主页

soruce Transform # When we studied tokenization and numericalization in the last chapter, we started by grabbing a bunch of texts: files = get_text_files(path, folders = ['train', 'test']) txts = L(o.open().read() for o in files[:2000]) # We then showed how to tokenize them with a Tokenizer: tok = Tokenizer.from_folder(path) tok.setup(txts) to...

soruce write a custom model from fastai.vision.all import * path = untar_data(URLs.PETS) files = get_image_files(path/"images") class SiameseImage(fastuple): def show(self, ctx=None, **kwargs): img1,img2,same_breed = self if not isinstance(img1, Tensor): if img2.size != img1.size: img2 = img2.resize(img1.size) ...

soruce Single-label classification Cats vs Dogs from fastai.vision.all import * path = untar_data(URLs.PETS) path.ls() files = get_image_files(path/"images") len(files) def label_func(f): return f[0].isupper() dls = ImageDataLoaders.from_name_func(path, files, label_func, item_tfms=Resize(224)) dls.show_batch() learn = vision_learner(dls,...

soruce Text transfer learning !pip install -Uq transformers from transformers import GPT2LMHeadModel, GPT2TokenizerFast from fastai.text.all import * pretrained_weights = 'gpt2' tokenizer = GPT2TokenizerFast.from_pretrained(pretrained_weights) model = GPT2LMHeadModel.from_pretrained(pretrained_weights) ids = tokenizer.encode('This is an exam...

soruce Text transfer learning from fastai.text.all import * Train a text classifier from a pretrained model Using the high-level API path = untar_data(URLs.IMDB) dls = TextDataLoaders.from_folder(untar_data(URLs.IMDB), valid='test') dls.show_batch() text category 0 xxbos xxmaj match 1 : xxmaj tag xxmaj team xxmaj table xxmaj match xx...

soruce Tabular training from fastai.tabular.all import * path = untar_data(URLs.ADULT_SAMPLE) path.ls() df = pd.read_csv(path/'adult.csv') df.head() dls = TabularDataLoaders.from_csv(path/'adult.csv', path=path, y_names="salary", cat_names = ['workclass', 'education', 'marital-status', 'occupation', 'relationship', 'race'], cont_names...

soruce fine-tune Fine-tuning: A transfer learning technique where the parameters of a pretrained model are updated by training for additional epochs using a different task to that used for pretraining. When you use the fine_tune method, fastai will use these tricks for you. There are a few parameters you can set (which we’ll discuss later), bu...

soruce Transform from fastai.text.all import * from fastai.vision.all import * source = untar_data(URLs.MNIST_TINY)/'train' items = get_image_files(source) fn = items[0]; fn img = PILImage.create(fn); img tconv = ToTensor() img = tconv(img) img.shape,type(img) lbl = parent_label(fn); lbl tcat = Categorize(vocab=['3','7']) lbl = tcat(lbl); l...