alberthg / coursera-deep-learning-deeplearning.ai Goto Github PK
View Code? Open in Web Editor NEW(完结)网易云课堂微专业《深度学习工程师》听课笔记,编程作业和课后练习
Home Page: https://github.com/AlbertHG/Coursera-Deep-Learning-deeplearning.ai
License: MIT License
(完结)网易云课堂微专业《深度学习工程师》听课笔记,编程作业和课后练习
Home Page: https://github.com/AlbertHG/Coursera-Deep-Learning-deeplearning.ai
License: MIT License
在运行报错!!!
yolo_model = load_model("model_data/yolo.h5")
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-24-7a6f0063995c> in <module>()
----> 1 yolo_model = load_model("model_data/yolo.h5")
C:\ProgramData\Anaconda3\lib\site-packages\keras\models.py in load_model(filepath, custom_objects, compile)
241
242 # set weights
--> 243 topology.load_weights_from_hdf5_group(f['model_weights'], model.layers)
244
245 # Early return if compilation is not required.
C:\ProgramData\Anaconda3\lib\site-packages\keras\models.py in model_from_config(config, custom_objects)
315
316
--> 317 def model_from_yaml(yaml_string, custom_objects=None):
318 """Parses a yaml model configuration file and returns a model instance.
319
C:\ProgramData\Anaconda3\lib\site-packages\keras\layers\__init__.py in deserialize(config, custom_objects)
53 module_objects=globs,
54 custom_objects=custom_objects,
---> 55 printable_module_name='layer')
C:\ProgramData\Anaconda3\lib\site-packages\keras\utils\generic_utils.py in deserialize_keras_object(identifier, module_objects, custom_objects, printable_module_name)
142 return cls.from_config(config['config'])
143 else:
--> 144 # Then `cls` may be a function returning a class.
145 # in this case by convention `config` holds
146 # the kwargs of the function.
C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\topology.py in from_config(cls, config, custom_objects)
2518
2519 def save(self, filepath, overwrite=True, include_optimizer=True):
-> 2520 """Save the model to a single HDF5 file.
2521
2522 The savefile includes:
C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\topology.py in process_node(layer, node_data)
2475 layer = deserialize_layer(layer_data,
2476 custom_objects=custom_objects)
-> 2477 created_layers[layer_name] = layer
2478
2479 # Gather layer inputs.
C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\topology.py in __call__(self, inputs, **kwargs)
615 if len(output_ls_copy) == 1:
616 output = output_ls_copy[0]
--> 617 else:
618 output = output_ls_copy
619
C:\ProgramData\Anaconda3\lib\site-packages\keras\layers\advanced_activations.py in call(self, inputs)
44 config = {'alpha': float(self.alpha)}
45 base_config = super(LeakyReLU, self).get_config()
---> 46 return dict(list(base_config.items()) + list(config.items()))
47
48
C:\ProgramData\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py in relu(x, alpha, max_value)
2916
2917 output_shape = output.get_shape()
-> 2918 targets = cast(flatten(target), 'int64')
2919 logits = tf.reshape(output, [-1, int(output_shape[-1])])
2920 res = tf.nn.sparse_softmax_cross_entropy_with_logits(
AttributeError: module 'tensorflow.python.ops.nn' has no attribute 'leaky_relu'
01-Neural Networks and Deep Learning/week4/answer-Building your Deep Neural Network-Step by Step.ipynb
函数 L_model_backward 中有一段for循环
for l in reversed(range(L-1)):
current_cache = caches[L - 2 - l]
dA_prev_temp, dW_temp, db_temp = linear_activation_backward(grads["dA" + str(L)], current_cache, activation = 'relu')
我感觉有点问题。
我的答案是
for l in reversed(range(L - 1)):
current_cache = caches[l]
dA_prev_temp, dW_temp, db_temp = linear_activation_backward(grads["dA" + str(l + 2)], current_cache, "relu")
你认为呢?
raw_code = codecs.decode(code.encode('ascii'), 'base64')
UnicodeEncodeError: 'ascii' codec can't encode character '\xe3' in position 0: ordinal not in range(128)
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.