jeremyjordan

# Create a directory with images named 1.jpg, 2.jpg, 3.jpg, etc.

# Generate a custom color palette
ffmpeg -framerate 0.5 -i %d.jpg \
  -vf "format=rgba,fps=0.5,palettegen=stats_mode=diff" \
  -y palette.png
  
# Create the gif
ffmpeg -framerate 0.5 -i %d.jpg -i palette.png \
  -lavfi "format=rgba,fps=0.5,paletteuse=dither=none" \

jeremyjordan

Example for discussion: https://discuss.streamlit.io/t/how-to-evolve-complex-state-e-g-annotate-data/

Install the requirements.

fastapi==0.42.0
streamlit==0.49.0
uvicorn==0.9.1

Run the server.

jeremyjordan

import numpy as np
import streamlit as st

from .streamlit_utils import SessionState

session_state = SessionState.get(page=1)


def main():
    # Render the readme as markdown using st.markdown.

jeremyjordan

def soft_dice_loss(y_true, y_pred, epsilon=1e-6): 
    ''' 
    Soft dice loss calculation for arbitrary batch size, number of classes, and number of spatial dimensions.
    Assumes the `channels_last` format.
  
    # Arguments
        y_true: b x X x Y( x Z...) x c One hot encoding of ground truth
        y_pred: b x X x Y( x Z...) x c Network output, must sum to 1 over c channel (such as after softmax) 
        epsilon: Used for numerical stability to avoid divide by zero errors
    

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,

jeremyjordan

import numpy as np
from keras.callbacks import LearningRateScheduler

def step_decay_schedule(initial_lr=1e-3, decay_factor=0.75, step_size=10):
    '''
    Wrapper function to create a LearningRateScheduler with step decay schedule.
    '''
    def schedule(epoch):
        return initial_lr * (decay_factor ** np.floor(epoch/step_size))
    

jeremyjordan

import matplotlib.pyplot as plt
import keras.backend as K
from keras.callbacks import Callback


class LRFinder(Callback):
    
    '''
    A simple callback for finding the optimal learning rate range for your model + dataset.