wusaifei / garbage_classify Goto Github PK

想问一下大佬，你这个实验结果的准确率是验证集上的还是测试集上的，你测试集用完一次就不用了吗

Traceback (most recent call last):
File "/tmp/pycharm_project_329/run.py", line 166, in
tf.compat.v1.app.run()
File "/home/jx/.local/lib/python3.5/site-packages/tensorflow/python/platform/app.py", line 40, in run
_run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
File "/home/jx/.local/lib/python3.5/site-packages/absl/app.py", line 299, in run
_run_main(main, args)
File "/home/jx/.local/lib/python3.5/site-packages/absl/app.py", line 250, in _run_main
sys.exit(main(argv))
File "/tmp/pycharm_project_329/run.py", line 122, in main
check_args(FLAGS)
File "/tmp/pycharm_project_329/run.py", line 61, in check_args
raise Exception('FLAGS.num_classes error, '
Exception: FLAGS.num_classes error, should be a positive number associated with your classification task

您帮我看一下，主要我用的是别人服务器的环境，tensflow是1.14，numpy是1.14.5，python是3.5，我怕新建个环境还得重新安装包，或者会出现缺少各种的麻烦。谢谢

我在运行时出现了File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5f.pyx", line 78, in h5py.h5f.open
OSError: Unable to open file (file signature not found)
请问该如何解决这个问题呢

你好作者，我按照你的要求安装了所有的环境 但是训练的时候找不到指定模块是怎么回事
“
Traceback (most recent call last):
File "run.py", line 17, in
import tensorflow as tf
File "C:\ProgramData\Anaconda3\envs\tf_1_13_1\lib\site-packages\tensorflow_init_.py", line 24, in
from tensorflow.python import pywrap_tensorflow # pylint: disable=unused-import
File "C:\ProgramData\Anaconda3\envs\tf_1_13_1\lib\site-packages\tensorflow\python_init_.py", line 49, in
from tensorflow.python import pywrap_tensorflow
File "C:\ProgramData\Anaconda3\envs\tf_1_13_1\lib\site-packages\tensorflow\python\pywrap_tensorflow.py", line 74, in
raise ImportError(msg)
ImportError: Traceback (most recent call last):
File "C:\ProgramData\Anaconda3\envs\tf_1_13_1\lib\site-packages\tensorflow\python\pywrap_tensorflow.py", line 58, in
from tensorflow.python.pywrap_tensorflow_internal import *
File "C:\ProgramData\Anaconda3\envs\tf_1_13_1\lib\site-packages\tensorflow\python\pywrap_tensorflow_internal.py", line 28, in
_pywrap_tensorflow_internal = swig_import_helper()
File "C:\ProgramData\Anaconda3\envs\tf_1_13_1\lib\site-packages\tensorflow\python\pywrap_tensorflow_internal.py", line 24, in swig_import_helper
_mod = imp.load_module('_pywrap_tensorflow_internal', fp, pathname, description)
File "C:\ProgramData\Anaconda3\envs\tf_1_13_1\lib\imp.py", line 243, in load_module
return load_dynamic(name, filename, file)
File "C:\ProgramData\Anaconda3\envs\tf_1_13_1\lib\imp.py", line 343, in load_dynamic
return _load(spec)
ImportError: DLL load failed: 找不到指定的模块。
”

另外我想问一下 这个训练里面的“--train_url='./model_snapshots‘’”是什么意思 没找到这个文件夹

我是新手小白，不太懂这里边的道理。
是不是说先用efficientnet提取特征，然后用SVM代替原来的Linear进行分类分类？这样子的精度会提高多少？

你好，我按照你的步骤运行python run.py --data_url='../datasets/garbage_classify/train_data' --train_url='./model_snapshots' --deploy_script_path='./deploy_scripts'，已经cd到run.py的目录，运行结果提示：
File "run.py", line 68, in check_args
raise Exception('FLAGS.data_url: %s is not exist' % FLAGS.data_url)
Exception: FLAGS.data_url: './garbage_classify/train_data' is not exist
可是这个训练集是在这个目录，请问要怎么解决

使用的是Xception模型，训练10轮acc没改变。请教一下博主 @saifeiwu

你好 可以说一下运行的环境吗

请问一下大佬，你这个准确率是整个数据集识别正确的除以整个数据集的数量，还是40个小类识别准确率的平均值啊

在训练了1个epoch后，开始回调时出现了下面这个报错信息：

Traceback (most recent call last):
File "run.py", line 166, in
tf.app.run()
File "e:\Anaconda3\lib\site-packages\tensorflow\python\platform\app.py", line 125, in run
_sys.exit(main(argv))
File "run.py", line 157, in main
train_model(FLAGS)
File "D:\garbage_classification\garbage_classify-master\train.py", line 134, in train_model
shuffle=False
File "e:\Anaconda3\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "e:\Anaconda3\lib\site-packages\keras\engine\training.py", line 1732, in fit_generator
initial_epoch=initial_epoch)
File "e:\Anaconda3\lib\site-packages\keras\engine\training_generator.py", line 242, in fit_generator
workers=0)
File "e:\Anaconda3\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "e:\Anaconda3\lib\site-packages\keras\engine\training.py", line 1791, in evaluate_generator
verbose=verbose)
File "e:\Anaconda3\lib\site-packages\keras\engine\training_generator.py", line 341, in evaluate_generator
callbacks._call_begin_hook('test')
File "e:\Anaconda3\lib\site-packages\keras\callbacks\callbacks.py", line 105, in _call_begin_hook
self.on_test_begin()
File "e:\Anaconda3\lib\site-packages\keras\callbacks\callbacks.py", line 239, in on_test_begin
callback.on_test_begin(logs)
AttributeError: 'WarmUpCosineDecayScheduler' object has no attribute 'on_test_begin'

我的运行环境和作者的是一样的，用笔记本跑的代码，所以把调用GPU的代码注释了
报错信息上说WarmUpCosineDecayScheduler这个类缺少on_test_begin，我看了一下作者重写的这个回调类里确实没有，但是我单独运行这个类检查是没问题的，不知道该怎么改，求解答，非常感谢！

`(tfenv) D:\DeepLearnning\Code\RubbishSort\garbage_classify-master>python run.py --mode=eval --eval_pb_path=./model_snapshots/model --test_data_url=./datasets/garbage_classify/tr
ain_data --num_classes=40
Using TensorFlow backend.
2020-03-12 10:09:15.415268: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
2020-03-12 10:09:16.536963: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1433] Found device 0 with properties:
name: GeForce MX250 major: 6 minor: 1 memoryClockRate(GHz): 1.582
pciBusID: 0000:06:00.0
totalMemory: 2.00GiB freeMemory: 1.62GiB
2020-03-12 10:09:16.571051: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1512] Adding visible gpu devices: 0
2020-03-12 10:09:25.865212: I tensorflow/core/common_runtime/gpu/gpu_device.cc:984] Device interconnect StreamExecutor with strength 1 edge matrix:
2020-03-12 10:09:25.879351: I tensorflow/core/common_runtime/gpu/gpu_device.cc:990] 0
2020-03-12 10:09:25.885838: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1003] 0: N
2020-03-12 10:09:25.956745: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 1364 MB memory)
-> physical GPU (device: 0, name: GeForce MX250, pci bus id: 0000:06:00.0, compute capability: 6.1)
WARNING:tensorflow:From D:\DeepLearnning\Code\RubbishSort\garbage_classify-master\eval.py:131: load (from tensorflow.python.saved_model.loader_impl) is deprecated and will be re
moved in a future version.
Instructions for updating:
This function will only be available through the v1 compatibility library as tf.compat.v1.saved_model.loader.load or tf.compat.v1.saved_model.load. There will be a new function
for importing SavedModels in Tensorflow 2.0.
WARNING:tensorflow:From D:\DeepLearnning\anaconda3\envs\tfenv\lib\site-packages\tensorflow\python\training\saver.py:1266: checkpoint_exists (from tensorflow.python.training.chec
kpoint_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.
2020-03-12 10:09:38.781264: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1512] Adding visible gpu devices: 0
2020-03-12 10:09:38.846031: I tensorflow/core/common_runtime/gpu/gpu_device.cc:984] Device interconnect StreamExecutor with strength 1 edge matrix:
2020-03-12 10:09:38.874307: I tensorflow/core/common_runtime/gpu/gpu_device.cc:990] 0
2020-03-12 10:09:38.876455: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1003] 0: N
2020-03-12 10:09:38.889822: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 1364 MB memory)
-> physical GPU (device: 0, name: GeForce MX250, pci bus id: 0000:06:00.0, compute capability: 6.1)
Traceback (most recent call last):
File "D:\DeepLearnning\anaconda3\envs\tfenv\lib\site-packages\tensorflow\python\client\session.py", line 1092, in _run
subfeed, allow_tensor=True, allow_operation=False)
File "D:\DeepLearnning\anaconda3\envs\tfenv\lib\site-packages\tensorflow\python\framework\ops.py", line 3478, in as_graph_element
return self._as_graph_element_locked(obj, allow_tensor, allow_operation)
File "D:\DeepLearnning\anaconda3\envs\tfenv\lib\site-packages\tensorflow\python\framework\ops.py", line 3557, in _as_graph_element_locked
raise ValueError("Tensor %s is not an element of this graph." % obj)
ValueError: Tensor Tensor("input_1:0", shape=(?, 456, 456, 3), dtype=float32) is not an element of this graph.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "run.py", line 169, in
tf.app.run()
File "D:\DeepLearnning\anaconda3\envs\tfenv\lib\site-packages\tensorflow\python\platform\app.py", line 125, in run
_sys.exit(main(argv))
File "run.py", line 165, in main
eval_model(FLAGS)
File "D:\DeepLearnning\Code\RubbishSort\garbage_classify-master\eval.py", line 215, in eval_model
test_single_model(FLAGS)
File "D:\DeepLearnning\Code\RubbishSort\garbage_classify-master\eval.py", line 159, in test_single_model
pred_score = sess1.run([output_score], feed_dict={input_images: img})
File "D:\DeepLearnning\anaconda3\envs\tfenv\lib\site-packages\tensorflow\python\client\session.py", line 929, in run
run_metadata_ptr)
File "D:\DeepLearnning\anaconda3\envs\tfenv\lib\site-packages\tensorflow\python\client\session.py", line 1095, in _run
'Cannot interpret feed_dict key as Tensor: ' + e.args[0])
TypeError: Cannot interpret feed_dict key as Tensor: Tensor Tensor("input_1:0", shape=(?, 456, 456, 3), dtype=float32) is not an element of this graph.
`
我在--mode=eval估值的时候遇到了这个问题，请教博主！

楼主你好
我这边发现用阿里云服务器 nvidia的P100 16G显存的话batch size貌似8都不行，只能到6， Ubuntu的系统，你做training的时候用的啥系统，啥配置？

另外关于数据增强的部分是不是只再training的时候才用到，还是做最后模型检测的时候，也像数据归一化一样可以使用。

ValueError: Error when checking input: expected conv2d_1_input to have 4 dimensions, but got array with shape (16, 1)

我看了run.py的freeze_weight_path那段代码，没明白这段代码的意思
if not os.path.exists(FLAGS.freeze_weights_file_path):
raise Exception('FLAGS.freeze_weights_file_path: %s is not exist' %
FLAGS.freeze_weights_file_path)
if os.path.isdir(FLAGS.freeze_weights_file_path):
raise Exception('FLAGS.freeze_weights_file_path must be a file path, not a directory, %s ' %
FLAGS.freeze_weights_file_path)
if os.path.exists(FLAGS.freeze_weights_file_path.rsplit('/', 1)[0] + '/model'):
raise Exception('a model directory is already exist in ' +
FLAGS.freeze_weights_file_path.rsplit('/', 1)[0]
+ ', please rename or remove the model directory ')

Using TensorFlow backend.
2020-03-23 14:30:41.084890: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2020-03-23 14:30:44.398776: I tensorflow/compiler/xla/service/service.cc:150] XLA service 0x5638b17ca080 executing computations on platform CUDA. Devices:
2020-03-23 14:30:44.398829: I tensorflow/compiler/xla/service/service.cc:158] StreamExecutor device (0): GeForce RTX 2080 Ti, Compute Capability 7.5
2020-03-23 14:30:44.398840: I tensorflow/compiler/xla/service/service.cc:158] StreamExecutor device (1): GeForce RTX 2080 Ti, Compute Capability 7.5
2020-03-23 14:30:44.405480: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2499995000 Hz
2020-03-23 14:30:44.408096: I tensorflow/compiler/xla/service/service.cc:150] XLA service 0x5638b193fdc0 executing computations on platform Host. Devices:
2020-03-23 14:30:44.408128: I tensorflow/compiler/xla/service/service.cc:158] StreamExecutor device (0): ,
2020-03-23 14:30:44.408312: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1433] Found device 0 with properties:
name: GeForce RTX 2080 Ti major: 7 minor: 5 memoryClockRate(GHz): 1.545
pciBusID: 0000:01:00.0
totalMemory: 10.76GiB freeMemory: 10.60GiB
2020-03-23 14:30:44.408403: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1433] Found device 1 with properties:
name: GeForce RTX 2080 Ti major: 7 minor: 5 memoryClockRate(GHz): 1.545
pciBusID: 0000:02:00.0
totalMemory: 10.76GiB freeMemory: 10.60GiB
2020-03-23 14:30:44.408541: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1512] Adding visible gpu devices: 0, 1
2020-03-23 14:30:44.411191: I tensorflow/core/common_runtime/gpu/gpu_device.cc:984] Device interconnect StreamExecutor with strength 1 edge matrix:
2020-03-23 14:30:44.411219: I tensorflow/core/common_runtime/gpu/gpu_device.cc:990] 0 1
2020-03-23 14:30:44.411233: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1003] 0: N N
2020-03-23 14:30:44.411244: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1003] 1: N N
2020-03-23 14:30:44.411375: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10312 MB memory) -> physical GPU (device: 0, name: GeForce RTX 2080 Ti, pci bus id: 0000:01:00.0, compute capability: 7.5)
2020-03-23 14:30:44.411927: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:1 with 10312 MB memory) -> physical GPU (device: 1, name: GeForce RTX 2080 Ti, pci bus id: 0000:02:00.0, compute capability: 7.5)
WARNING:tensorflow:From /opt/shakey/imageclass/garbage_classify-master/eval.py:134: load (from tensorflow.python.saved_model.loader_impl) is deprecated and will be removed in a future version.
Instructions for updating:
This function will only be available through the v1 compatibility library as tf.compat.v1.saved_model.loader.load or tf.compat.v1.saved_model.load. There will be a new function for importing SavedModels in Tensorflow 2.0.
WARNING:tensorflow:From /opt/shakey/.local/lib/python3.6/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.
2020-03-23 14:31:22.029904: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1512] Adding visible gpu devices: 0, 1
2020-03-23 14:31:22.030413: I tensorflow/core/common_runtime/gpu/gpu_device.cc:984] Device interconnect StreamExecutor with strength 1 edge matrix:
2020-03-23 14:31:22.030436: I tensorflow/core/common_runtime/gpu/gpu_device.cc:990] 0 1
2020-03-23 14:31:22.030449: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1003] 0: N N
2020-03-23 14:31:22.030459: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1003] 1: N N
2020-03-23 14:31:22.030628: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10312 MB memory) -> physical GPU (device: 0, name: GeForce RTX 2080 Ti, pci bus id: 0000:01:00.0, compute capability: 7.5)
2020-03-23 14:31:22.030908: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:1 with 10312 MB memory) -> physical GPU (device: 1, name: GeForce RTX 2080 Ti, pci bus id: 0000:02:00.0, compute capability: 7.5)
Traceback (most recent call last):
File "/opt/shakey/.local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1092, in _run
subfeed, allow_tensor=True, allow_operation=False)
File "/opt/shakey/.local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3478, in as_graph_element
return self._as_graph_element_locked(obj, allow_tensor, allow_operation)
File "/opt/shakey/.local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3557, in _as_graph_element_locked
raise ValueError("Tensor %s is not an element of this graph." % obj)
ValueError: Tensor Tensor("input_1:0", shape=(?, 456, 456, 3), dtype=float32) is not an element of this graph.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "run.py", line 168, in
tf.app.run()
File "/opt/shakey/.local/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 125, in run
_sys.exit(main(argv))
File "run.py", line 165, in main
eval_model(FLAGS)
File "/opt/shakey/imageclass/garbage_classify-master/eval.py", line 218, in eval_model
test_single_model(FLAGS)
File "/opt/shakey/imageclass/garbage_classify-master/eval.py", line 162, in test_single_model
pred_score = sess1.run([output_score], feed_dict={input_images: img})
File "/opt/shakey/.local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 929, in run
run_metadata_ptr)
File "/opt/shakey/.local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1095, in _run
'Cannot interpret feed_dict key as Tensor: ' + e.args[0])
TypeError: Cannot interpret feed_dict key as Tensor: Tensor Tensor("input_1:0", shape=(?, 456, 456, 3), dtype=float32) is not an element of this graph.

请问楼主大神，mean_std.py最后执行的结果也没有保存，那它对最后识别的准确率有什么影响，没看懂mean_std.py是干什么的，望您解答，谢谢您！

作者您好！华为云官网比赛结束后没有公布测试集。我训练了一下官方给的baseline代码（src_v2.zip的代码），数据集用的是garbage_classify_v2.zip, Baseline只训练了5个epoch，训练集：验证集=0.75:0.25，结果train_acc到了99%，val_acc到了98.5%，我不知道这个是什么原因，想请教一下您！

用链接里的数据集训练，30epoch为0.825的准确率，并没有这么高，batch由于内存限制设置的4，其他都没改动，能帮忙找一下原因嘛？

作者您好 我在本地运行您的run.py文件，用的efficentnet-b5_notop.h5权重文件，input_size=228(没有用456，GPU原因)，batch_size=8，epoch=30 但是loss下降的很慢，训练集acc能到0.95，但是测试集acc基本在70%左右不怎么变化 请问下是什么原因呢

你好，数据增强不是通过旋转平移等操作来增加原本的数据集吗，我看到aug.py和data_gen.py里面虽然进行了数据增强，但是是直接替换了原始读取的图片，数据集的总量还是没有变的，对这里有点疑惑？

运行mean_std.py报错
Traceback (most recent call last):
File "D:/PycharmProjects/garbage_classify-master/mean_std.py", line 31, in
means[i] += img[:, :, i].mean()
IndexError: invalid index to scalar variable.

AttributeError: 'BaseSequence' object has no attribute 'shape'
这个类有问题？

Fatal Python error: Segmentation fault

Thread 0x00007f9b32efe700 (most recent call first):

'Cannot interpret feed_dict key as Tensor: ' + e.args[0])
TypeError: Cannot interpret feed_dict key as Tensor: Tensor Tensor("input_1:0", shape=(?, 456, 456, 3), dtype=float32) is not an element of this graph.
这个问题怎么解决啊，望大佬赐教

File "run.py", line 160, in main
from train import train_model
File "G:\garbage_classify-master\train.py", line 6, in
import keras.backend
ModuleNotFoundError: No module named 'keras'

你们有遇到过这种情况吗，keras我确认是安装了的。

组归一化（GroupNormalization）代替批量归一化，会影响预训练权值吗

以下是多gpu并行训练的loss：

在第一个epoch的时候loss 和对应的 acc是正常的，到第二个epoch有问题，怀疑是合并参数的时候有问题？？

作者你好customize_service这个文件的一个库 from model_service.tfserving_model_service import TfServingBaseService 在你的源码中没有，请问这是你自己定义的么，在你的源码项目中没有这个

@saifeiwu 博主，请问你还有efficientnet-b5_notop.h5权重吗？我下载了好几天也没成功。

楼主，请问你还有这个.h5权重吗？我下载了几天也没下载下来，需要你的帮助，谢谢！QQ598770323

总共10类，每类几百张照片，val accuracy 在第三轮就达到了1.0，之后一直不变。test accuracy 在前几轮不断上升，上升到第8轮为0.69，之后不断震荡、下降，50轮时，test accuracy 为0.3。loss下降缓慢，到第10轮之后下降的特别特别慢，几乎保持不变。请问楼主，这是什么原因。

您好，在代码中有很多,h5文件，是所有的.h5文件都要下载吗？谢谢您

还有这个地方怎么处理？需要下载吗。谢谢您

BASE_WEIGHTS_PATH = (
'https://github.com/Callidior/keras-applications/'
'releases/download/efficientnet/')

WEIGHTS_HASHES = {
'efficientnet-b0': ('163292582f1c6eaca8e7dc7b51b01c61'
'5b0dbc0039699b4dcd0b975cc21533dc',
'c1421ad80a9fc67c2cc4000f666aa507'
'89ce39eedb4e06d531b0c593890ccff3'),
'efficientnet-b1': ('d0a71ddf51ef7a0ca425bab32b7fa7f1'
'6043ee598ecee73fc674d9560c8f09b0',
'75de265d03ac52fa74f2f510455ba64f'
'9c7c5fd96dc923cd4bfefa3d680c4b68'),
'efficientnet-b2': ('bb5451507a6418a574534aa76a91b106'
'f6b605f3b5dde0b21055694319853086',
'433b60584fafba1ea3de07443b74cfd3'
'2ce004a012020b07ef69e22ba8669333'),

在window下运行的，运行run.py文件，错误为：OSError: Unable to open file (unable to open file: name = '/home/work/user-job-dir/src/efficientnet-b5_notop.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)
找不到这个文件，求解答

你好，我把model_fn改成了自己的模型，但是训练了一个epoch之后报这个错误：
Traceback (most recent call last):
File "run.py", line 154, in
tf.app.run()
File "/home/dell/anaconda3/envs/tensorflow-1.14-python-3.6/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 40, in run
_run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
File "/home/dell/anaconda3/envs/tensorflow-1.14-python-3.6/lib/python3.6/site-packages/absl/app.py", line 299, in run
_run_main(main, args)
File "/home/dell/anaconda3/envs/tensorflow-1.14-python-3.6/lib/python3.6/site-packages/absl/app.py", line 250, in _run_main
sys.exit(main(argv))
File "run.py", line 145, in main
train_model(FLAGS)
File "/data2/hlf/garbage_classify/train.py", line 277, in train_model
File "/home/dell/anaconda3/envs/tensorflow-1.14-python-3.6/lib/python3.6/site-packages/keras/legacy/interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "/home/dell/anaconda3/envs/tensorflow-1.14-python-3.6/lib/python3.6/site-packages/keras/engine/training.py", line 1732, in fit_generator
initial_epoch=initial_epoch)
File "/home/dell/anaconda3/envs/tensorflow-1.14-python-3.6/lib/python3.6/site-packages/keras/engine/training_generator.py", line 260, in fit_generator
callbacks.on_epoch_end(epoch, epoch_logs)
File "/home/dell/anaconda3/envs/tensorflow-1.14-python-3.6/lib/python3.6/site-packages/keras/callbacks/callbacks.py", line 152, in on_epoch_end
callback.on_epoch_end(epoch, logs)
File "/data2/hlf/garbage_classify/train.py", line 210, in on_epoch_end
TypeError: must be real number, not NoneType
不知道是什么问题呢？想请教一下的！！！

def on_epoch_end(self, epoch, logs={}):
self.losses.append(logs.get('loss'))
self.val_losses.append(logs.get('val_loss'))
save_path = os.path.join(self.FLAGS.train_local, 'weights_%03d_%.4f.h5' % (epoch,logs.get('val_acc'))) # 210行
self.model.save_weights(save_path)
if self.FLAGS.train_url.startswith('s3://'):
save_url = os.path.join(self.FLAGS.train_url, 'weights_%03d_%.4f.h5' % (epoch, logs.get('val_acc')))
shutil.copyfile(save_path, save_url)
print('save weights file', save_path)
if self.FLAGS.keep_weights_file_num > -1:
weights_files = glob(os.path.join(self.FLAGS.train_local, '*.h5'))
if len(weights_files) >= self.FLAGS.keep_weights_file_num:
weights_files.sort(key=lambda file_name: os.stat(file_name).st_ctime, reverse=True)

1

2020-03-10 10:37:34.998582: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1003] 1: N N
2020-03-10 10:37:34.998708: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10312 MB memory) -> physical GPU (device: 0, name: GeForce RTX 2080 Ti, pci bus id: 0000:01:00.0, compute capability: 7.5)
2020-03-10 10:37:34.998966: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:1 with 10312 MB memory) -> physical GPU (device: 1, name: GeForce RTX 2080 Ti, pci bus id: 0000:02:00.0, compute capability: 7.5)
Traceback (most recent call last):
File "/opt/shakey/.local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1092, in _run
subfeed, allow_tensor=True, allow_operation=False)
File "/opt/shakey/.local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3478, in as_graph_element
return self._as_graph_element_locked(obj, allow_tensor, allow_operation)
File "/opt/shakey/.local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3557, in _as_graph_element_locked
raise ValueError("Tensor %s is not an element of this graph." % obj)
ValueError: Tensor Tensor("input_1:0", shape=(?, 456, 456, 3), dtype=float32) is not an element of this graph.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "run.py", line 166, in
tf.app.run()
File "/opt/shakey/.local/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 125, in run
_sys.exit(main(argv))
File "run.py", line 163, in main
eval_model(FLAGS)
File "/opt/shakey/imageclass/garbage_classify-master/eval.py", line 215, in eval_model
test_single_model(FLAGS)
File "/opt/shakey/imageclass/garbage_classify-master/eval.py", line 159, in test_single_model
pred_score = sess1.run([output_score], feed_dict={input_images: img})
File "/opt/shakey/.local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 929, in run
run_metadata_ptr)
File "/opt/shakey/.local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1095, in _run
'Cannot interpret feed_dict key as Tensor: ' + e.args[0])
TypeError: Cannot interpret feed_dict key as Tensor: Tensor Tensor("input_1:0", shape=(?, 456, 456, 3), dtype=float32) is not an element of this graph.

我的是笔记本，显卡1050，运行时候出现ImportError: DLL load failed: 页面文件太小，无法完成操作。是带不动问题吗

我也存在这样的问题，请问你解决了吗

Originally posted by @LwXxz in #32 (comment)

from moxing.framework import file

ModuleNotFoundError: No module named 'moxing'

这个moxing是指哪个啊？

作者好，我是一个小白。环境已配好，但项目跑不起来，训练时报错，详情如下图。望指教，非常感谢。

楼主你好：
我这边在本地跑测试1080t batch size设置为4 因为mem不够 size还是456没有减少，这个运行结果可能还有其他影响因素么？
另外这个batch size的设置是最优设置是16么？ 理论依据楼主能麻烦贴个链接么？
多谢