keras_to_tensorflow
keras_to_tensorflow copied to clipboard
amir-abdi
NameError: name 'yolo_head' is not defined
I trained yolov3 on my own dataset and I got an .h5 file by using model.save() function. Now I wanna use keras_to_tensorflow.py to convert this .h5 file to .pb file, and the error occors like this:
Traceback (most recent call last):
File "C:/Users/75401/Desktop/python/keras-yolo3-master/model_data/convert.py", line 50, in
I am sure that the "yolo_head" function is right there in model.py. I got the same error even if I annotate the sentence! That's really absurd！
I trained yolov3 on my own dataset and I got an .h5 file by using model.save() function. Now I wanna use keras_to_tensorflow.py to convert this .h5 file to .pb file, and the error occors like this: Traceback (most recent call last): File "C:/Users/75401/Desktop/python/keras-yolo3-master/model_data/convert.py", line 50, in net_model = load_model(weight_file_path) File "C:\Users\75401\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\engine\saving.py", line 419, in load_model model = deserialize_model(f, custom_objects, compile) File "C:\Users\75401\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\engine\saving.py", line 225, in deserialize_model model = model_from_config(model_config, custom_objects=custom_objects) File "C:\Users\75401\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\engine\saving.py", line 458, in model_from_config return deserialize(config, custom_objects=custom_objects) File "C:\Users\75401\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\layers__init.py", line 55, in deserialize printable_module_name='layer') File "C:\Users\75401\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\utils\generic_utils.py", line 145, in deserialize_keras_object list(custom_objects.items()))) File "C:\Users\75401\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\engine\network.py", line 1032, in from_config process_node(layer, node_data) File "C:\Users\75401\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\engine\network.py", line 991, in process_node layer(unpack_singleton(input_tensors), **kwargs) File "C:\Users\75401\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\engine\base_layer.py", line 457, in call output = self.call(inputs, **kwargs) File "C:\Users\75401\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\layers\core.py", line 687, in call return self.function(inputs, **arguments) File "C:\Users\kewin\Desktop\dongxu\keras-yolo3-master\yolo3\model.py", line 375, in yolo_loss grid, raw_pred, pred_xy, pred_wh = yolo_head(yolo_outputs[l], NameError: name 'yolo_head' is not defined
I am sure that the "yolo_head" function is right there in model.py. I got the same error even if I annotate the sentence! That's really absurd！
have you solved this question?
The problem is not finding the network structure of yolov3,
Import py files with network structure
`try: from yolo3.model import yolo_body,yolo_head #######yolo3 is file ，model is py ，yolo_body is function ,this is my network structure from keras.layers import Input ＃model = keras.models.load_model（input_model_path，compile = False） model = yolo_body（Input（shape = {None，None，3）），9 // 3,10） model.load_weights（input_model_path）＃model = keras。 models.load_model（input_model_path） ------------------ 原始邮件 ------------------ 发件人: "chenyao96"<[email protected]>; 发送时间: 2020年1月17日(星期五) 下午3:28 收件人: "amir-abdi/keras_to_tensorflow"<[email protected]>; 抄送: "1342868324"<[email protected]>;"Comment"<[email protected]>; 主题: Re: [amir-abdi/keras_to_tensorflow] NameError: name 'yolo_head' is not defined (#73)
I trained yolov3 on my own dataset and I got an .h5 file by using model.save() function. Now I wanna use keras_to_tensorflow.py to convert this .h5 file to .pb file, and the error occors like this: Traceback (most recent call last): File "C:/Users/75401/Desktop/python/keras-yolo3-master/model_data/convert.py", line 50, in net_model = load_model(weight_file_path) File "C:\Users\75401\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\engine\saving.py", line 419, in load_model model = deserialize_model(f, custom_objects, compile) File "C:\Users\75401\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\engine\saving.py", line 225, in deserialize_model model = model_from_config(model_config, custom_objects=custom_objects) File "C:\Users\75401\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\engine\saving.py", line 458, in model_from_config return deserialize(config, custom_objects=custom_objects) File "C:\Users\75401\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\layers__init.py", line 55, in deserialize printable_module_name='layer') File "C:\Users\75401\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\utils\generic_utils.py", line 145, in deserialize_keras_object list(custom_objects.items()))) File "C:\Users\75401\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\engine\network.py", line 1032, in from_config process_node(layer, node_data) File "C:\Users\75401\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\engine\network.py", line 991, in process_node layer(unpack_singleton(input_tensors), **kwargs) File "C:\Users\75401\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\engine\base_layer.py", line 457, in call output = self.call(inputs, **kwargs) File "C:\Users\75401\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\layers\core.py", line 687, in call return self.function(inputs, **arguments) File "C:\Users\kewin\Desktop\dongxu\keras-yolo3-master\yolo3\model.py", line 375, in yolo_loss grid, raw_pred, pred_xy, pred_wh = yolo_head(yolo_outputs[l], NameError: name 'yolo_head' is not defined
I am sure that the "yolo_head" function is right there in model.py. I got the same error even if I annotate the sentence! That's really absurd！
have you solved this question?
— You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.
please help me to solve this problem
Using TensorFlow backend.
WARNING:tensorflow:From C:\ProgramData\Anaconda3\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.
W0311 16:36:04.171489 9120 deprecation.py:323] From C:\ProgramData\Anaconda3\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.
2020-03-11 16:36:04.228873: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
Traceback (most recent call last):
File "keras_to_tensorflow.py", line 182, in
please help "tf_model.pb", as_text=False) Traceback (most recent call last):
File "
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\models.py", line 243, in load_model model = model_from_config(model_config, custom_objects=custom_objects)
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\models.py", line 317, in model_from_config return layer_module.deserialize(config, custom_objects=custom_objects)
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\layers_init_.py", line 55, in deserialize printable_module_name='layer')
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\utils\generic_utils.py", line 143, in deserialize_keras_object list(custom_objects.items())))
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\topology.py", line 2517, in from_config process_node(layer, node_data)
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\topology.py", line 2476, in process_node layer(input_tensors, **kwargs)
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\topology.py", line 617, in call output = self.call(inputs, **kwargs)
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\layers\core.py", line 663, in call return self.function(inputs, **arguments)
File "C:\Users\a.kumar2\Desktop\TrainYourOwnYOLO-hiiiiii\TrainYourOwnYOLO\2_Training\src\keras_yolo3\yolo3\model.py", line 440, in yolo_loss grid, raw_pred, pred_xy, pred_wh = yolo_head(
NameError: name 'yolo_head' is not defined
import os
from keras import backend as K
This line must be executed before loading Keras model.
K.set_learning_phase(0)
from keras.models import load_model
model = load_model("keras_model.h5") Traceback (most recent call last):
File "
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\models.py", line 243, in load_model model = model_from_config(model_config, custom_objects=custom_objects)
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\models.py", line 317, in model_from_config return layer_module.deserialize(config, custom_objects=custom_objects)
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\layers_init_.py", line 55, in deserialize printable_module_name='layer')
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\utils\generic_utils.py", line 143, in deserialize_keras_object list(custom_objects.items())))
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\topology.py", line 2517, in from_config process_node(layer, node_data)
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\topology.py", line 2476, in process_node layer(input_tensors, **kwargs)
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\topology.py", line 617, in call output = self.call(inputs, **kwargs)
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\layers\core.py", line 663, in call return self.function(inputs, **arguments)
File "C:\Users\a.kumar2\Desktop\TrainYourOwnYOLO-hiiiiii\TrainYourOwnYOLO\2_Training\src\keras_yolo3\yolo3\model.py", line 440, in yolo_loss grid, raw_pred, pred_xy, pred_wh = yolo_head(
NameError: name 'yolo_head' is not defined
keras_to_tensorflow.py
add: from yolo3.model import yolo_head,yolo_body
around 60 lines:
def load_model(input_model_path, input_json_path=None, input_yaml_path=None):
if not Path(input_model_path).exists():
raise FileNotFoundError(
'Model file {} does not exist.'.format(input_model_path))
try:
print("input_model_path")
try:
model = keras.models.load_model(input_model_path,compile=False)
except:
model = yolo_body(Input(shape=(None, None, 3)), 3, 1)
model.load_weights("ep054-loss16.461-val_loss16.501.h5")
return model
except FileNotFoundError as err:
logging.error('Input mode file (%s) does not exist.', FLAGS.input_model)
raise err
.......
------------------ 原始邮件 ------------------ 发件人: "birth2507"<[email protected]>; 发送时间: 2020年3月11日(星期三) 晚上7:22 收件人: "amir-abdi/keras_to_tensorflow"<[email protected]>; 抄送: "1342868324"<[email protected]>; "Comment"<[email protected]>; 主题: Re: [amir-abdi/keras_to_tensorflow] NameError: name 'yolo_head' is not defined (#73)
请帮我解决这个问题
使用TensorFlow后端 警告：tensorflow：来自C：\ ProgramData \ Anaconda3 \ lib \ site-packages \ tensorflow \ python \ framework \ op_def_library.py：263：colocate_with（来自tensorflow.python.framework.ops）已被弃用，以后将被删除版。 更新说明： 托管服务器自动处理的托管。 W0311 16：36：04.171489 9120 deprecation.py:323]来自C：\ ProgramData \ Anaconda3 \ lib \ site-packages \ tensorflow \ python \ framework \ op_def_library.py：263：colocate_with（来自tensorflow.python.framework.ops）已不推荐使用，并将在以后的版本中删除。 更新说明： 托管服务器自动处理的托管。 2020-03-1116：36：04.228873：我tensorflow / core / platform / cpu_feature_guard.cc：141]您的CPU支持该TensorFlow二进制文件未编译为使用的指令：AVX2 Traceback（最近一次调用）： 文件“ keras_to_tensorflow.py”，行182，在 app.run（主） 文件“ C：\ ProgramData \ Anaconda3 \ lib \ site-packages \ absl \ app.py”中，行299，在运行 run_main（main，args） 文件“ C：\ ProgramData \ Anaconda3 \ lib \ site-packages \ absl \ app.py“，第250行，位于run_main sys.exit（main（argv）） 文件“ keras_to_tensorflow.py”，第128行，在主 模型中= load_model（FLAGS.input_model，FLAGS。 input_model_json，FLAGS.input_model_yaml） 文件“ keras_to_tensorflow.py”，第63行，在load_model中 模型= keras.models.load_model（input_model_path） 文件“ C：\ ProgramData \ Anaconda3 \ lib \ site-packages \ keras \ models.py”，第243行，在load_model中， 模型= model_from_config（model_config，custom_objects = custom_objects） 文件“ C ：\ ProgramData \ Anaconda3 \ lib \ site-packages \ keras \ models.py“，行317，在model_from_config中 返回layer_module.deserialize（config，custom_objects = custom_objects） 文件” C：\ ProgramData \ Anaconda3 \ lib \ site \ packages \ keras \ layers init .py“，反序列化 printable_module_name ='layer'中的第55行） 文件“ C：\ ProgramData \ Anaconda3 \ lib \ site-packages \ keras \ utils \ generic_utils.py”，反序列化，第143行，在deserialize_keras_object 列表中（ custom_objects.items（））） 在from_config进程节点 （层，node_data）中的 文件“ C：\ ProgramData \ Anaconda3 \ lib \ site-packages \ keras \ engine \ topology.py”，第2517行，文件“ C：\ ProgramData \ Anaconda3 \ lib \ site-packages \ keras \ engine \ topology.py”，行2476，在process_node 层（input_tensors，** kwargs）中， 文件“ C：\ ProgramData \ Anaconda3 \ lib \ site-packages \ keras \ engine \ topology.py”，行617，在呼叫 输出= self.call（输入，** kwargs） 文件“ C：\ ProgramData \ Anaconda3 \ lib \ site-packages \ keras \ layers \ core.py”，呼叫 返回self.function（输入，* *参数） 文件“ C：\ Users \ a.kumar2 \ Desktop \ TrainYourOwnYOLO-hiiiiii \ TrainYourOwnYOLO \ 2_Training \ src \ keras_yolo3 \ yolo3 \ model.py”，第440行，位于yolo_loss 网格中，raw_pred，pred_xy，pred_wh = yolo_head（ NameError：名称“ yolo_head”未定义
— 因为评论，您收到此消息。 直接回复此电子邮件，在GitHub上查看，或取消订阅。
keras_to_tensorflow.py
add: from yolo3.model import yolo_head,yolo_body
around 60 lines:
def load_model(input_model_path, input_json_path=None, input_yaml_path=None):
if not Path(input_model_path).exists():
raise FileNotFoundError(
'Model file {} does not exist.'.format(input_model_path))
try:
print("input_model_path")
try:
model = keras.models.load_model(input_model_path,compile=False)
except:
model = yolo_body(Input(shape=(None, None, 3)), 3, 1)
model.load_weights("ep054-loss16.461-val_loss16.501.h5")
return model
except FileNotFoundError as err:
logging.error('Input mode file (%s) does not exist.', FLAGS.input_model)
raise err
.......
------------------ 原始邮件 ------------------ 发件人: "Gannyn"<[email protected]>; 发送时间: 2020年2月22日(星期六) 凌晨0:55 收件人: "amir-abdi/keras_to_tensorflow"<[email protected]>; 抄送: "1342868324"<[email protected]>; "Comment"<[email protected]>; 主题: Re: [amir-abdi/keras_to_tensorflow] NameError: name 'yolo_head' is not defined (#73)
请问这个问题解决了吗？
— 因为评论，您收到此消息。 直接回复此电子邮件，在GitHub上查看，或取消订阅。
keras_to_tensorflow.py
add: from yolo3.model import yolo_head,yolo_body
around 60 lines:
def load_model(input_model_path, input_json_path=None, input_yaml_path=None):
if not Path(input_model_path).exists():
raise FileNotFoundError(
'Model file {} does not exist.'.format(input_model_path))
try:
print("input_model_path")
try:
model = keras.models.load_model(input_model_path,compile=False)
except:
model = yolo_body(Input(shape=(None, None, 3)), 3, 1)
model.load_weights("ep054-loss16.461-val_loss16.501.h5")
return model
except FileNotFoundError as err:
logging.error('Input mode file (%s) does not exist.', FLAGS.input_model)
raise err
.......
------------------ 原始邮件 ------------------ 发件人: "Gannyn"<[email protected]>; 发送时间: 2020年2月22日(星期六) 凌晨0:55 收件人: "amir-abdi/keras_to_tensorflow"<[email protected]>; 抄送: "1342868324"<[email protected]>; "Comment"<[email protected]>; 主题: Re: [amir-abdi/keras_to_tensorflow] NameError: name 'yolo_head' is not defined (#73)
请问这个问题解决了吗？
— You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.
here, yolo_head method is already defined in model.py file, still this error is coming. please help me out from this.
