代码拉取完成，页面将自动刷新
运行指令： /root/anaconda3/envs/tensorflow/bin/python /usr/local/week7/quiz-w7-2-densenet/train_image_classifier.py --train_dir=/usr/local/week7/cifar10/train_logs --dataset_name=cifar10 --dataset_split_name=train --dataset_dir=/usr/local/week7/cifar10 --model_name=densenet WARNING:tensorflow:From /root/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/contrib/learn/python/learn/datasets/base.py:198: retry (from tensorflow.contrib.learn.python.learn.datasets.base) is deprecated and will be removed in a future version. Instructions for updating: Use the retry module or similar alternatives. WARNING:tensorflow:From /usr/local/week7/quiz-w7-2-densenet/train_image_classifier.py:400: create_global_step (from tensorflow.contrib.framework.python.ops.variables) is deprecated and will be removed in a future version. Instructions for updating: Please switch to tf.train.create_global_step WARNING:tensorflow:From /usr/local/week7/quiz-w7-2-densenet/train_image_classifier.py:468: softmax_cross_entropy (from tensorflow.contrib.losses.python.losses.loss_ops) is deprecated and will be removed after 2016-12-30. Instructions for updating: Use tf.losses.softmax_cross_entropy instead. Note that the order of the logits and labels arguments has been changed. WARNING:tensorflow:From /root/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/contrib/losses/python/losses/loss_ops.py:397: softmax_cross_entropy_with_logits (from tensorflow.python.ops.nn_ops) is deprecated and will be removed in a future version. Instructions for updating:
Future major versions of TensorFlow will allow gradients to flow into the labels input on backprop by default.
See tf.nn.softmax_cross_entropy_with_logits_v2.
WARNING:tensorflow:From /root/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/contrib/losses/python/losses/loss_ops.py:398: compute_weighted_loss (from tensorflow.contrib.losses.python.losses.loss_ops) is deprecated and will be removed after 2016-12-30. Instructions for updating: Use tf.losses.compute_weighted_loss instead. WARNING:tensorflow:From /root/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/contrib/losses/python/losses/loss_ops.py:146: add_arg_scope..func_with_args (from tensorflow.contrib.losses.python.losses.loss_ops) is deprecated and will be removed after 2016-12-30. Instructions for updating: Use tf.losses.add_loss instead. INFO:tensorflow:Summary name /clone_loss is illegal; using clone_loss instead. WARNING:tensorflow:From /root/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/contrib/slim/python/slim/learning.py:736: Supervisor.init (from tensorflow.python.training.supervisor) is deprecated and will be removed in a future version. Instructions for updating: Please switch to tf.train.MonitoredTrainingSession INFO:tensorflow:Running local_init_op. INFO:tensorflow:Done running local_init_op. INFO:tensorflow:Starting Session. INFO:tensorflow:Saving checkpoint to path /usr/local/week7/cifar10/train_logs/model.ckpt INFO:tensorflow:Starting Queues. INFO:tensorflow:global_step/sec: 0 INFO:tensorflow:Recording summary at step 0. INFO:tensorflow:Saving checkpoint to path /usr/local/week7/cifar10/train_logs/model.ckpt INFO:tensorflow:global_step/sec: 0.00162744 INFO:tensorflow:Recording summary at step 1. 中间结果省略 2018-04-25 13:04:04: I tensorflow/core/kernels/logging_ops.cc:79] eval/Accuracy[0.152138377] 2018-04-25 13:04:04: I tensorflow/core/kernels/logging_ops.cc:79] eval/Recall_5[0.294846059]
稠密连接：每层以之前层的输出为输入，对于有L层的传统网络，一共有L个连接，对于DenseNet，则有L(L+1)/2。 Growth rate：由于每个层的输入是所有之前层输出的连接，因此每个层的输出不需要像传统网络一样多。 这里Hl(.)的输出的特征图的数量都为k，k即为Growth Rate，用来控制网络的“宽度”（特征图的通道数）. 比如说第l层有k(l−1)+k0的输入特征图，k0是输入图片的通道数。 虽然说每个层只产生k个输出，但是后面层的输入依然会很多，因此引入了Bottleneck layers 。本质上是引入1x1的卷积层来减少输入的数量，Hl的具体表示如下 BN−>ReLU−>Conv(1×1)−>BN−>ReLU−>Conv(3×3)
本代码为系列课程, 第七周部分的课后作业内容。 https://edu.csdn.net/topic/ai115
学员自己实现一个densenet的网络，并插入到slim框架中进行训练。
tinymind 使用说明：https://gitee.com/ai100/quiz-w7-doc
本数据集拥有200个分类，每个分类300张图片，共计6W张图片，其中5W张作为训练集，1W张图片作为验证集。图片已经预打包为tfrecord格式并上传到tinymind上。地址如下： https://www.tinymind.com/ai100/datasets/quiz-w7
模型代码来自： https://github.com/tensorflow/models/tree/master/research/slim
这里为了适应本作业提供的数据集，稍作修改，添加了一个quiz数据集以及一个训练并验证的脚本，实际使用的代码为： https://gitee.com/ai100/quiz-w7-2-densenet
其中nets目录下的densenet.py中已经定义了densenet网络的入口函数等，相应的辅助代码也都已经完成，学员只需要check或者fork这里的代码，添加自己的densenet实现并在tinymind上建立相应的模型即可。
densenet论文参考 https://arxiv.org/abs/1608.06993
在tinymind上新建一个模型，模型设置参考如下模型：
https://www.tinymind.com/ai100/quiz-w7-2-densenet 复制模型后可以看到模型的全部参数。
模型参数的解释：
鼓励参与课程的学员尝试不同的参数组合以体验不同的参数对训练准确率和收敛速度的影响。
学员需要提供运行log的截图和文档描述
在tinymind运行log的输出中，可以看到如下内容：
2017-12-1 23:03:04.327009: I tensorflow/core/kernels/logging_ops.cc:79] eval/Accuracy[0.252197266]
2017-12-1 23:03:04.327097: I tensorflow/core/kernels/logging_ops.cc:79] eval/Recall_5[0.494873047]
densenet的网络，效果要略好于inceptionv4。考虑到实现的不同，而且没有预训练模型，这里不对准确率做要求。只要训练运行成功并有准确率输出即可认为及格60分。
提供对densenet实现过程的描述： 对growth的理解 20分 对稠密链接的理解 20分
epoch计算方式： epoch = step * batch_size / count_all_train_pics
本地运行slim框架所用命令行：
使用预训练模型进行inceptionv4等的finetune
训练：
python3 train_image_classifier.py --dataset_name=quiz --dataset_dir=/path/to/data --checkpoint_path=/path/to/inception_v4.ckpt --model_name=inception_v4 --checkpoint_exclude_scopes=InceptionV4/Logits,InceptionV4/AuxLogits/Aux_logits --train_dir=/path/to/train_ckpt --learning_rate=0.001 --optimizer=rmsprop --batch_size=32
train集验证：
python3 eval_image_classifier.py --dataset_name=quiz --dataset_dir=/path/to/data --dataset_split_name=train --model_name=inception_v4 --checkpoint_path=/path/to/train_ckpt --eval_dir=/path/to/train_eval --batch_size=32 --max_num_batches=128
validation集验证：
python3 eval_image_classifier.py --dataset_name=quiz --dataset_dir=/path/to/data --dataset_split_name=validation --model_name=inception_v4 --checkpoint_path=/path/to/train_ckpt --eval_dir=/path/to/validation_eval --batch_size=32 --max_num_batches=128
统一脚本：
python3 train_eval_image_classifier.py --dataset_name=quiz --dataset_dir=/path/to/data --checkpoint_path=/path/to/inception_v4.ckpt --model_name=inception_v4 --checkpoint_exclude_scopes=InceptionV4/Logits,InceptionV4/AuxLogits/Aux_logits --optimizer=rmsprop --train_dir=/path/to/log/train_ckpt --learning_rate=0.001 --dataset_split_name=validation --eval_dir=/path/to/eval --max_num_batches=128
从头开始训练densenet
训练
python3 train_image_classifier.py --dataset_name=quiz --dataset_dir=/path/to/data --model_name=densenet --train_dir=/path/to/train_ckpt_den --learning_rate=0.1 --optimizer=rmsprop --batch_size=16/path/to
train集验证：
python3 eval_image_classifier.py --dataset_name=quiz --dataset_dir=/path/to/data --dataset_split_name=train --model_name=densenet --checkpoint_path=/path/to/train_ckpt_den --eval_dir=/path/to/train_eval_den --batch_size=32 --max_num_batches=128
validation集验证：
python3 eval_image_classifier.py --dataset_name=quiz --dataset_dir=/path/to/data --dataset_split_name=validation --model_name=densenet --checkpoint_path=/path/to/train_ckpt_den --eval_dir=/path/to/validation_eval_den --batch_size=32 --max_num_batches=128
统一脚本：
python3 train_eval_image_classifier.py --dataset_name=quiz --dataset_dir=/path/to/data --model_name=densenet --checkpoint_exclude_scopes=InceptionV4/Logits,InceptionV4/AuxLogits/Aux_logits --train_dir=/path/to/log/train_ckpt --learning_rate=0.1 --dataset_split_name=validation --eval_dir=/path/to/eval_den --max_num_batches=128
本地没有显卡的情况下，使用上述命令进行训练会导致错误。只使用CPU进行训练的话，需要在训练命令或者统一脚本上添加**--clone_on_cpu=True参数。tinymind上则需要新建一个clone_on_cpu的bool类型参数并设置为True**
TF-slim
is a new lightweight high-level API of TensorFlow (tensorflow.contrib.slim)
for defining, training and evaluating complex
models. This directory contains
code for training and evaluating several widely used Convolutional Neural
Network (CNN) image classification models using TF-slim.
It contains scripts that will allow
you to train models from scratch or fine-tune them from pre-trained network
weights. It also contains code for downloading standard image datasets,
converting them
to TensorFlow's native TFRecord format and reading them in using TF-Slim's
data reading and queueing utilities. You can easily train any model on any of
these datasets, as we demonstrate below. We've also included a
jupyter notebook,
which provides working examples of how to use TF-Slim for image classification.
For developing or modifying your own models, see also the main TF-Slim page.
Maintainers of TF-slim:
Installation and setup
Preparing the datasets
Using pre-trained models
Training from scratch
Fine tuning to a new task
Evaluating performance
Exporting Inference Graph
Troubleshooting
In this section, we describe the steps required to install the appropriate prerequisite packages.
TF-Slim is available as tf.contrib.slim via TensorFlow 1.0. To test that your
installation is working, execute the following command; it should run without
raising any errors.
python -c "import tensorflow.contrib.slim as slim; eval = slim.evaluation.evaluate_once"
To use TF-Slim for image classification, you also have to install the TF-Slim image models library, which is not part of the core TF library. To do this, check out the tensorflow/models repository as follows:
cd $HOME/workspace
git clone https://github.com/tensorflow/models/
This will put the TF-Slim image models library in $HOME/workspace/models/research/slim.
(It will also create a directory called
models/inception,
which contains an older version of slim; you can safely ignore this.)
To verify that this has worked, execute the following commands; it should run without raising any errors.
cd $HOME/workspace/models/research/slim
python -c "from nets import cifarnet; mynet = cifarnet.cifarnet"
As part of this library, we've included scripts to download several popular image datasets (listed below) and convert them to slim format.
| Dataset | Training Set Size | Testing Set Size | Number of Classes | Comments |
|---|---|---|---|---|
| Flowers | 2500 | 2500 | 5 | Various sizes (source: Flickr) |
| Cifar10 | 60k | 10k | 10 | 32x32 color |
| MNIST | 60k | 10k | 10 | 28x28 gray |
| ImageNet | 1.2M | 50k | 1000 | Various sizes |
For each dataset, we'll need to download the raw data and convert it to TensorFlow's native TFRecord format. Each TFRecord contains a TF-Example protocol buffer. Below we demonstrate how to do this for the Flowers dataset.
$ DATA_DIR=/tmp/data/flowers
$ python download_and_convert_data.py \
--dataset_name=flowers \
--dataset_dir="${DATA_DIR}"
When the script finishes you will find several TFRecord files created:
$ ls ${DATA_DIR}
flowers_train-00000-of-00005.tfrecord
...
flowers_train-00004-of-00005.tfrecord
flowers_validation-00000-of-00005.tfrecord
...
flowers_validation-00004-of-00005.tfrecord
labels.txt
These represent the training and validation data, sharded over 5 files each.
You will also find the $DATA_DIR/labels.txt file which contains the mapping
from integer labels to class names.
You can use the same script to create the mnist and cifar10 datasets. However, for ImageNet, you have to follow the instructions here. Note that you first have to sign up for an account at image-net.org. Also, the download can take several hours, and could use up to 500GB.
Once the TFRecord files have been created, you can easily define a Slim Dataset, which stores pointers to the data file, as well as various other pieces of metadata, such as the class labels, the train/test split, and how to parse the TFExample protos. We have included the TF-Slim Dataset descriptors for Cifar10, ImageNet, Flowers, and MNIST. An example of how to load data using a TF-Slim dataset descriptor using a TF-Slim DatasetDataProvider is found below:
import tensorflow as tf
from datasets import flowers
slim = tf.contrib.slim
# Selects the 'validation' dataset.
dataset = flowers.get_split('validation', DATA_DIR)
# Creates a TF-Slim DataProvider which reads the dataset in the background
# during both training and testing.
provider = slim.dataset_data_provider.DatasetDataProvider(dataset)
[image, label] = provider.get(['image', 'label'])
Training a model with the ImageNet dataset is a common request. To facilitate working with the ImageNet dataset, we provide an automated script for downloading and processing the ImageNet dataset into the native TFRecord format.
The TFRecord format consists of a set of sharded files where each entry is a serialized tf.Example proto. Each tf.Example proto contains the ImageNet image (JPEG encoded) as well as metadata such as label and bounding box information.
We provide a single script for downloading and converting ImageNet data to TFRecord format. Downloading and preprocessing the data may take several hours (up to half a day) depending on your network and computer speed. Please be patient.
To begin, you will need to sign up for an account with [ImageNet] (http://image-net.org) to gain access to the data. Look for the sign up page, create an account and request an access key to download the data.
After you have USERNAME and PASSWORD, you are ready to run our script. Make
sure that your hard disk has at least 500 GB of free space for downloading and
storing the data. Here we select DATA_DIR=$HOME/imagenet-data as such a
location but feel free to edit accordingly.
When you run the below script, please enter USERNAME and PASSWORD when prompted. This will occur at the very beginning. Once these values are entered, you will not need to interact with the script again.
# location of where to place the ImageNet data
DATA_DIR=$HOME/imagenet-data
# build the preprocessing script.
bazel build slim/download_and_preprocess_imagenet
# run it
bazel-bin/slim/download_and_preprocess_imagenet "${DATA_DIR}"
The final line of the output script should read:
2016-02-17 14:30:17.287989: Finished writing all 1281167 images in data set.
When the script finishes you will find 1024 and 128 training and validation
files in the DATA_DIR. The files will match the patterns train-????-of-1024
and validation-?????-of-00128, respectively.
Congratulations! You are now ready to train or evaluate with the ImageNet data set.
Neural nets work best when they have many parameters, making them powerful function approximators. However, this means they must be trained on very large datasets. Because training models from scratch can be a very computationally intensive process requiring days or even weeks, we provide various pre-trained models, as listed below. These CNNs have been trained on the ILSVRC-2012-CLS image classification dataset.
In the table below, we list each model, the corresponding TensorFlow model file, the link to the model checkpoint, and the top 1 and top 5 accuracy (on the imagenet test set). Note that the VGG and ResNet V1 parameters have been converted from their original caffe formats (here and here), whereas the Inception and ResNet V2 parameters have been trained internally at Google. Also be aware that these accuracies were computed by evaluating using a single image crop. Some academic papers report higher accuracy by using multiple crops at multiple scales.
^ ResNet V2 models use Inception pre-processing and input image size of 299 (use
--preprocessing_name inception --eval_image_size 299 when using
eval_image_classifier.py). Performance numbers for ResNet V2 models are
reported on the ImageNet validation set.
(#) More information and details about the NASNet architectures are available at this README
All 16 MobileNet Models reported in the MobileNet Paper can be found here.
(*): Results quoted from the paper.
Here is an example of how to download the Inception V3 checkpoint:
$ CHECKPOINT_DIR=/tmp/checkpoints
$ mkdir ${CHECKPOINT_DIR}
$ wget http://download.tensorflow.org/models/inception_v3_2016_08_28.tar.gz
$ tar -xvf inception_v3_2016_08_28.tar.gz
$ mv inception_v3.ckpt ${CHECKPOINT_DIR}
$ rm inception_v3_2016_08_28.tar.gz
We provide an easy way to train a model from scratch using any TF-Slim dataset. The following example demonstrates how to train Inception V3 using the default parameters on the ImageNet dataset.
DATASET_DIR=/tmp/imagenet
TRAIN_DIR=/tmp/train_logs
python train_image_classifier.py \
--train_dir=${TRAIN_DIR} \
--dataset_name=imagenet \
--dataset_split_name=train \
--dataset_dir=${DATASET_DIR} \
--model_name=inception_v3
This process may take several days, depending on your hardware setup. For convenience, we provide a way to train a model on multiple GPUs, and/or multiple CPUs, either synchrononously or asynchronously. See model_deploy for details.
To visualize the losses and other metrics during training, you can use TensorBoard by running the command below.
tensorboard --logdir=${TRAIN_DIR}
Once TensorBoard is running, navigate your web browser to http://localhost:6006.
Rather than training from scratch, we'll often want to start from a pre-trained
model and fine-tune it.
To indicate a checkpoint from which to fine-tune, we'll call training with
the --checkpoint_path flag and assign it an absolute path to a checkpoint
file.
When fine-tuning a model, we need to be careful about restoring checkpoint
weights. In particular, when we fine-tune a model on a new task with a different
number of output labels, we wont be able restore the final logits (classifier)
layer. For this, we'll use the --checkpoint_exclude_scopes flag. This flag
hinders certain variables from being loaded. When fine-tuning on a
classification task using a different number of classes than the trained model,
the new model will have a final 'logits' layer whose dimensions differ from the
pre-trained model. For example, if fine-tuning an ImageNet-trained model on
Flowers, the pre-trained logits layer will have dimensions [2048 x 1001] but
our new logits layer will have dimensions [2048 x 5]. Consequently, this
flag indicates to TF-Slim to avoid loading these weights from the checkpoint.
Keep in mind that warm-starting from a checkpoint affects the model's weights
only during the initialization of the model. Once a model has started training,
a new checkpoint will be created in ${TRAIN_DIR}. If the fine-tuning
training is stopped and restarted, this new checkpoint will be the one from
which weights are restored and not the ${checkpoint_path}$. Consequently,
the flags --checkpoint_path and --checkpoint_exclude_scopes are only used
during the 0-th global step (model initialization). Typically for fine-tuning
one only want train a sub-set of layers, so the flag --trainable_scopes allows
to specify which subsets of layers should trained, the rest would remain frozen.
Below we give an example of fine-tuning inception-v3 on flowers, inception_v3 was trained on ImageNet with 1000 class labels, but the flowers dataset only have 5 classes. Since the dataset is quite small we will only train the new layers.
$ DATASET_DIR=/tmp/flowers
$ TRAIN_DIR=/tmp/flowers-models/inception_v3
$ CHECKPOINT_PATH=/tmp/my_checkpoints/inception_v3.ckpt
$ python train_image_classifier.py \
--train_dir=${TRAIN_DIR} \
--dataset_dir=${DATASET_DIR} \
--dataset_name=flowers \
--dataset_split_name=train \
--model_name=inception_v3 \
--checkpoint_path=${CHECKPOINT_PATH} \
--checkpoint_exclude_scopes=InceptionV3/Logits,InceptionV3/AuxLogits \
--trainable_scopes=InceptionV3/Logits,InceptionV3/AuxLogits
To evaluate the performance of a model (whether pretrained or your own), you can use the eval_image_classifier.py script, as shown below.
Below we give an example of downloading the pretrained inception model and evaluating it on the imagenet dataset.
CHECKPOINT_FILE = ${CHECKPOINT_DIR}/inception_v3.ckpt # Example
$ python eval_image_classifier.py \
--alsologtostderr \
--checkpoint_path=${CHECKPOINT_FILE} \
--dataset_dir=${DATASET_DIR} \
--dataset_name=imagenet \
--dataset_split_name=validation \
--model_name=inception_v3
See the evaluation module example for an example of how to evaluate a model at multiple checkpoints during or after the training.
Saves out a GraphDef containing the architecture of the model.
To use it with a model name defined by slim, run:
$ python export_inference_graph.py \
--alsologtostderr \
--model_name=inception_v3 \
--output_file=/tmp/inception_v3_inf_graph.pb
$ python export_inference_graph.py \
--alsologtostderr \
--model_name=mobilenet_v1 \
--image_size=224 \
--output_file=/tmp/mobilenet_v1_224.pb
If you then want to use the resulting model with your own or pretrained checkpoints as part of a mobile model, you can run freeze_graph to get a graph def with the variables inlined as constants using:
bazel build tensorflow/python/tools:freeze_graph
bazel-bin/tensorflow/python/tools/freeze_graph \
--input_graph=/tmp/inception_v3_inf_graph.pb \
--input_checkpoint=/tmp/checkpoints/inception_v3.ckpt \
--input_binary=true --output_graph=/tmp/frozen_inception_v3.pb \
--output_node_names=InceptionV3/Predictions/Reshape_1
The output node names will vary depending on the model, but you can inspect and estimate them using the summarize_graph tool:
bazel build tensorflow/tools/graph_transforms:summarize_graph
bazel-bin/tensorflow/tools/graph_transforms/summarize_graph \
--in_graph=/tmp/inception_v3_inf_graph.pb
To run the resulting graph in C++, you can look at the label_image sample code:
bazel build tensorflow/examples/label_image:label_image
bazel-bin/tensorflow/examples/label_image/label_image \
--image=${HOME}/Pictures/flowers.jpg \
--input_layer=input \
--output_layer=InceptionV3/Predictions/Reshape_1 \
--graph=/tmp/frozen_inception_v3.pb \
--labels=/tmp/imagenet_slim_labels.txt \
--input_mean=0 \
--input_std=255
See Model Runs out of CPU memory.
The ImageNet dataset provided has an empty background class which can be used to fine-tune the model to other tasks. If you try training or fine-tuning the VGG or ResNet models using the ImageNet dataset, you might encounter the following error:
InvalidArgumentError: Assign requires shapes of both tensors to match. lhs shape= [1001] rhs shape= [1000]
This is due to the fact that the VGG and ResNet V1 final layers have only 1000 outputs rather than 1001.
To fix this issue, you can set the --labels_offset=1 flag. This results in
the ImageNet labels being shifted down by one:
The preprocessing functions all take height and width as parameters. You
can change the default values using the following snippet:
image_preprocessing_fn = preprocessing_factory.get_preprocessing(
preprocessing_name,
height=MY_NEW_HEIGHT,
width=MY_NEW_WIDTH,
is_training=True)
此处可能存在不合适展示的内容，页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容，可点击提交进行申诉，我们将尽快为您处理。