Vít Růžička previtus

qubvel / checkpoints_weights_averaging.py

Created November 19, 2019 09:17

	import torch
	from collections import OrderedDict
	from typing import List

	checkpoints_weights_paths: List[str] = ... # sorted in descending order by score
	model: torch.nn.Module = ...


	def average_weights(state_dicts: List[dict]):
	everage_dict = OrderedDict()

max-mapper / upload.sh

Created March 27, 2019 00:43

upload large file to zenodo from command line (curl)

	# in zenodo ui create a deposition. get the id

	curl -H "Accept: application/json" -H "Authorization: Bearer $TOKEN" "https://www.zenodo.org/api/deposit/depositions/$DEPOSITION"
	# get the bucket id from above

	curl --progress-bar -o /dev/null --upload-file ./$FILE https://www.zenodo.org/api/files/$BUCKET/$FILE?access_token=$TOKEN

Nikhil-Kasukurthi / visualisation.py

Last active December 13, 2022 16:55

Visualisation of CNN using Grad-Cam on PyTorch

	import cv2
	import numpy as np
	import torch
	from torchvision import models, transforms
	from torch.autograd import Variable
	import torch
	import torch.nn as nn
	import pickle
	import os
	import argparse

mvoelk / resnet-152_keras.py

Last active March 11, 2022 08:06

Resnet-152 pre-trained model in TF Keras 2.x

	# -- coding: utf-8 --

	import cv2
	import numpy as np

	from tensorflow.keras.layers import Input, Dense, Conv2D, MaxPool2D, AvgPool2D, Activation
	from tensorflow.keras.layers import Layer, BatchNormalization, ZeroPadding2D, Flatten, add
	from tensorflow.keras.optimizers import SGD
	from tensorflow.keras.models import Model
	from tensorflow.keras import initializers

jeffbass / zmqimage.py

Last active November 6, 2022 16:59

zmqimage.py -- classes to send, receive and display OpenCV images from a headless computer to a display computer using cv2.imshow()

	# zmqimage.py -- classes to send, receive and display cv2 images via zmq
	# based on serialization in pyzmq docs and pyzmq/examples/serialization

	'''
	PURPOSE:
	These classes allow a headless (no display) computer running OpenCV code
	to display OpenCV images on another computer with a display.
	For example, a headless Raspberry Pi with no display can run OpenCV code
	and can display OpenCV images on a Mac with a display.
	USAGE:

rxaviers / gist:7360908

Last active December 12, 2025 14:32

Complete list of github markdown emoji markup

People

dlion / wget_thread.sh

Created January 20, 2013 02:51

Allows to download a file with wget using multi-threading.