Comments (4)
Check the variable type that is going in preprocess_input
. It should be a numpy array of rank 3 or 4. You can try this:
print(type(img))
print(img.dim)
from efficientnet.
HI @shubhaminnani
Code have been tested with
- tf 1.14 (cpu) + keras 2.2.4
- tf.keras 1.14 (cpu)
- tf 1.12 (gpu) + keras 2.2.4
What kind of error do you have? Could you provide a traceback?
from efficientnet.
Not in efficientnet but while training the code.
from efficientnet.
img = preprocess_input(img)
File "/home/gpu3/anaconda3/envs/shubham/lib/python3.6/site-packages/efficientnet/preprocessing.py", line 56, in preprocess_input
assert x.ndim in (3, 4)
AttributeError: 'Tensor' object has no attribute 'ndim'
from efficientnet.
Related Issues (20)
- The drop connect rate (aka survival rate) is incorrect HOT 2
- Top 1 AND Top 5 ACCURACIES
- ValueError: Unknown layer: FixedDropout HOT 6
- Depthwise separable convolution for _expand_conv
- if _IMAGENET_MEAN is None:
- ValueError: Layer #0 (named "efficientnetb0" in the current model) was found to correspond to layer efficientnet-b0 in the save file. However the new layer efficientnetb0 expects 312 weights, but the saved weights have 309 elements. HOT 1
- How to take multiple output from pretrained network
- ValueError: rate must be a scalar tensor or a float in the range [0, 1), got 1 HOT 1
- how can i change backbone from resnet to efficientnet HOT 6
- Some question about the grid search
- Invalid argument: Incompatible shapes: [131072] vs. [262144] HOT 1
- The input must have 3 channels, I need 1 channel HOT 2
- I have malimg dataset and i want to apply EfficientNet model, can u help to do that ? be
- Efficientnet model not saving completely after training
- ModuleNotFoundError: No module named 'keras_applications' HOT 2
- Difference of EfficientNetB0 between this model and Official Tensorflow
- Bad prediction result using EfficientNet
- Remove `FixedDropout`
- Pickling errors for `preprocess_input` due to `functools.wraps`
- How to create a new network that has the same backbone but two detection heads: one with the imagenet weights and the second head with the new custom classes. I want to predict both imagenet and custom classes with the model
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 efficientnet.