keras-flops
FLOPs calculator for neural network architecture written in tensorflow (tf.keras) v2.2+
This stands on the shoulders of giants, tf.profiler.
Requirements
- Python 3.6+
- Tensorflow 2.2+
Installation
Using pip:
pip install keras-flops
Example
See colab examples here in details.
from tensorflow.keras import Model, Input
from tensorflow.keras.layers import Dense, Flatten, Conv2D, MaxPooling2D, Dropout
from keras_flops import get_flops
# build model
inp = Input((32, 32, 3))
x = Conv2D(32, kernel_size=(3, 3), activation="relu")(inp)
x = Conv2D(64, (3, 3), activation="relu")(x)
x = MaxPooling2D(pool_size=(2, 2))(x)
x = Dropout(0.25)(x)
x = Flatten()(x)
x = Dense(128, activation="relu")(x)
x = Dropout(0.5)(x)
out = Dense(10, activation="softmax")(x)
model = Model(inp, out)
# Calculae FLOPS
flops = get_flops(model, batch_size=1)
print(f"FLOPS: {flops / 10 ** 9:.03} G")
# >>> FLOPS: 0.0338 G
Support
Support tf.keras.layers as follows,
| name | layer |
|---|---|
| Conv | Conv[1D/2D/3D] |
| Conv[1D/2D]Transpose | |
| DepthwiseConv2D | |
| SeparableConv[1D/2D] | |
| Pooling | AveragePooling[1D/2D] |
| GlobalAveragePooling[1D/2D/3D] | |
| MaxPooling[1D/2D] | |
| GlobalMaxPool[1D/2D/3D] | |
| Normalization | BatchNormalization |
| Activation | Softmax |
| Attention | Attention |
| AdditiveAttention | |
| others | Dense |
Not supported
Not support tf.keras.layers as follows. They are calculated as zero or smaller value than correct value.
| name | layer |
|---|---|
| Conv | Conv3DTranspose |
| Pooling | AveragePooling3D |
| MaxPooling3D | |
| UpSampling[1D/2D/3D] | |
| Normalization | LayerNormalization |
| RNN | SimpleRNN |
| LSTM | |
| GRU | |
| others | Embedding |
Metadata
Release files for keras-flops 0.1.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| keras-flops-0.1.2.tar.gz | 4.4 kB | Without provenance | Details for keras-flops-0.1.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| keras_flops-0.1.2-py3-none-any.whl | Python 3 | none | any | Details for keras_flops-0.1.2-py3-none-any.whl |
Total release size: 9.6 kB
Release files / keras-flops-0.1.2.tar.gz
| Download URL | keras-flops-0.1.2.tar.gz |
|---|---|
| Size | 4.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
2561043d435dce3b0b6a68573a538facddbcfa637faf7ae7f48b2e8f373ed84e
|
|
BLAKE2b-256 checksum How to use checksums |
65d4bc5aeafede12dd7e31b71653349d791e31610e6d5859fce556599f8af91e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.0.8 CPython/3.6.10 Linux/4.19.84-microsoft-standard
|
Release files / keras_flops-0.1.2-py3-none-any.whl
| Download URL | keras_flops-0.1.2-py3-none-any.whl |
|---|---|
| Size | 5.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
1202bb610f82a931ed65964fb9c330875001a5b1d527b279062185178541366a
|
|
BLAKE2b-256 checksum How to use checksums |
bc77e384f6e427e1920624a9229b411010eaa244134cff6a230d303d3b1ea0be
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.0.8 CPython/3.6.10 Linux/4.19.84-microsoft-standard
|
Security for keras-flops 0.1.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.