pat= r'/([^/]+)_\d+.jpg$' data = ImageDataBunch.from_name_re( path_img, fnames, pat, ds_tfms=get_transforms(), size=224, bs=bs ).normalize(imagenet_stats) qiita.com:embed:cite]https://www.debuggex.com/?re=&str=

def ifnone(a:Any,b:Any)->Any: "`a` if `a` is not None, otherwise `b`." return b if a is None else a https://github.com/fastai/fastai/blob/master/fastai/core.py 「aがNoneでなければa、そうでなければbです。」 def test_ifnone(): assert ifnone(…

def untar_data( url:str, fname:PathOrStr=None, dest:PathOrStr=None, data=True, force_download=False) -> Path: "Download `url` to `fname` if it doesn't exist, and un-tgz to folder `dest`." dest = url2path(url, data) if dest is None else Pat…

どうやって、出ないようにするんだろう？暗号化された接続が確立されたドメインに対する信頼性を保証できません アプリ ：Chrome理由：自己署名証明書

Batch size=256のとき、エラーになった。 Batch size=128のとき、エラー。 Batch size= 64のとき、ワーニング。 64のとき、progress epoch 7 step 1 image/sec 15.1 remaining 563m 9時間ちょい ResourceExhaustedError (see above for traceback): OOM when…

再読込

/tools/node/bin/lt -> /tools/node/lib/node_modules/localtunnel/bin/client + localtunnel@1.9.1 updated 1 package in 2.558s your url is: https://strong-rabbit-23.localtunnel.me your url is: https://spicy-cougar-27.localtunnel.me /tools/node/…

dataset [AlignedDataset] was created initialize network with normal model [Pix2PixModel] was created loading the model from log_train/sub_20190130_1324/pix2pix_popRam/latest_net_G.pth Traceback (most recent call last): File "pytorch-CycleG…

$ tensorboard --help usage: tensorboard [-h] [--helpfull] [--logdir PATH] [--host ADDR] [--port PORT] [--purge_orphaned_data BOOL] [--reload_interval SECONDS] [--db URI] [--db_import] [--db_import_use_op] [--inspect] [--tag TAG] [--event_f…

if self.display_id > 0: # connect to a visdom server given <display_port> and <display_server> import visdom self.ncols = opt.display_ncols self.vis = visdom.Visdom(server=opt.display_server, port=opt.display_port, env=opt.display_env) if not self.vis.check_connection(</display_server></display_port>…

これで、動いてるのかな？ ! npm install -g localtunnel !python3 -m pip install visdom !python3 -m visdom.server -port 6006 >> visdomlog.txt 2>&1 & !lt --port 6006 >> url.txt 2>&1 & #get_ipython().system_raw('/usr/local/bin/python3 -m pip in…

Traceback (most recent call last): File "train.py", line 70, in <module> tf.app.run() File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/platform/app.py", line 125, in run _sys.exit(main(argv)) File "train.py", line 66, in main flip_la</module>…

Traceback (most recent call last): File "train.py", line 70, in <module> tf.app.run() File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/platform/app.py", line 125, in run _sys.exit(main(argv)) File "train.py", line 66, in main flip_la</module>…

Traceback (most recent call last): File "package.py", line 8, in <module> import cPickle as pickle ModuleNotFoundError: No module named 'cPickle'testpy.hatenablog.com</module>

https://fomoro.com/projects/project/receptive-field-calculator#https://fomoro.com/projects/project/receptive-field-calculator#4,2,1,SAME;4,2,1,SAME;4,2,1,SAME;2,1,1,VALID;2,1,1,VALID

ENOCEAN TELEGRAM DECODER DRAFT1 https://ermine.co.jp/enocean-telegram-decoder-rev-0-1/

graphから、出力フォルダを変えてtensorboardの起動 !pip install tensorboardcolab from tensorboardcolab import * # #tbc = TensorBoardColab(graph_path='./Graph') tbc = TensorBoardColab(graph_path='./output_train') # #summary_writer = tbc.get_w…

ValueError: Floating point image RGB values must be in the 0..1 range. Time taken for epoch 1 is 132.77519750595093 sec --------------------------------------------------------------------------- ValueError Traceback (most recent call last)…

gist.github.com

Google ColabでTensorBoardを利用しようとしていたら、以下のエラーがでた。CPUだと起こるみたい、GPUにするとエラーが出なくなった。 ランタイムのリセットも必要かもしれない。 ソースの元 stackoverflow.com from __future__ import print_function impor…

ValueError: To visualize embeddings, embeddings_data must be provided.callbacks = [ keras.callbacks.TensorBoard( log_dir='my_log_dir', # ログ・ファイルはこの場所に書き込まれる histogram_freq = 1, # １エポックごとに活性化ヒストグラムを記録 …

!apt-get install graphviz !pip install pydot-ng !pip install graphvizmodel.summary() from IPython.display import SVG from keras.utils.vis_utils import model_to_dot SVG(model_to_dot(model,show_shapes=True).create(prog='dot', format='svg')) …

speech.ee.ntu.edu.tw李宏毅 - GAN (不是髒話) - 2017 台灣人工智慧年會－人工智慧．智慧台灣

https://github.com/phillipi/pix2pix/blob/master/train.lua -- usage example: DATA_ROOT=/path/to/data/ which_direction=BtoA name=expt1 th train.lua -- -- code derived from https://github.com/soumith/dcgan.torch -- >|lua| require 'torch' requ…

!python main.py 64 64 --backend tensorflow --nb_epoch 10Using TensorFlow backend. RuntimeError: module compiled against API version 0xc but this version of numpy is 0xb ImportError: numpy.core.multiarray failed to import ImportError: numpy…

VAEのもとのソースをgoogle colabで実行したら、以下のようなエラーがでた。 for i in range(30000): batch = [np.reshape(b, [28, 28]) for b in mnist.train.next_batch(batch_size=batch_size)[0]] sess.run(optimizer, feed_dict = {X_in: batch, Y: bat…

medium.comhackernoon.comFast.ai Machine Learning Lesson 1 | Kaggle

df_raw = pd.read_feather('tmp/bulldozers-raw')--------------------------------------------------------------------------- TypeError Traceback (most recent call last) <ipython-input-62-54f538a9be00> in <module>() ----> 1 df_raw = pd.read_feather('tmp/bulldozers-raw') /usr/local/</module></ipython-input-62-54f538a9be00>…

tail()したものを、転置していた。

qiita.com