From ed026519d959ecc60a895f379c228de5df77ffb0 Mon Sep 17 00:00:00 2001
From: zhang <zch921005@126.com>
Date: Sun, 19 Jun 2022 09:20:25 +0800
Subject: daily update

---
 learn_keras/seq2seq.py              |  0
 learn_torch/bert/fill_mask.py       | 28 ++++++++++++++++++++
 learn_torch/seq2seq/base_model.py   | 51 +++++++++++++++++++++++++++++++++++++
 pretrained/swin/603_timm_swin.ipynb |  3 +--
 pretrained/swin/demo.py             |  1 +
 web/learn_canvas/basics/index.html  | 39 +++++++++++++++++++++++++++-
 6 files changed, 119 insertions(+), 3 deletions(-)
 create mode 100644 learn_keras/seq2seq.py
 create mode 100644 learn_torch/bert/fill_mask.py
 create mode 100644 learn_torch/seq2seq/base_model.py

diff --git a/learn_keras/seq2seq.py b/learn_keras/seq2seq.py
new file mode 100644
index 0000000..e69de29
diff --git a/learn_torch/bert/fill_mask.py b/learn_torch/bert/fill_mask.py
new file mode 100644
index 0000000..24e177f
--- /dev/null
+++ b/learn_torch/bert/fill_mask.py
@@ -0,0 +1,28 @@
+
+import torch
+from datasets import load_dataset
+from transformers import BertTokenizer
+
+
+#定义数据集
+class Dataset(torch.utils.data.Dataset):
+    def __init__(self, split):
+        dataset = load_dataset(path='seamew/ChnSentiCorp', split=split)
+
+        def f(data):
+            return len(data['text']) > 30
+
+        self.dataset = dataset.filter(f)
+
+    def __len__(self):
+        return len(self.dataset)
+
+    def __getitem__(self, i):
+        text = self.dataset[i]['text']
+
+        return text
+
+if __name__ == '__main__':
+    dataset = Dataset('train')
+    print(len(dataset), dataset[0])
+    tokenizer = BertTokenizer.from_pretrained('bert-base-chinese')
diff --git a/learn_torch/seq2seq/base_model.py b/learn_torch/seq2seq/base_model.py
new file mode 100644
index 0000000..bc292cf
--- /dev/null
+++ b/learn_torch/seq2seq/base_model.py
@@ -0,0 +1,51 @@
+import torch
+import torch.nn as nn
+import torch.optim as optim
+
+from torchtext.legacy.datasets import Multi30k
+from torchtext.legacy.data import Field, BucketIterator
+
+import spacy
+import numpy as np
+
+import random
+import math
+import time
+
+
+SEED = 1234
+
+random.seed(SEED)
+np.random.seed(SEED)
+torch.manual_seed(SEED)
+torch.cuda.manual_seed(SEED)
+torch.backends.cudnn.deterministic = True
+
+spacy_de = spacy.load('de_core_news_sm')
+spacy_en = spacy.load('en_core_web_sm')
+
+def tokenize_de(text):
+    """
+    Tokenizes German text from a string into a list of strings (tokens) and reverses it
+    """
+    return [tok.text for tok in spacy_de.tokenizer(text)][::-1]
+
+def tokenize_en(text):
+    """
+    Tokenizes English text from a string into a list of strings (tokens)
+    """
+    return [tok.text for tok in spacy_en.tokenizer(text)]
+
+SRC = Field(tokenize = tokenize_de,
+            init_token = '<sos>',
+            eos_token = '<eos>',
+            lower = True)
+
+TRG = Field(tokenize = tokenize_en,
+            init_token = '<sos>',
+            eos_token = '<eos>',
+            lower = True)
+
+train_data, valid_data, test_data = Multi30k.splits(exts = ('.de', '.en'),
+                                                    fields = (SRC, TRG))
+
diff --git a/pretrained/swin/603_timm_swin.ipynb b/pretrained/swin/603_timm_swin.ipynb
index 5e4ef1c..2d0cbf2 100644
--- a/pretrained/swin/603_timm_swin.ipynb
+++ b/pretrained/swin/603_timm_swin.ipynb
@@ -320,8 +320,7 @@
     "ExecuteTime": {
      "end_time": "2022-06-03T03:33:39.593106Z",
      "start_time": "2022-06-03T03:33:39.583112Z"
-    },
-    "collapsed": true
+    }
    },
    "outputs": [
     {
diff --git a/pretrained/swin/demo.py b/pretrained/swin/demo.py
index 6f8d87b..3b6d9d9 100644
--- a/pretrained/swin/demo.py
+++ b/pretrained/swin/demo.py
@@ -20,6 +20,7 @@ if __name__ == '__main__':
     batch_input = transformed.unsqueeze(0)
     print(batch_input.shape)
 
+    timm.list_models()
     model = timm.create_model('swin_base_patch4_window7_224', pretrained=True)
 
     with torch.no_grad():
diff --git a/web/learn_canvas/basics/index.html b/web/learn_canvas/basics/index.html
index 3c0cfb8..e3d6e7f 100644
--- a/web/learn_canvas/basics/index.html
+++ b/web/learn_canvas/basics/index.html
@@ -3,9 +3,46 @@
 <head>
     <meta charset="UTF-8">
     <title>Title</title>
+    <style>
+        canvas {
+            border: 1px solid #ccc
+        }
+    </style>
 </head>
 <body>
     <canvas id="canvas"></canvas>
+    <script>
+        var can = document.getElementById("canvas");
+        can.width = 800;
+        can.height = 600;
+
+        var ctx = can.getContext("2d");
+
+        <!--ctx.beginPath();-->
+        ctx.rect(50, 50, 100, 100);
+
+        <!--ctx.fillStyle = "#00cc00";-->
+        <!--ctx.fill();-->
+
+        ctx.strokeStyle = "#cc0000";
+        ctx.stroke();
+
+        ctx.beginPath();
+        ctx.rect(200, 50, 100, 100);
+        ctx.strokeStyle = "#00cc00";
+        ctx.stroke();
+
+        ctx.beginPath();
+        ctx.moveTo(600, 100);
+        ctx.lineTo(650, 150);
+        ctx.lineTo(550, 150);
+        <!--ctx.lineTo(600, 100);-->
+        ctx.closePath();
+        ctx.lineWidth = 10;
+        ctx.strokeStyle = '#0000cc';
+        ctx.stroke();
+
+    </script>
 </body>
-<script src="main.js"></script>
+<!--<script src="main.js"></script>-->
 </html>
\ No newline at end of file
-- 
cgit v1.2.3