Comments (5)
Can you try to give me a script to reproduce the issue? It can be very difficult to pinpoint the cause of the bug otherwise.
from heatmaps.
I've used my model like this:
json_file = open(
'/home/hashed/PoshaQ/testing/heatmap/neck_model_version1_convo2D_Nor_PReLU_do.json', 'r')
loaded_model_json = json_file.read()
json_file.close()
loaded_model = model_from_json(loaded_model_json)
loaded_model.load_weights("/home/hashed/PoshaQ/testing/heatmap/Neck_96_96_version1_conv2D_Nor_PReLU_do.h5")
print("Loaded model from disk")
new_model = to_heatmap(loaded_model)
idx = 0
display_heatmap(new_model, "/home/hashed/PoshaQ/testing/wrong_cropped/3146.jpg", idx)
`
And the model architecture looks like this
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) (None, 96, 96, 1) 0
_________________________________________________________________
conv2D_1 (Conv2D) (None, 96, 96, 32) 832
_________________________________________________________________
bn_conv1 (BatchNormalization (None, 96, 96, 32) 128
_________________________________________________________________
p_re_lu_1 (PReLU) (None, 96, 96, 32) 294912
_________________________________________________________________
conv2D_2 (Conv2D) (None, 96, 96, 32) 9248
_________________________________________________________________
bn_conv2 (BatchNormalization (None, 96, 96, 32) 128
_________________________________________________________________
p_re_lu_2 (PReLU) (None, 96, 96, 32) 294912
_________________________________________________________________
max_pool1 (MaxPooling2D) (None, 48, 48, 32) 0
_________________________________________________________________
conv2D_3 (Conv2D) (None, 48, 48, 64) 18496
_________________________________________________________________
bn_conv3 (BatchNormalization (None, 48, 48, 64) 256
_________________________________________________________________
p_re_lu_3 (PReLU) (None, 48, 48, 64) 147456
_________________________________________________________________
flatten_1 (Flatten) (None, 147456) 0
_________________________________________________________________
dense_1 (Dense) (None, 512) 75497984
_________________________________________________________________
p_re_lu_4 (PReLU) (None, 512) 512
_________________________________________________________________
dropout_1 (Dropout) (None, 512) 0
_________________________________________________________________
dense_2 (Dense) (None, 9) 4617
=================================================================
Total params: 76,269,481
Trainable params: 76,269,225
Non-trainable params: 256
_________________________________________________________________
from heatmaps.
Thanks! I'll look it up once I have more time. In the meantime, can you also give me the version of keras that you are using?
from heatmaps.
the version is 2.2.2
thanks
from heatmaps.
I will need the script which you used to create the model (I don't need to train it) it's just painful to re implement it just from the summary which you are providing. Could you copy past it there? Thank you.
from heatmaps.
Related Issues (15)
- regarding using a dataset of different domain HOT 6
- AttributeError: 'Model' object has no attribute 'name' HOT 5
- Error using own Model with non-quadratic images HOT 3
- can it be used to grey-level imageset network? HOT 2
- to_heatmap function error HOT 2
- KeyError: 'Strides' With Custom Model HOT 1
- Example not working: NameError: name 'preprocess_input' is not defined HOT 5
- regarding re-train the VGG19 model HOT 5
- Update to Keras 2 HOT 4
- Usign the code on your own model HOT 32
- sigmoid outputs? HOT 2
- MemoryError on Raspberry Pi HOT 17
- Issues with target size HOT 5
- why must you replace softmax by softmax4D HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from heatmaps.