simongrest

gilrosenthal

!pip install fastai
!apt-get -qq install -y libsm6 libxext6 && pip install -q -U opencv-python
import cv2
from os import path
from wheel.pep425tags import get_abbr_impl, get_impl_ver, get_abi_tag
platform = '{}{}-{}'.format(get_abbr_impl(), get_impl_ver(), get_abi_tag())

accelerator = 'cu80' if path.exists('/opt/bin/nvidia-smi') else 'cpu'

!pip install -q http://download.pytorch.org/whl/{accelerator}/torch-0.3.0.post4-{platform}-linux_x86_64.whl torchvision

Mirodil

class LearningRateFinder(Callback):
    '''
    This callback implements a learning rate finder(LRF)
    The learning rate is constantly increased during training.
    On training end, the training loss is plotted against the learning rate.
    One may choose a learning rate for a model based on the given graph,
    selecting a value slightly before the minimal training loss.
    # Example
        lrf = LearningRateFinder([0.0001, 0.0005, 0.001, 0.005, 0.01, 0.05])
        model.fit(x_train, y_train, epochs=1, batch_size=128, callbacks=[lrf])

Mirodil

import numpy as np
from keras import backend as K
from keras.preprocessing.image import Iterator, load_img, img_to_array

class FileListIterator(Iterator):
    """Iterator capable of reading images from an array of the filenames.
    # Arguments
        filenames: Path to the directory to read images from.
            Each subdirectory in this directory will be
            considered to contain images from one class,

jeremyjordan

from keras.callbacks import Callback
import keras.backend as K
import numpy as np

class SGDRScheduler(Callback):
    '''Cosine annealing learning rate scheduler with periodic restarts.

    # Usage
        ```python
            schedule = SGDRScheduler(min_lr=1e-5,

sbugallo

from keras.layers import Conv2D
from keras.layers import Activation
from keras.layers import Add
from keras.layers import BatchNormalization
from keras.layers import ZeroPadding2D
from keras.layers import MaxPooling2D

def identity_block(input_tensor, kernel_size, filters, stage, block, use_bias=True):
    """
    This block is the one with no convolutional layer at its shortcut branch

chourobin

Bridging Native & React for iOS & Android

js -> native

• Simple Example
• Callbacks
• Promises
• Properties

native -> js

fchollet

'''This script goes along the blog post
"Building powerful image classification models using very little data"
from blog.keras.io.
It uses data that can be downloaded at:
https://www.kaggle.com/c/dogs-vs-cats/data
In our setup, we:
- created a data/ folder
- created train/ and validation/ subfolders inside data/
- created cats/ and dogs/ subfolders inside train/ and validation/
- put the cat pictures index 0-999 in data/train/cats

trevnorris

The prep-script.sh will setup the latest Node and install the latest perf version on your Linux box.

When you want to generate the flame graph, run the following (folder locations taken from install script):

sudo sysctl kernel.kptr_restrict=0
# May also have to do the following:
# (additional reading http://unix.stackexchange.com/questions/14227/do-i-need-root-admin-permissions-to-run-userspace-perf-tool-perf-events-ar )
sudo sysctl kernel.perf_event_paranoid=0