Update app.py
Browse files
app.py
CHANGED
@@ -1,11 +1,3 @@
|
|
1 |
-
!wget --no-check-certificate 'https://docs.google.com/uc?export=download&id=12reT7rxiRqTERYqeKYx7WGz5deMXjnEo' -O filetxt
|
2 |
-
!unzip filetxt
|
3 |
-
|
4 |
-
from roboflow import Roboflow
|
5 |
-
rf = Roboflow(api_key="kGIFR6wPmDow2dHnoXoi")
|
6 |
-
project = rf.workspace("capstone-design-oyzc3").project("dataset-train-test")
|
7 |
-
dataset = project.version(1).download("folder")
|
8 |
-
|
9 |
import os
|
10 |
import torch
|
11 |
import evaluate
|
@@ -15,7 +7,7 @@ import glob as glob
|
|
15 |
import torch.optim as optim
|
16 |
import matplotlib.pyplot as plt
|
17 |
import torchvision.transforms as transforms
|
18 |
-
|
19 |
|
20 |
from PIL import Image
|
21 |
from zipfile import ZipFile
|
@@ -31,6 +23,16 @@ from transformers import (
|
|
31 |
default_data_collator
|
32 |
AutoModel
|
33 |
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
|
35 |
def seed_everything(seed_value):
|
36 |
np.random.seed(seed_value)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
import os
|
2 |
import torch
|
3 |
import evaluate
|
|
|
7 |
import torch.optim as optim
|
8 |
import matplotlib.pyplot as plt
|
9 |
import torchvision.transforms as transforms
|
10 |
+
import subprocess
|
11 |
|
12 |
from PIL import Image
|
13 |
from zipfile import ZipFile
|
|
|
23 |
default_data_collator
|
24 |
AutoModel
|
25 |
)
|
26 |
+
from roboflow import Roboflow
|
27 |
+
rf = Roboflow(api_key="kGIFR6wPmDow2dHnoXoi")
|
28 |
+
project = rf.workspace("capstone-design-oyzc3").project("dataset-train-test")
|
29 |
+
dataset = project.version(1).download("folder")
|
30 |
+
|
31 |
+
#!wget --no-check-certificate 'https://docs.google.com/uc?export=download&id=12reT7rxiRqTERYqeKYx7WGz5deMXjnEo' -O filetxt
|
32 |
+
|
33 |
+
# Use subprocess to execute the wget command
|
34 |
+
subprocess.run(['wget', '--no-check-certificate', 'https://docs.google.com/uc?export=download&id=12reT7rxiRqTERYqeKYx7WGz5deMXjnEo', '-O', 'filetxt'])
|
35 |
+
!unzip filetxt
|
36 |
|
37 |
def seed_everything(seed_value):
|
38 |
np.random.seed(seed_value)
|