有的话有什么方法可以查看呢？ 跪求大佬们的指导
Python Tensorflow中dense问题_course
2019-04-12tf.layers.dense中units的参数设定依据什么规则？是维数越大越精确吗？刚刚开始学，希望能细讲下谢谢
在测试模型时，仅仅添加了这一句就显示：tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [184,7,7,256] vs. [9,7,7,256] [[{{node roi_align_classifier/Add_1}}]]_course
2020-02-17在测试模型时，仅仅添加了这一句就显示：tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [184,7,7,256] vs. [9,7,7,256] [[{{node roi_align_classifier/Add_1}}]] 添加的内容： for i in range(4): if i != 0: feature_maps[i] = tf.add(feature_maps[i], feature_maps[i-1]) feature_maps是个list，有4个feature_map。feature_map格式如下: [batch, height, width, channels]。急需大神帮忙解决
python有没有那个版本可以同时使用karas、tensorflow、sklearn?_course
2019-12-23最近在使用python研究LSTM，结果出现了各种库的问题，使用pycharm的时候，明明已经装上了sklearn，但就是出现找不到库文件的提示，再在anaconda配置好了环境，也同时安装了sklearn库，同时也可以在IDLE使用import sklearn语句，结果放到pycharm中还是不能使用，感觉python搞这么多版本真的仍让人头疼，一个环境配置都把人搞头大了
用tensorflow做机器翻译时训练代码有问题_course
2019-05-27``` # -*- coding:UTF-8 -*- import tensorflow as tf src_path = 'D:/Python37/untitled1/train.tags.en-zh.en.deletehtml' trg_path = 'D:/Python37/untitled1/train.tags.en-zh.zh.deletehtml' SRC_TRAIN_DATA = 'D:/Python37/untitled1/train.tags.en-zh.en.deletehtml.segment' # 源语言输入文件 TRG_TRAIN_DATA = 'D:/Python37/untitled1/train.tags.en-zh.zh.deletehtml.segment' # 目标语言输入文件 CHECKPOINT_PATH = './model/seq2seq_ckpt' # checkpoint保存路径 HIDDEN_SIZE = 1024 # LSTM的隐藏层规模 NUM_LAYERS = 2 # 深层循环神经网络中LSTM结构的层数 SRC_VOCAB_SIZE = 10000 # 源语言词汇表大小 TRG_VOCAB_SIZE = 4000 # 目标语言词汇表大小 BATCH_SIZE = 100 # 训练数据batch的大小 NUM_EPOCH = 5 # 使用训练数据的轮数 KEEP_PROB = 0.8 # 节点不被dropout的概率 MAX_GRAD_NORM = 5 # 用于控制梯度膨胀的梯度大小上限 SHARE_EMB_AND_SOFTMAX = True # 在softmax层和词向量层之间共享参数 MAX_LEN = 50 # 限定句子的最大单词数量 SOS_ID = 1 # 目标语言词汇表中<sos>的ID """ function: 数据batching,产生最后输入数据格式 Parameters: file_path-数据路径 Returns: dataset- 每个句子－对应的长度组成的TextLineDataset类的数据集对应的张量 """ def MakeDataset(file_path): dataset = tf.data.TextLineDataset(file_path) # map(function, sequence[, sequence, ...]) -> list # 通过定义可以看到，这个函数的第一个参数是一个函数，剩下的参数是一个或多个序列，返回值是一个集合。 # function可以理解为是一个一对一或多对一函数，map的作用是以参数序列中的每一个元素调用function函数，返回包含每次function函数返回值的list。 # lambda argument_list: expression # 其中lambda是Python预留的关键字,argument_list和expression由用户自定义 # argument_list参数列表, expression 为函数表达式 # 根据空格将单词编号切分开并放入一个一维向量 dataset = dataset.map(lambda string: tf.string_split([string]).values) # 将字符串形式的单词编号转化为整数 dataset = dataset.map(lambda string: tf.string_to_number(string, tf.int32)) # 统计每个句子的单词数量，并与句子内容一起放入Dataset dataset = dataset.map(lambda x: (x, tf.size(x))) return dataset """ function: 从源语言文件src_path和目标语言文件trg_path中分别读取数据，并进行填充和batching操作 Parameters: src_path-源语言，即被翻译的语言,英语. trg_path-目标语言，翻译之后的语言,汉语. batch_size-batch的大小 Returns: dataset- 每个句子－对应的长度 组成的TextLineDataset类的数据集 """ def MakeSrcTrgDataset(src_path, trg_path, batch_size): # 首先分别读取源语言数据和目标语言数据 src_data = MakeDataset(src_path) trg_data = MakeDataset(trg_path) # 通过zip操作将两个Dataset合并为一个Dataset，现在每个Dataset中每一项数据ds由4个张量组成 # ds[0][0]是源句子 # ds[0][1]是源句子长度 # ds[1][0]是目标句子 # ds[1][1]是目标句子长度 #https://blog.csdn.net/qq_32458499/article/details/78856530这篇博客看一下可以细致了解一下Dataset这个库，以及.map和.zip的用法 dataset = tf.data.Dataset.zip((src_data, trg_data)) # 删除内容为空(只包含<eos>)的句子和长度过长的句子 def FilterLength(src_tuple, trg_tuple): ((src_input, src_len), (trg_label, trg_len)) = (src_tuple, trg_tuple) # tf.logical_and 相当于集合中的and做法，后面两个都为true最终结果才会为true，否则为false # tf.greater Returns the truth value of (x > y),所以以下所说的是句子长度必须得大于一也就是不能为空的句子 # tf.less_equal Returns the truth value of (x <= y),所以所说的是长度要小于最长长度 src_len_ok = tf.logical_and(tf.greater(src_len, 1), tf.less_equal(src_len, MAX_LEN)) trg_len_ok = tf.logical_and(tf.greater(trg_len, 1), tf.less_equal(trg_len, MAX_LEN)) return tf.logical_and(src_len_ok, trg_len_ok) #两个都满足才返回true # filter接收一个函数Func并将该函数作用于dataset的每个元素，根据返回值True或False保留或丢弃该元素，True保留该元素，False丢弃该元素 # 最后得到的就是去掉空句子和过长的句子的数据集 dataset = dataset.filter(FilterLength) # 解码器需要两种格式的目标句子： # 1.解码器的输入(trg_input), 形式如同'<sos> X Y Z' # 2.解码器的目标输出(trg_label), 形式如同'X Y Z <eos>' # 上面从文件中读到的目标句子是'X Y Z <eos>'的形式，我们需要从中生成'<sos> X Y Z'形式并加入到Dataset # 编码器只有输入,没有输出,而解码器有输入也有输出，输入为<sos>＋(除去最后一位eos的label列表) # 例如train.en最后都为2,ｉｄ为２就是eos def MakeTrgInput(src_tuple, trg_tuple): ((src_input, src_len), (trg_label, trg_len)) = (src_tuple, trg_tuple) # tf.concat用法 https://blog.csdn.net/qq_33431368/article/details/79429295 trg_input = tf.concat([[SOS_ID], trg_label[:-1]], axis=0) return ((src_input, src_len), (trg_input, trg_label, trg_len)) dataset = dataset.map(MakeTrgInput) # 随机打乱训练数据 dataset = dataset.shuffle(10000) # 规定填充后的输出的数据维度 padded_shapes = ( (tf.TensorShape([None]), # 源句子是长度未知的向量 tf.TensorShape([])), # 源句子长度是单个数字 (tf.TensorShape([None]), # 目标句子(解码器输入)是长度未知的向量 tf.TensorShape([None]), # 目标句子(解码器目标输出)是长度未知的向量 tf.TensorShape([])) # 目标句子长度(输出)是单个数字 ) # 调用padded_batch方法进行padding 和 batching操作 batched_dataset = dataset.padded_batch(batch_size, padded_shapes) return batched_dataset """ function: seq2seq模型 Parameters: Returns: """ class NMTModel(object): """ function: 模型初始化 Parameters: Returns: """ def __init__(self): # 定义编码器和解码器所使用的LSTM结构 self.enc_cell = tf.nn.rnn_cell.MultiRNNCell( [tf.nn.rnn_cell.LSTMCell(HIDDEN_SIZE) for _ in range(NUM_LAYERS)]) self.dec_cell = tf.nn.rnn_cell.MultiRNNCell( [tf.nn.rnn_cell.LSTMCell(HIDDEN_SIZE) for _ in range(NUM_LAYERS)]) # 为源语言和目标语言分别定义词向量 self.src_embedding = tf.get_variable('src_emb', [SRC_VOCAB_SIZE, HIDDEN_SIZE]) self.trg_embedding = tf.get_variable('trg_emb', [TRG_VOCAB_SIZE, HIDDEN_SIZE]) # 定义softmax层的变量 if SHARE_EMB_AND_SOFTMAX: self.softmax_weight = tf.transpose(self.trg_embedding) else: self.softmax_weight = tf.get_variable('weight', [HIDDEN_SIZE, TRG_VOCAB_SIZE]) self.softmax_bias = tf.get_variable('softmax_loss', [TRG_VOCAB_SIZE]) """ function: 在forward函数中定义模型的前向计算图 Parameters: MakeSrcTrgDataset函数产生的五种张量如下（全部为张量） src_input: 编码器输入（源数据） src_size : 输入大小 trg_input：解码器输入（目标数据） trg_label：解码器输出（目标数据） trg_size： 输出大小 Returns: """ def forward(self, src_input, src_size, trg_input, trg_label, trg_size): batch_size = tf.shape(src_input)[0] # 将输入和输出单词转为词向量（rnn中输入数据都要转换成词向量） # 相当于input中的每个id对应的embedding中的向量转换 src_emb = tf.nn.embedding_lookup(self.src_embedding, src_input) trg_emb = tf.nn.embedding_lookup(self.trg_embedding, trg_input) # 在词向量上进行dropout src_emb = tf.nn.dropout(src_emb, KEEP_PROB) trg_emb = tf.nn.dropout(trg_emb, KEEP_PROB) # 使用dynamic_rnn构造编码器 # 编码器读取源句子每个位置的词向量，输出最后一步的隐藏状态enc_state # 因为编码器是一个双层LSTM，因此enc_state是一个包含两个LSTMStateTuple类的tuple， # 每个LSTMStateTuple对应编码器中一层的状态 # enc_outputs是顶层LSTM在每一步的输出，它的维度是[batch_size, max_time, HIDDEN_SIZE] # seq2seq模型中不需要用到enc_outputs,而attention模型会用到它 with tf.variable_scope('encoder'): enc_outputs, enc_state = tf.nn.dynamic_rnn(self.enc_cell, src_emb, src_size, dtype=tf.float32) # 使用dynamic_rnn构造解码器 # 解码器读取目标句子每个位置的词向量，输出的dec_outputs为每一步顶层LSTM的输出 # dec_outputs的维度是[batch_size, max_time, HIDDEN_SIZE] # initial_state=enc_state表示用编码器的输出来初始化第一步的隐藏状态 # 编码器最后编码结束最后的状态为解码器初始化的状态 with tf.variable_scope('decoder'): dec_outputs, _ = tf.nn.dynamic_rnn(self.dec_cell, trg_emb, trg_size, initial_state=enc_state) # 计算解码器每一步的log perplexity # 输出重新转换成shape为[,HIDDEN_SIZE] output = tf.reshape(dec_outputs, [-1, HIDDEN_SIZE]) # 计算解码器每一步的softmax概率值 logits = tf.matmul(output, self.softmax_weight) + self.softmax_bias # 交叉熵损失函数，算loss loss = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=tf.reshape(trg_label, [-1]), logits=logits) # 在计算平均损失时，需要将填充位置的权重设置为0，以避免无效位置的预测干扰模型的训练 label_weights = tf.sequence_mask(trg_size, maxlen=tf.shape(trg_label)[1], dtype=tf.float32) label_weights = tf.reshape(label_weights, [-1]) cost = tf.reduce_sum(loss * label_weights) cost_per_token = cost / tf.reduce_sum(label_weights) # 定义反向传播操作 trainable_variables = tf.trainable_variables() # 控制梯度大小，定义优化方法和训练步骤 # 算出每个需要更新的值的梯度，并对其进行控制 grads = tf.gradients(cost / tf.to_float(batch_size), trainable_variables) grads, _ = tf.clip_by_global_norm(grads, MAX_GRAD_NORM) # 利用梯度下降优化算法进行优化.学习率为1.0 optimizer = tf.train.GradientDescentOptimizer(learning_rate=1.0) # 相当于minimize的第二步，正常来讲所得到的list[grads,vars]由compute_gradients得到，返回的是执行对应变量的更新梯度操作的op train_op = optimizer.apply_gradients(zip(grads, trainable_variables)) return cost_per_token, train_op """ function: 使用给定的模型model上训练一个epoch，并返回全局步数，每训练200步便保存一个checkpoint Parameters: session : 会议 cost_op : 计算loss的操作op train_op： 训练的操作op saver： 保存model的类 step： 训练步数 Returns: """ def run_epoch(session, cost_op, train_op, saver, step): # 训练一个epoch # 重复训练步骤直至遍历完Dataset中所有数据 while True: try: # 运行train_op并计算cost_op的结果也就是损失值，训练数据在main()函数中以Dataset方式提供 cost, _ = session.run([cost_op, train_op]) # 步数为１０的倍数进行打印 if step % 10 == 0: print('After %d steps, per token cost is %.3f' % (step, cost)) # 每200步保存一个checkpoint if step % 200 == 0: saver.save(session, CHECKPOINT_PATH, global_step=step) step += 1 except tf.errors.OutOfRangeError: break return step """ function: 主函数 Parameters: Returns: """ def main(): # 定义初始化函数 initializer = tf.random_uniform_initializer(-0.05, 0.05) # 定义训练用的循环神经网络模型 with tf.variable_scope('nmt_model', reuse=None, initializer=initializer): train_model = NMTModel() # 定义输入数据 data = MakeSrcTrgDataset(SRC_TRAIN_DATA, TRG_TRAIN_DATA, BATCH_SIZE) iterator = data.make_initializable_iterator() (src, src_size), (trg_input, trg_label, trg_size) = iterator.get_next() # 定义前向计算图，输入数据以张量形式提供给forward函数 cost_op, train_op = train_model.forward(src, src_size, trg_input, trg_label, trg_size) # 训练模型 # 保存模型 saver = tf.train.Saver() step = 0 with tf.Session() as sess: # 初始化全部变量 tf.global_variables_initializer().run() # 进行NUM_EPOCH轮数 for i in range(NUM_EPOCH): print('In iteration: %d' % (i + 1)) sess.run(iterator.initializer) step = run_epoch(sess, cost_op, train_op, saver, step) if __name__ == '__main__': main() ``` 问题如下，不知道怎么解决，谢谢！ Traceback (most recent call last): File "D:\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\client\session.py", line 1334, in _do_call return fn(*args) File "D:\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\client\session.py", line 1319, in _run_fn options, feed_dict, fetch_list, target_list, run_metadata) File "D:\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\client\session.py", line 1407, in _call_tf_sessionrun run_metadata) tensorflow.python.framework.errors_impl.InvalidArgumentError: StringToNumberOp could not correctly convert string: This [[{{node StringToNumber}}]] [[{{node IteratorGetNext}}]] During handling of the above exception, another exception occurred: Traceback (most recent call last): File "D:/Python37/untitled1/train_model.py", line 277, in <module> main() File "D:/Python37/untitled1/train_model.py", line 273, in main step = run_epoch(sess, cost_op, train_op, saver, step) File "D:/Python37/untitled1/train_model.py", line 231, in run_epoch cost, _ = session.run([cost_op, train_op]) File "D:\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\client\session.py", line 929, in run run_metadata_ptr) File "D:\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\client\session.py", line 1152, in _run feed_dict_tensor, options, run_metadata) File "D:\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\client\session.py", line 1328, in _do_run run_metadata) File "D:\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\client\session.py", line 1348, in _do_call raise type(e)(node_def, op, message) tensorflow.python.framework.errors_impl.InvalidArgumentError: StringToNumberOp could not correctly convert string: This [[{{node StringToNumber}}]] [[node IteratorGetNext (defined at D:/Python37/untitled1/train_model.py:259) ]]
在训练Tensorflow模型(object_detection)时，训练在第一次评估后退出，怎么使训练继续下去？_course
2019-08-15当我进行ssd模型训练时，训练进行了10分钟，然后进入评估阶段，评估之后程序就自动退出了，没有看到误和警告，这是为什么，怎么让程序一直训练下去？ 训练命令： ``` python object_detection/model_main.py --pipeline_config_path=D:/gitcode/models/research/object_detection/ssd_mobilenet_v1_coco_2018_01_28/pipeline.config --model_dir=D:/gitcode/models/research/object_detection/ssd_mobilenet_v1_coco_2018_01_28/saved_model --num_train_steps=50000 --alsologtostderr ``` 配置文件： ``` training exit after the first evaluation(only one evaluation) in Tensorflow model(object_detection) without error and waring System information What is the top-level directory of the model you are using:models/research/object_detection/ Have I written custom code (as opposed to using a stock example script provided in TensorFlow):NO OS Platform and Distribution (e.g., Linux Ubuntu 16.04):Windows-10(64bit) TensorFlow installed from (source or binary):conda install tensorflow-gpu TensorFlow version (use command below):1.13.1 Bazel version (if compiling from source):N/A CUDA/cuDNN version:cudnn-7.6.0 GPU model and memory:GeForce GTX 1060 6GB Exact command to reproduce:See below my command for training : python object_detection/model_main.py --pipeline_config_path=D:/gitcode/models/research/object_detection/ssd_mobilenet_v1_coco_2018_01_28/pipeline.config --model_dir=D:/gitcode/models/research/object_detection/ssd_mobilenet_v1_coco_2018_01_28/saved_model --num_train_steps=50000 --alsologtostderr This is my config : train_config { batch_size: 24 data_augmentation_options { random_horizontal_flip { } } data_augmentation_options { ssd_random_crop { } } optimizer { rms_prop_optimizer { learning_rate { exponential_decay_learning_rate { initial_learning_rate: 0.00400000018999 decay_steps: 800720 decay_factor: 0.949999988079 } } momentum_optimizer_value: 0.899999976158 decay: 0.899999976158 epsilon: 1.0 } } fine_tune_checkpoint: "D:/gitcode/models/research/object_detection/ssd_mobilenet_v1_coco_2018_01_28/model.ckpt" from_detection_checkpoint: true num_steps: 200000 train_input_reader { label_map_path: "D:/gitcode/models/research/object_detection/idol/tf_label_map.pbtxt" tf_record_input_reader { input_path: "D:/gitcode/models/research/object_detection/idol/train/Iframe_??????.tfrecord" } } eval_config { num_examples: 8000 max_evals: 10 use_moving_averages: false } eval_input_reader { label_map_path: "D:/gitcode/models/research/object_detection/idol/tf_label_map.pbtxt" shuffle: false num_readers: 1 tf_record_input_reader { input_path: "D:/gitcode/models/research/object_detection/idol/eval/Iframe_??????.tfrecord" } ``` 窗口输出： (default) D:\gitcode\models\research>python object_detection/model_main.py --pipeline_config_path=D:/gitcode/models/research/object_detection/ssd_mobilenet_v1_coco_2018_01_28/pipeline.config --model_dir=D:/gitcode/models/research/object_detection/ssd_mobilenet_v1_coco_2018_01_28/saved_model --num_train_steps=50000 --alsologtostderr WARNING: The TensorFlow contrib module will not be included in TensorFlow 2.0. For more information, please see: https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md https://github.com/tensorflow/addons If you depend on functionality not listed there, please file an issue. WARNING:tensorflow:Forced number of epochs for all eval validations to be 1. WARNING:tensorflow:Expected number of evaluation epochs is 1, but instead encountered eval_on_train_input_config.num_epochs = 0. Overwriting num_epochs to 1. WARNING:tensorflow:Estimator's model_fn (<function create_model_fn..model_fn at 0x0000027CBAB7BB70>) includes params argument, but params are not passed to Estimator. WARNING:tensorflow:From C:\Users\qian\Anaconda3\envs\default\lib\site-packages\tensorflow\python\framework\op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version. Instructions for updating: Colocations handled automatically by placer. WARNING:tensorflow:From C:\Users\qian\Anaconda3\envs\default\lib\site-packages\object_detection-0.1-py3.7.egg\object_detection\builders\dataset_builder.py:86: parallel_interleave (from tensorflow.contrib.data.python.ops.interleave_ops) is deprecated and will be removed in a future version. Instructions for updating: Use tf.data.experimental.parallel_interleave(...). WARNING:tensorflow:From C:\Users\qian\Anaconda3\envs\default\lib\site-packages\object_detection-0.1-py3.7.egg\object_detection\core\preprocessor.py:196: sample_distorted_bounding_box (from tensorflow.python.ops.image_ops_impl) is deprecated and will be removed in a future version. Instructions for updating: seed2 arg is deprecated.Use sample_distorted_bounding_box_v2 instead. WARNING:tensorflow:From C:\Users\qian\Anaconda3\envs\default\lib\site-packages\object_detection-0.1-py3.7.egg\object_detection\builders\dataset_builder.py:158: batch_and_drop_remainder (from tensorflow.contrib.data.python.ops.batching) is deprecated and will be removed in a future version. Instructions for updating: Use tf.data.Dataset.batch(..., drop_remainder=True). WARNING:tensorflow:From C:\Users\qian\Anaconda3\envs\default\lib\site-packages\tensorflow\python\ops\losses\losses_impl.py:448: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use tf.cast instead. WARNING:tensorflow:From C:\Users\qian\Anaconda3\envs\default\lib\site-packages\tensorflow\python\ops\array_grad.py:425: 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. 2019-08-14 16:29:31.607841: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1433] Found device 0 with properties: name: GeForce GTX 1060 6GB major: 6 minor: 1 memoryClockRate(GHz): 1.7845 pciBusID: 0000:04:00.0 totalMemory: 6.00GiB freeMemory: 4.97GiB 2019-08-14 16:29:31.621836: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1512] Adding visible gpu devices: 0 2019-08-14 16:29:32.275712: I tensorflow/core/common_runtime/gpu/gpu_device.cc:984] Device interconnect StreamExecutor with strength 1 edge matrix: 2019-08-14 16:29:32.283072: I tensorflow/core/common_runtime/gpu/gpu_device.cc:990] 0 2019-08-14 16:29:32.288675: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1003] 0: N 2019-08-14 16:29:32.293514: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4714 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060 6GB, pci bus id: 0000:04:00.0, compute capability: 6.1) WARNING:tensorflow:From C:\Users\qian\Anaconda3\envs\default\lib\site-packages\object_detection-0.1-py3.7.egg\object_detection\eval_util.py:796: to_int64 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use tf.cast instead. WARNING:tensorflow:From C:\Users\qian\Anaconda3\envs\default\lib\site-packages\object_detection-0.1-py3.7.egg\object_detection\utils\visualization_utils.py:498: py_func (from tensorflow.python.ops.script_ops) is deprecated and will be removed in a future version. Instructions for updating: tf.py_func is deprecated in TF V2. Instead, use tf.py_function, which takes a python function which manipulates tf eager tensors instead of numpy arrays. It's easy to convert a tf eager tensor to an ndarray (just call tensor.numpy()) but having access to eager tensors means tf.py_functions can use accelerators such as GPUs as well as being differentiable using a gradient tape. 2019-08-14 16:41:44.736212: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1512] Adding visible gpu devices: 0 2019-08-14 16:41:44.741242: I tensorflow/core/common_runtime/gpu/gpu_device.cc:984] Device interconnect StreamExecutor with strength 1 edge matrix: 2019-08-14 16:41:44.747522: I tensorflow/core/common_runtime/gpu/gpu_device.cc:990] 0 2019-08-14 16:41:44.751256: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1003] 0: N 2019-08-14 16:41:44.755548: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4714 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060 6GB, pci bus id: 0000:04:00.0, compute capability: 6.1) WARNING:tensorflow:From C:\Users\qian\Anaconda3\envs\default\lib\site-packages\tensorflow\python\training\saver.py:1266: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version. Instructions for updating: Use standard file APIs to check for files with this prefix. creating index... index created! creating index... index created! Running per image evaluation... Evaluate annotation type bbox DONE (t=2.43s). Accumulating evaluation results... DONE (t=0.14s). Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.287 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.529 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.278 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.031 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.312 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.162 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.356 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.356 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.061 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.384 (default) D:\gitcode\models\research>
简单BP神经网络训练鸢尾花_course
2019-06-09大佬们，请问result为什么大于0.8就是1，小于0.2是0，其他值则为0.5啊？ ``` import pandas as pd import matplotlib.pyplot as plt import numpy as np import tensorflow as tf iris = pd.read_csv("Iris.txt",names=['a','b','c','d','class']) iris['class'][iris['class']=="Iris-setosa"] = 0 iris['class'][iris['class']=="Iris-versicolor"] = 0.5 iris['class'][iris['class']=="Iris-virginica"] = 1 iris_class1 = iris[iris["class"]==0] iris_class2 = iris[iris["class"]==0.5] iris_class3 = iris[iris["class"]==1] temp = np.array(iris) train_data = np.delete(temp,range(len(temp))[::3],axis=0) test_data = temp[::3,:] """ 添加神经网络层的函数 inputs -- 输入内容 in_size -- 输入尺寸 out_size -- 输出尺寸 activation_function --- 激励函数，可以不用输入 """ def add_layer(inputs,in_size,out_size,activation_function=None): W = tf.Variable(tf.zeros([in_size,out_size])+0.01) #定义，in_size行,out_size列的矩阵,随机矩阵，全为0效果不佳 b = tf.Variable(tf.zeros([1,out_size])+0.01) #不建议为0 Wx_plus_b = tf.matmul(inputs,W) + b # WX + b if activation_function is None: #如果有激励函数就激励，否则直接输出 output = Wx_plus_b else: output = activation_function(Wx_plus_b) return output X = tf.placeholder(tf.float32,[None,4]) Y = tf.placeholder(tf.float32,[None,1]) output1 = add_layer(X,4,8,activation_function = tf.nn.sigmoid) output2 = add_layer(output1,8,3,activation_function = tf.nn.sigmoid) temp_y = add_layer(output2,3,1,activation_function = tf.nn.sigmoid) #先求平方，再求和，在求平均 loss = tf.reduce_mean(tf.reduce_sum(tf.square(Y-temp_y),reduction_indices=[1])) #通过优化器，以0.001的学习率，减小误差loss train_step = tf.train.AdamOptimizer(0.001).minimize(loss) #拆分训练集数据集，分为输入和输出 train_x = train_data[:,:4] train_y = train_data[:,-1:] sess = tf.Session() sess.run(tf.global_variables_initializer()) save_process = [] for i in range(90000):#训练90000次 sess.run(train_step,feed_dict={X:train_x,Y:train_y}) if i%300 == 0:#每300次记录损失值（偏差值） save_process.append(sess.run(loss,feed_dict={X:train_x,Y:train_y})) #第前两个数据比较大，踢掉 # save_process = np.delete(save_process,[0,1]) # plt.plot(range(len(save_process)),save_process) def compare_numpy(a,b,is_num=False): """比较两个维度相同的数组，返回相同数字个数/相似度""" num = 0 for i in range(len(a)): if a[i]==b[i]: num+=1 return num if is_num else num/len(a) test_x = test_data[:,:4] test_y = test_data[:,-1:] result = sess.run(temp_y,feed_dict={X:test_x}) result[result > 0.8] = 1 result[result < 0.2] = 0 result[(result < 0.8) & ( result > 0.2)] = 0.5 print("总数:",len(test_data)," 准确个数：",compare_numpy(result,test_y,True)," 精确度：",compare_numpy(result,test_y)) ```
下了一个利用gym环境进行机器学习的代码，配置好环境后，运行失败，实在是看不懂了？_course
2020-02-18本人配置的环境是 tensorflow2.1.0 keras2.3.1 代码运行错误的输出如下 在网上找没找到出现类似问题的。。哭了 ``` Traceback (most recent call last): File ".\DeepQ_v0.py", line 157, in <module> learner.train() File ".\DeepQ_v0.py", line 110, in train update_target = np.copy(self.model.predict(old_state.reshape(1, self.input_width))[0]) File "D:\python3.6.3\lib\site-packages\keras\engine\training.py", line 1462, in predict callbacks=callbacks) File "D:\python3.6.3\lib\site-packages\keras\engine\training_arrays.py", line 324, in predict_loop batch_outs = f(ins_batch) File "D:\python3.6.3\lib\site-packages\tensorflow_core\python\keras\backend.py", line 3727, in __call__ outputs = self._graph_fn(*converted_inputs) File "D:\python3.6.3\lib\site-packages\tensorflow_core\python\eager\function.py", line 1551, in __call__ return self._call_impl(args, kwargs) File "D:\python3.6.3\lib\site-packages\tensorflow_core\python\eager\function.py", line 1591, in _call_impl return self._call_flat(args, self.captured_inputs, cancellation_manager) File "D:\python3.6.3\lib\site-packages\tensorflow_core\python\eager\function.py", line 1692, in _call_flat ctx, args, cancellation_manager=cancellation_manager)) File "D:\python3.6.3\lib\site-packages\tensorflow_core\python\eager\function.py", line 545, in call ctx=ctx) File "D:\python3.6.3\lib\site-packages\tensorflow_core\python\eager\execute.py", line 67, in quick_execute six.raise_from(core._status_to_exception(e.code, message), None) File "<string>", line 3, in raise_from tensorflow.python.framework.errors_impl.NotFoundError: '__inference_keras_scratch_graph_144' is neither a type of a primitive operation nor a name of a function registered in binary running on LAPTOP-JKA2BVQ. Make sure the operation or function is registered in the binary running in this process. ```
如何使用labview调用tensorflow训练好的模型_course
2019-06-18https://forums.ni.com/t5/LabVIEW-Idea-Exchange/Tensorflow-API-for-LabVIEW/idi-p/3248737?profile.language=zh-CN 按照上面链接的配置labview调用tensorflow模型，一直报错  但我节点名称也应该是对的啊
代码用tensorflow-CPU运行时没有错误，用GPU运行时每次到51%报错_course
2019-08-12 51%|████████████████████████████████████████████████████████████████████████████████████████████████████▎ | 199/391 [00:38<00:21, 8.81it/s]2019-08-12 20:20:04.963304: I tensorflow/core/kernels/cuda_solvers.cc:159] Creating CudaSolver handles for stream 0000016EAC1D0A40 2019-08-12 20:20:05.763636: W tensorflow/core/framework/op_kernel.cc:1401] OP_REQUIRES failed at cuda_solvers.cc:260 : Invalid argument: Got info = 85505 for batch index 0, expected info = 0. Debug_info = heevd ** On entry to SGEMM parameter number 10 had an illegal value 2019-08-12 20:20:06.320473: W tensorflow/core/framework/op_kernel.cc:1401] OP_REQUIRES failed at cuda_solvers.cc:260 : Invalid argument: Got info = 5236925 for batch index 0, expected info = 0. Debug_info = heevd 2019-08-12 20:20:06.328931: W tensorflow/core/framework/op_kernel.cc:1401] OP_REQUIRES failed at cuda_solvers.cc:260 : Invalid argument: Got info = 1871 for batch index 0, expected info = 0. Debug_info = heevd 2019-08-12 20:20:06.838588: W tensorflow/core/framework/op_kernel.cc:1401] OP_REQUIRES failed at cuda_solvers.cc:260 : Invalid argument: Got info = 687520 for batch index 0, expected info = 0. Debug_info = heevd 2019-08-12 20:20:06.850771: W tensorflow/core/framework/op_kernel.cc:1401] OP_REQUIRES failed at cuda_solvers.cc:260 : Invalid argument: Got info = 321 for batch index 0, expected info = 0. Debug_info = heevd 2019-08-12 20:20:06.999345: W tensorflow/core/framework/op_kernel.cc:1401] OP_REQUIRES failed at cuda_solvers.cc:260 : Invalid argument: Got info = 42770 for batch index 0, expected info = 0. Debug_info = heevd 2019-08-12 20:20:07.499292: W tensorflow/core/framework/op_kernel.cc:1401] OP_REQUIRES failed at cuda_solvers.cc:260 : Invalid argument: Got info = 1497278 for batch index 0, expected info = 0. Debug_info = heevd 2019-08-12 20:20:07.510245: W tensorflow/core/framework/op_kernel.cc:1401] OP_REQUIRES failed at cuda_solvers.cc:260 : Invalid argument: Got info = 321 for batch index 0, expected info = 0. Debug_info = heevd 2019-08-12 20:20:08.020011: W tensorflow/core/framework/op_kernel.cc:1401] OP_REQUIRES failed at cuda_solvers.cc:260 : Invalid argument: Got info = 256112 for batch index 0, expected info = 0. Debug_info = heevd 2019-08-12 20:20:08.529828: W tensorflow/core/framework/op_kernel.cc:1401] OP_REQUIRES failed at cuda_solvers.cc:260 : Invalid argument: Got info = 341471 for batch index 0, expected info = 0. Debug_info = heevd 2019-08-12 20:20:08.540870: W tensorflow/core/framework/op_kernel.cc:1401] OP_REQUIRES failed at cuda_solvers.cc:260 : Invalid argument: Got info = 16833 for batch index 0, expected info = 0. Debug_info = heevd 2019-08-12 20:20:08.697339: W tensorflow/core/framework/op_kernel.cc:1401] OP_REQUIRES failed at cuda_solvers.cc:260 : Invalid argument: Got info = 1190 for batch index 0, expected info = 0. Debug_info = heevd Traceback (most recent call last): File "D:\softAPP\python\anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1334, in _do_call return fn(*args) File "D:\softAPP\python\anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1319, in _run_fn options, feed_dict, fetch_list, target_list, run_metadata) File "D:\softAPP\python\anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1407, in _call_tf_sessionrun run_metadata) tensorflow.python.framework.errors_impl.InvalidArgumentError: Got info = 85505 for batch index 0, expected info = 0. Debug_info = heevd [[{{node KFAC/SelfAdjointEigV2_10}}]] During handling of the above exception, another exception occurred: Traceback (most recent call last): File "main.py", line 67, in <module> main() File "main.py", line 63, in main trainer.train() File "E:\python代码\noisy-K-FAC\noisy-K-FAC\core\train.py", line 16, in train self.train_epoch() File "E:\python代码\noisy-K-FAC\noisy-K-FAC\core\train.py", line 42, in train_epoch self.sess.run([self.model.inv_update_op, self.model.var_update_op], feed_dict=feed_dict) File "D:\softAPP\python\anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 929, in run run_metadata_ptr) File "D:\softAPP\python\anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1152, in _run feed_dict_tensor, options, run_metadata) File "D:\softAPP\python\anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1328, in _do_run run_metadata) File "D:\softAPP\python\anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1348, in _do_call raise type(e)(node_def, op, message) tensorflow.python.framework.errors_impl.InvalidArgumentError: Got info = 85505 for batch index 0, expected info = 0. Debug_info = heevd [[node KFAC/SelfAdjointEigV2_10 (defined at E:\python代码\noisy-K-FAC\noisy-K-FAC\ops\utils.py:161) ]] Caused by op 'KFAC/SelfAdjointEigV2_10', defined at: File "main.py", line 67, in <module> main() File "main.py", line 60, in main model_ = Model(config, _INPUT_DIM[config.dataset], len(train_loader.dataset)) File "E:\python代码\noisy-K-FAC\noisy-K-FAC\core\model.py", line 21, in __init__ self.init_optim() File "E:\python代码\noisy-K-FAC\noisy-K-FAC\core\model.py", line 70, in init_optim momentum=self.config.momentum) File "E:\python代码\noisy-K-FAC\noisy-K-FAC\ops\optimizer.py", line 66, in __init__ inv_devices=inv_devices) File "E:\python代码\noisy-K-FAC\noisy-K-FAC\ops\estimator.py", line 58, in __init__ setup = self._setup(cov_ema_decay) File "E:\python代码\noisy-K-FAC\noisy-K-FAC\ops\estimator.py", line 108, in _setup inv_updates = {op.name: op for op in self._get_all_inverse_update_ops()} File "E:\python代码\noisy-K-FAC\noisy-K-FAC\ops\estimator.py", line 108, in <dictcomp> inv_updates = {op.name: op for op in self._get_all_inverse_update_ops()} File "E:\python代码\noisy-K-FAC\noisy-K-FAC\ops\estimator.py", line 116, in _get_all_inverse_update_ops for op in factor.make_inverse_update_ops(): File "E:\python代码\noisy-K-FAC\noisy-K-FAC\ops\fisher_factors.py", line 360, in make_inverse_update_ops ops.append(inv.assign(utils.posdef_inv(self._cov, damping))) File "E:\python代码\noisy-K-FAC\noisy-K-FAC\ops\utils.py", line 144, in posdef_inv return posdef_inv_functions[POSDEF_INV_METHOD](tensor, identity, damping) File "E:\python代码\noisy-K-FAC\noisy-K-FAC\ops\utils.py", line 161, in posdef_inv_eig tensor + damping * identity) File "D:\softAPP\python\anaconda3\lib\site-packages\tensorflow\python\ops\linalg_ops.py", line 328, in self_adjoint_eig e, v = gen_linalg_ops.self_adjoint_eig_v2(tensor, compute_v=True, name=name) File "D:\softAPP\python\anaconda3\lib\site-packages\tensorflow\python\ops\gen_linalg_ops.py", line 2016, in self_adjoint_eig_v2 "SelfAdjointEigV2", input=input, compute_v=compute_v, name=name) File "D:\softAPP\python\anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 788, in _apply_op_helper op_def=op_def) File "D:\softAPP\python\anaconda3\lib\site-packages\tensorflow\python\util\deprecation.py", line 507, in new_func return func(*args, **kwargs) File "D:\softAPP\python\anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 3300, in create_op op_def=op_def) File "D:\softAPP\python\anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1801, in __init__ self._traceback = tf_stack.extract_stack() InvalidArgumentError (see above for traceback): Got info = 85505 for batch index 0, expected info = 0. Debug_info = heevd [[node KFAC/SelfAdjointEigV2_10 (defined at E:\python代码\noisy-K-FAC\noisy-K-FAC\ops\utils.py:161) ]] ``` ```
神经网络GPU运算内存不足_course
2020-05-15# 类型一（通过自动求导来优化模型参数） ``` import tensorflow as tf from tensorflow import keras from tensorflow.keras import optimizers, datasets from tensorflow.keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPooling2D from sklearn.model_selection import train_test_split import matplotlib.pyplot as plt import os 提取mnist数据集 def mnist_dataset(): (x, y), (x_test, y_test) = datasets.mnist.load_data() x_train,x_valid,y_train,y_valid = train_test_split(x, y, test_size=0.2) #划分验证集 #Normalize归一化 x_train = tf.cast(x_train/255.0, dtype=tf.float32) x_valid = tf.cast(x_valid/255.0, dtype=tf.float32) x_test = tf.cast(x_test/255.0, dtype=tf.float32) #增加维度:( , , )-->( , , , ) x_train = tf.expand_dims(x_train, axis=3) x_valid = tf.expand_dims(x_valid, axis=3) x_test = tf.expand_dims(x_test, axis=3) #对标签数据进行独热编码 y_train = tf.one_hot(y_train, depth=10, dtype=tf.float32) y_valid = tf.one_hot(y_valid, depth=10, dtype=tf.float32) y_test = tf.one_hot(y_test, depth=10, dtype=tf.float32) return (x_train, y_train), (x_valid, y_valid), (x_test, y_test) #定义模型 class Convolution_NN(keras.Model): def __init__(self): super(Convolution_NN, self).__init__() # super(): https://wiki.jikexueyuan.com/project/explore-python/Class/super.html self.L1_conv = Conv2D(filters=10, kernel_size=(5, 5), activation='relu', padding='same') self.L2_conv = Conv2D(filters=10, kernel_size=(5, 5), activation='relu', padding='same') self.pool = MaxPooling2D(pool_size=(2, 2), strides=2) self.flat = Flatten() self.dense1 = Dense(100, activation='tanh') self.dense2 = Dense(10, activation='softmax') def call(self, inputs): h1 = self.L1_conv(inputs) h1_pool = self.pool(h1) h2 = self.L2_conv(h1_pool) h2_pool = self.pool(h2) flat_h = self.flat(h2_pool) dense1 = self.dense1(flat_h) logits = self.dense2(dense1) return logits #定义交叉熵损失函数 def compute_loss(logits, labels): return tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels, logits)) #定义预测准确率函数 def compute_accuracy(logits, labels): predictions = tf.argmax(logits, axis=1) labels = tf.argmax(labels, axis=1) return tf.reduce_mean(tf.cast(tf.equal(predictions, labels), tf.float32)) #参数优化 def train_one_step(model, optimizer, x, y): with tf.GradientTape() as tape: logits = model(x) loss = compute_loss(logits, y) #compute gradient grads = tape.gradient(loss, model.trainable_variables) #update to weights optimizer.apply_gradients(zip(grads, model.trainable_variables)) #------------------------------ if __name__ == '__main__': (x_train, y_train), (x_valid, y_valid), (x_test, y_test) = mnist_dataset() #设置训练超参数 training_epochs = 20 #训练轮数 batch_size = 50 #单次训练的样本数(批次的大小) Mini-Batch优化 learning_rate = 0.001 #学习率 model = Convolution_NN() optimizer = optimizers.Adam(learning_rate=learning_rate) steps = int(x_train.shape[0]/batch_size) #一轮训练的批次 for epoch in range(training_epochs): for step in range(steps): X = x_train[step*batch_size:(step+1)*batch_size] Y = y_train[step*batch_size:(step+1)*batch_size] train_one_step(model, optimizer, X, Y) ``` # 类型二（通过tf的高阶API-Keras来训练模型参数） ``` import tensorflow as tf from tensorflow import keras from tensorflow.keras import optimizers, datasets from tensorflow.keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPooling2D from sklearn.model_selection import train_test_split import matplotlib.pyplot as plt import os #提取mnist数据集 def mnist_dataset(): (x_train, y_train), (x_test, y_test) = datasets.mnist.load_data() #Normalize归一化 x_train = tf.cast(x_train/255.0, dtype=tf.float32) x_test = tf.cast(x_test/255.0, dtype=tf.float32) #增加维度:( , , )-->( , , , ) x_train = tf.expand_dims(x_train, axis=3) x_test = tf.expand_dims(x_test, axis=3) #对标签数据进行独热编码 y_train = tf.one_hot(y_train, depth=10, dtype=tf.float32) y_test = tf.one_hot(y_test, depth=10, dtype=tf.float32) return (x_train, y_train), (x_test, y_test) #定义模型 class Convolution_NN(keras.Model): def __init__(self): super(Convolution_NN, self).__init__() # super(): https://wiki.jikexueyuan.com/project/explore-python/Class/super.html self.L1_conv = Conv2D(filters=10, kernel_size=(5, 5), activation='relu', padding='same') self.L2_conv = Conv2D(filters=10, kernel_size=(5, 5), activation='relu', padding='same') self.pool = MaxPooling2D(pool_size=(2, 2), strides=2) self.flat = Flatten() self.dense1 = Dense(100, activation='tanh') self.dense2 = Dense(10, activation='softmax') def call(self, inputs): h1 = self.L1_conv(inputs) h1_pool = self.pool(h1) h2 = self.L2_conv(h1_pool) h2_pool = self.pool(h2) flat_h = self.flat(h2_pool) dense1 = self.dense1(flat_h) logits = self.dense2(dense1) return logits #------------------------------ if __name__ == '__main__': #os.environ["CUDA_VISIBLE_DEVICES"] = "-1" #GPU内存不足(降低batch_size),改用CPU运算 (x_train, y_train), (x_test, y_test) = mnist_dataset() model = Convolution_NN() optimizer = optimizers.Adam() model.compile(optimizer=optimizer, loss='categorical_crossentropy', metrics=['accuracy']) #设置训练超参数 training_epochs = 20 #训练轮数 batch_size = 50 #单次训练的样本数(批次的大小) Mini-Batch优化 #训练模型 train_history = model.fit(x_train, y_train, validation_split=0.2, epochs=training_epochs, batch_size=batch_size, verbose=2) ``` ## 一句话总结：类型一，我自己优化参数，在GPU上跑，显示：OOM when allocating tensor with shape[48000,28,28,10] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc [Op:Conv2D]，即内存不足。 类型二，无脑调用API优化参数，很流畅的在GPU上跑。 为什么呢？很迷惑！讲道理Keras优化参数的方法应该和我一致呀，只是它的封装好了，为什么它的可以在GPU上跑，我的就显示内存不足呢？
TensorFlow如何在训练过程中获取权重值_course
2017-12-06比如一个两层卷积的网络，我想在每次训练的时候输出第一层卷积的权重值矩阵的数值，来观察随着训练的进行权重值如何更新。请问代码如何实现？
Tensorflow 如何判断两个tensor相等_course
2017-08-25Tensorflow 如何判断两个tensor相等? tf.equal()会判断tensor中每个元素是否相等，比如： a=[1,0] b=[1,1] tf.equal(a,b)结果为[True,False] 现在我希望整体判断，即tensor每个元素都相同，只返回一个True，否则返回一个False 要如何做呢？
tensorflow-gpu：Faild to load tensorflow native runtime_course
2019-05-23linux系统下，安装好了cuda9.0+cudnn7.5+tensorflow-gpu1.11.0，运行代码时出现f, 但是如果将tensorflow-gpu版本换成对于的tensorflow cpu版本时可以运行的，咋回事？？？
amd cpu跑深度学习可不可以，会不会有兼容之类的问题？_course
2020-04-15想要用amdCPU和n卡的笔记本跑深度学习毕设（深度学习，卷积神经网络），但是担心amd cpu 的兼容问题，想请教这种搭配稳不稳。
玩转Linux：常用命令实例指南
2019-09-28人工智能、物联网、大数据时代，Linux正有着一统天下的趋势，几乎每个程序员岗位，都要求掌握Linux。本课程零基础也能轻松入门。 本课程以简洁易懂的语言手把手教你系统掌握日常所需的Linux知识，每个知识点都会配合案例实战让你融汇贯通。课程通俗易懂，简洁流畅，适合0基础以及对Linux掌握不熟练的人学习； 【限时福利】 1）购课后按提示添加小助手，进答疑群，还可获得价值300元的编程大礼包！ 2）本月购买此套餐加入老师答疑交流群，可参加老师的免费分享活动，学习最新技术项目经验。 --------------------------------------------------------------- 29元=掌握Linux必修知识+社群答疑+讲师社群分享会+700元编程礼包。
专为程序员设计的数学课_course
2019-11-11<p> 限时福利限时福利，<span>15000+程序员的选择！</span> </p> <p> 购课后添加学习助手（微信号：csdn590），按提示消息领取编程大礼包！并获取讲师答疑服务！ </p> <p> <br> </p> <p> 套餐中一共包含5门程序员必学的数学课程（共47讲） </p> <p> 课程1：《零基础入门微积分》 </p> <p> 课程2：《数理统计与概率论》 </p> <p> 课程3：《代码学习线性代数》 </p> <p> 课程4：《数据处理的最优化》 </p> <p> 课程5：《马尔可夫随机过程》 </p> <p> <br> </p> <p> 哪些人适合学习这门课程？ </p> <p> 1）大学生，平时只学习了数学理论，并未接触如何应用数学解决编程问题； </p> <p> 2）对算法、数据结构掌握程度薄弱的人，数学可以让你更好的理解算法、数据结构原理及应用； </p> <p> 3）看不懂大牛代码设计思想的人，因为所有的程序设计底层逻辑都是数学； </p> <p> 4）想学习新技术，如：人工智能、机器学习、深度学习等，这门课程是你的必修课程； </p> <p> 5）想修炼更好的编程内功，在遇到问题时可以灵活的应用数学思维解决问题。 </p> <p> <br> </p> <p> 在这门「专为程序员设计的数学课」系列课中，我们保证你能收获到这些:<br> <br> <span> </span> </p> <p class="ql-long-24357476"> <span class="ql-author-24357476">①价值300元编程课程大礼包</span> </p> <p class="ql-long-24357476"> <span class="ql-author-24357476">②应用数学优化代码的实操方法</span> </p> <p class="ql-long-24357476"> <span class="ql-author-24357476">③数学理论在编程实战中的应用</span> </p> <p class="ql-long-24357476"> <span class="ql-author-24357476">④程序员必学的5大数学知识</span> </p> <p class="ql-long-24357476"> <span class="ql-author-24357476">⑤人工智能领域必修数学课</span> </p> <p> <br> 备注：此课程只讲程序员所需要的数学，即使你数学基础薄弱，也能听懂，只需要初中的数学知识就足矣。<br> <br> 如何听课？ </p> <p> 1、登录CSDN学院 APP 在我的课程中进行学习； </p> <p> 2、登录CSDN学院官网。 </p> <p> <br> </p> <p> 购课后如何领取免费赠送的编程大礼包和加入答疑群？ </p> <p> 购课后，添加助教微信：<span> csdn590</span>，按提示领取编程大礼包，或观看付费视频的第一节内容扫码进群答疑交流！ </p> <p> <img src="https://img-bss.csdn.net/201912251155398753.jpg" alt=""> </p>
- 博客 HTML5中的语义标签
- 博客 mnn python 笔记
- 下载 dbeaver-ce_7.1.4_amd64.deb
- 博客 Java排序算法之选择排序和冒泡排序
- 博客 收藏一道好题hdu多校的
- 下载 中文文本分类项目数据集.rar
- 下载 前端VOE.zip，一个基于HTML5开发的UI源代码
- 下载 机械加工技术规范 GB/T 33947-2017 再制造
- 下载 浩哥教你装系统2.1.pptx
- 下载 国网104规约遥测值转换十进制.docx
- 下载 两位数码管循环显示00～99的实验简介
- 博客 java之SpringBoot
- 学院 linux下c语言高级编程入门
- 学院 架构规范和架构技能
- 下载 钢筋混凝土用耐蚀钢筋 GB/T 33953-2017
- 博客 camerahal之---rkisp-hal3内部实现(2)
- 学院 学生综合素质测评系统(毕设)
- 下载 webgis2.zip
- 下载 python实现随机图像验证码的生成
- 博客 Java中的多线程你只要看这一篇就够了
- 学院 MySql学习三剑客 深入索引、查询、事务与锁
- 下载 飞思卡尔ISO26262 ASIL-D电子助力转向演示系统方案_官方技术文档.docx
- 学院 Kubernetes持续集成/持续部署
- 下载 Inspect-x64.zip
- 下载 shortestPath.zip
- 下载 系统代理设置器[小白最新版].exe
- 学院 1小时搞定命令行下操作MySQL
- 博客 如何增加mysql的多核心利用数量
- 博客 数据过滤AND OR IN BETWEEN AND操作符的说明与使用
- 博客 前端向后台传值的5种方式总结