jph00 commited on
Commit
4d6cfb5
·
1 Parent(s): 6238932
.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
Cat_November_2010-1a.jpg ADDED
Dog_1098119012_Teaser.png ADDED
German-shepherd.png ADDED
README.md ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ title: Fast Ai Models
3
+ emoji: 🐨
4
+ colorFrom: pink
5
+ colorTo: blue
6
+ sdk: streamlit
7
+ sdk_version: 1.21.0
8
+ app_file: app.py
9
+ pinned: false
10
+ license: apache-2.0
11
+ ---
12
+
13
+ Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
app.py ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import streamlit as st
2
+ from fastai.vision.all import *
3
+
4
+ def is_cat(x) : return x[0].isupper()
5
+
6
+ learn = load_learner('model.pkl')
7
+ categories = ('Dog', 'Cat')
8
+
9
+ def classify_image(img):
10
+ pred,idx,probs = learn.predict(img)
11
+ return dict(zip(categories,map(float,probs)))
12
+
13
+ def save_uploaded_file(uploadedfile):
14
+ path_name = os.path.join("tmp",uploadedfile.name)
15
+ with open(path_name,"wb") as f:
16
+ f.write(uploadedfile.getbuffer())
17
+ st.success(f"Saved file :{uploadedfile.name} as {path_name}")
18
+ return path_name
19
+
20
+ upload_image = st.file_uploader("Choose a file")
21
+
22
+ if upload_image is not None:
23
+ image = PILImage.create(upload_image)
24
+ image.thumbnail((192,192))
25
+ st.image(image)
26
+ path_name = save_uploaded_file(upload_image)
27
+ st.write("Prediction Propabilities:")
28
+ st.write(classify_image(path_name))
model.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a38b61493b46b5896543f2909c71192d4a5a2617dbf6dcfc8e136bae328c59e9
3
+ size 47063121
model.pkl:Zone.Identifier ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ [ZoneTransfer]
2
+ ZoneId=3
3
+ HostUrl=about:internet
requirements.txt ADDED
@@ -0,0 +1,225 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # This file may be used to create an environment using:
2
+ # $ conda create --name <env> --file <this file>
3
+ # platform: linux-64
4
+ _libgcc_mutex=0.1=conda_forge
5
+ _openmp_mutex=4.5=2_kmp_llvm
6
+ altair=5.0.1=pyhd8ed1ab_0
7
+ asttokens=2.2.1=pyhd8ed1ab_0
8
+ attrs=23.1.0=pyh71513ae_1
9
+ aws-c-auth=0.6.28=hccec9ca_5
10
+ aws-c-cal=0.5.27=hf85dbcb_0
11
+ aws-c-common=0.8.20=hd590300_0
12
+ aws-c-compression=0.2.17=h4b87b72_0
13
+ aws-c-event-stream=0.3.0=hc5de78f_6
14
+ aws-c-http=0.7.8=h412fb1b_4
15
+ aws-c-io=0.13.26=h0d05201_0
16
+ aws-c-mqtt=0.8.13=ha5d9b87_2
17
+ aws-c-s3=0.3.4=h95e21fb_5
18
+ aws-c-sdkutils=0.1.10=h4b87b72_0
19
+ aws-checksums=0.1.16=h4b87b72_0
20
+ aws-crt-cpp=0.20.2=h5289e1f_9
21
+ aws-sdk-cpp=1.10.57=h8101662_14
22
+ backcall=0.2.0=pyh9f0ad1d_0
23
+ backports=1.0=pyhd8ed1ab_3
24
+ backports.functools_lru_cache=1.6.4=pyhd8ed1ab_0
25
+ blinker=1.6.2=pyhd8ed1ab_0
26
+ brotli=1.0.9=h166bdaf_8
27
+ brotli-bin=1.0.9=h166bdaf_8
28
+ bzip2=1.0.8=h7f98852_4
29
+ c-ares=1.19.1=hd590300_0
30
+ ca-certificates=2023.5.7=hbcca054_0
31
+ cachetools=5.3.0=pyhd8ed1ab_0
32
+ catalogue=2.0.8=py310hff52083_1
33
+ certifi=2023.5.7=pyhd8ed1ab_0
34
+ charset-normalizer=3.1.0=pyhd8ed1ab_0
35
+ click=8.1.3=unix_pyhd8ed1ab_2
36
+ colorama=0.4.6=pyhd8ed1ab_0
37
+ comm=0.1.3=pyhd8ed1ab_0
38
+ commonmark=0.9.1=py_0
39
+ confection=0.0.4=py310hfdc917e_1
40
+ contourpy=1.1.0=py310hd41b1e2_0
41
+ cycler=0.11.0=pyhd8ed1ab_0
42
+ cymem=2.0.7=py310hd8f1fbe_1
43
+ cython-blis=0.7.9=py310hde88566_1
44
+ dataclasses=0.8=pyhc8e2a94_3
45
+ debugpy=1.6.7=py310heca2aa9_0
46
+ decorator=5.1.1=pyhd8ed1ab_0
47
+ executing=1.2.0=pyhd8ed1ab_0
48
+ fastai=2.7.11=pyhd8ed1ab_0
49
+ fastcore=1.5.29=pyhd8ed1ab_0
50
+ fastdownload=0.0.7=pyhd8ed1ab_0
51
+ fastprogress=1.0.3=pyhd8ed1ab_0
52
+ fonttools=4.40.0=py310h2372a71_0
53
+ freetype=2.12.1=hca18f0e_1
54
+ future=0.18.3=pyhd8ed1ab_0
55
+ gflags=2.2.2=he1b5a44_1004
56
+ gitdb=4.0.10=pyhd8ed1ab_0
57
+ gitpython=3.1.31=pyhd8ed1ab_0
58
+ glog=0.6.0=h6f12383_0
59
+ icu=72.1=hcb278e6_0
60
+ idna=3.4=pyhd8ed1ab_0
61
+ importlib-metadata=6.6.0=pyha770c72_0
62
+ importlib_metadata=6.6.0=hd8ed1ab_0
63
+ importlib_resources=5.12.0=pyhd8ed1ab_0
64
+ ipykernel=6.23.1=pyh210e3f2_0
65
+ ipython=8.14.0=pyh41d4057_0
66
+ ipywidgets=8.0.6=pyhd8ed1ab_0
67
+ jedi=0.18.2=pyhd8ed1ab_0
68
+ jinja2=3.1.2=pyhd8ed1ab_1
69
+ joblib=1.2.0=pyhd8ed1ab_0
70
+ jsonschema=4.17.3=pyhd8ed1ab_0
71
+ jupyter_client=8.2.0=pyhd8ed1ab_0
72
+ jupyter_core=5.3.1=py310hff52083_0
73
+ jupyterlab_widgets=3.0.7=pyhd8ed1ab_1
74
+ keyutils=1.6.1=h166bdaf_0
75
+ kiwisolver=1.4.4=py310hbf28c38_1
76
+ krb5=1.20.1=h81ceb04_0
77
+ langcodes=3.3.0=pyhd8ed1ab_0
78
+ lcms2=2.15=haa2dc70_1
79
+ ld_impl_linux-64=2.40=h41732ed_0
80
+ lerc=4.0.0=h27087fc_0
81
+ libabseil=20230125.2=cxx17_h59595ed_2
82
+ libarrow=12.0.0=hc00ebf5_8_cpu
83
+ libblas=3.9.0=17_linux64_openblas
84
+ libbrotlicommon=1.0.9=h166bdaf_8
85
+ libbrotlidec=1.0.9=h166bdaf_8
86
+ libbrotlienc=1.0.9=h166bdaf_8
87
+ libcblas=3.9.0=17_linux64_openblas
88
+ libcrc32c=1.1.2=h9c3ff4c_0
89
+ libcurl=8.1.2=h409715c_0
90
+ libdeflate=1.18=h0b41bf4_0
91
+ libedit=3.1.20191231=he28a2e2_2
92
+ libev=4.33=h516909a_1
93
+ libevent=2.1.12=hf998b51_1
94
+ libffi=3.4.2=h7f98852_5
95
+ libgcc-ng=13.1.0=he5830b7_0
96
+ libgfortran-ng=13.1.0=h69a702a_0
97
+ libgfortran5=13.1.0=h15d22d2_0
98
+ libgoogle-cloud=2.11.0=hac9eb74_1
99
+ libgrpc=1.54.2=hb20ce57_2
100
+ libhwloc=2.9.1=nocuda_h7313eea_6
101
+ libiconv=1.17=h166bdaf_0
102
+ libjpeg-turbo=2.1.5.1=h0b41bf4_0
103
+ liblapack=3.9.0=17_linux64_openblas
104
+ libnghttp2=1.52.0=h61bc06f_0
105
+ libnsl=2.0.0=h7f98852_0
106
+ libnuma=2.0.16=h0b41bf4_1
107
+ libopenblas=0.3.23=pthreads_h80387f5_0
108
+ libpng=1.6.39=h753d276_0
109
+ libprotobuf=3.21.12=h3eb15da_0
110
+ libsodium=1.0.18=h36c2ea0_1
111
+ libsqlite=3.42.0=h2797004_0
112
+ libssh2=1.11.0=h0841786_0
113
+ libstdcxx-ng=13.1.0=hfd8a6a1_0
114
+ libthrift=0.18.1=h8fd135c_2
115
+ libtiff=4.5.1=h8b53f26_0
116
+ libutf8proc=2.8.0=h166bdaf_0
117
+ libuuid=2.38.1=h0b41bf4_0
118
+ libwebp-base=1.3.0=h0b41bf4_0
119
+ libxcb=1.15=h0b41bf4_0
120
+ libxml2=2.11.4=h0d562d8_0
121
+ libzlib=1.2.13=hd590300_5
122
+ llvm-openmp=16.0.6=h4dfa4b3_0
123
+ lz4-c=1.9.4=hcb278e6_0
124
+ markupsafe=2.1.3=py310h2372a71_0
125
+ matplotlib-base=3.7.1=py310he60537e_0
126
+ matplotlib-inline=0.1.6=pyhd8ed1ab_0
127
+ mkl=2022.2.1=h84fe81f_16997
128
+ munkres=1.1.4=pyh9f0ad1d_0
129
+ murmurhash=1.0.9=py310hd8f1fbe_1
130
+ ncurses=6.4=hcb278e6_0
131
+ nest-asyncio=1.5.6=pyhd8ed1ab_0
132
+ numpy=1.25.0=py310ha4c1d20_0
133
+ openjpeg=2.5.0=hfec8fc6_2
134
+ openssl=3.1.1=hd590300_1
135
+ orc=1.8.4=h2f23424_0
136
+ packaging=23.1=pyhd8ed1ab_0
137
+ pandas=2.0.2=py310h7cbd5c2_0
138
+ parso=0.8.3=pyhd8ed1ab_0
139
+ pathy=0.10.1=pyhd8ed1ab_0
140
+ pexpect=4.8.0=pyh1a96a4e_2
141
+ pickleshare=0.7.5=py_1003
142
+ pillow=9.5.0=py310h582fbeb_1
143
+ pip=23.1.2=pyhd8ed1ab_0
144
+ pkgutil-resolve-name=1.3.10=pyhd8ed1ab_0
145
+ platformdirs=3.6.0=pyhd8ed1ab_0
146
+ pooch=1.7.0=pyha770c72_3
147
+ preshed=3.0.8=py310hd8f1fbe_1
148
+ prompt-toolkit=3.0.38=pyha770c72_0
149
+ prompt_toolkit=3.0.38=hd8ed1ab_0
150
+ protobuf=4.21.12=py310heca2aa9_0
151
+ psutil=5.9.5=py310h1fa729e_0
152
+ pthread-stubs=0.4=h36c2ea0_1001
153
+ ptyprocess=0.7.0=pyhd3deb0d_0
154
+ pure_eval=0.2.2=pyhd8ed1ab_0
155
+ pyarrow=12.0.0=py310h0576679_8_cpu
156
+ pydantic=1.10.9=py310h2372a71_0
157
+ pydeck=0.8.0=pyhd8ed1ab_0
158
+ pygments=2.15.1=pyhd8ed1ab_0
159
+ pympler=1.0.1=pyhd8ed1ab_0
160
+ pyparsing=3.0.9=pyhd8ed1ab_0
161
+ pyrsistent=0.19.3=py310h1fa729e_0
162
+ pysocks=1.7.1=pyha2e5f31_6
163
+ python=3.10.11=he550d4f_0_cpython
164
+ python-dateutil=2.8.2=pyhd8ed1ab_0
165
+ python-tzdata=2023.3=pyhd8ed1ab_0
166
+ python_abi=3.10=3_cp310
167
+ pytorch=1.13.1=cpu_py310hd11e9c7_1
168
+ pytz=2023.3=pyhd8ed1ab_0
169
+ pytz-deprecation-shim=0.1.0.post0=py310hff52083_3
170
+ pyyaml=6.0=py310h5764c6d_5
171
+ pyzmq=25.1.0=py310h5bbb5d0_0
172
+ rdma-core=28.9=h59595ed_1
173
+ re2=2023.03.02=h8c504da_0
174
+ readline=8.2=h8228510_1
175
+ requests=2.31.0=pyhd8ed1ab_0
176
+ rich=12.6.0=pyhd8ed1ab_0
177
+ s2n=1.3.45=h06160fa_0
178
+ scikit-learn=1.2.2=py310hf7d194e_2
179
+ scipy=1.10.1=py310ha4c1d20_3
180
+ setuptools=67.7.2=pyhd8ed1ab_0
181
+ shellingham=1.5.1=pyhd8ed1ab_0
182
+ six=1.16.0=pyh6c4a22f_0
183
+ sleef=3.5.1=h9b69904_2
184
+ smart_open=5.2.1=pyhd8ed1ab_0
185
+ smmap=3.0.5=pyh44b312d_0
186
+ snappy=1.1.10=h9fff704_0
187
+ spacy=3.5.3=py310hfb6f7a9_0
188
+ spacy-legacy=3.0.12=pyhd8ed1ab_0
189
+ spacy-loggers=1.0.4=pyhd8ed1ab_0
190
+ srsly=2.4.6=py310heca2aa9_0
191
+ stack_data=0.6.2=pyhd8ed1ab_0
192
+ streamlit=1.23.1=pyhd8ed1ab_0
193
+ tbb=2021.9.0=hf52228f_0
194
+ tenacity=8.2.2=pyhd8ed1ab_0
195
+ thinc=8.1.10=py310hfb6f7a9_0
196
+ threadpoolctl=3.1.0=pyh8a188c0_0
197
+ tk=8.6.12=h27826a3_0
198
+ toml=0.10.2=pyhd8ed1ab_0
199
+ toolz=0.12.0=pyhd8ed1ab_0
200
+ torchvision=0.14.1=cpu_py310hd3d2ac3_1
201
+ tornado=6.3.2=py310h2372a71_0
202
+ tqdm=4.65.0=pyhd8ed1ab_1
203
+ traitlets=5.9.0=pyhd8ed1ab_0
204
+ typer=0.7.0=pyhd8ed1ab_0
205
+ typing-extensions=4.6.3=hd8ed1ab_0
206
+ typing_extensions=4.6.3=pyha770c72_0
207
+ tzdata=2023c=h71feb2d_0
208
+ tzlocal=4.3=py310hff52083_0
209
+ ucx=1.14.1=hf587318_2
210
+ unicodedata2=15.0.0=py310h5764c6d_0
211
+ urllib3=2.0.3=pyhd8ed1ab_0
212
+ validators=0.20.0=pyhd8ed1ab_0
213
+ wasabi=1.1.2=py310hff52083_0
214
+ watchdog=3.0.0=py310hff52083_0
215
+ wcwidth=0.2.6=pyhd8ed1ab_0
216
+ wheel=0.40.0=pyhd8ed1ab_0
217
+ widgetsnbextension=4.0.7=pyhd8ed1ab_0
218
+ xorg-libxau=1.0.11=hd590300_0
219
+ xorg-libxdmcp=1.1.3=h7f98852_0
220
+ xz=5.2.6=h166bdaf_0
221
+ yaml=0.2.5=h7f98852_2
222
+ zeromq=4.3.4=h9c3ff4c_1
223
+ zipp=3.15.0=pyhd8ed1ab_0
224
+ zlib=1.2.13=hd590300_5
225
+ zstd=1.5.2=h3eb15da_6
test.ipynb ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": 1,
6
+ "metadata": {},
7
+ "outputs": [],
8
+ "source": [
9
+ "from fastai.vision.all import *\n",
10
+ "def is_cat(x) : return x[0].isupper()"
11
+ ]
12
+ },
13
+ {
14
+ "cell_type": "code",
15
+ "execution_count": 2,
16
+ "metadata": {},
17
+ "outputs": [],
18
+ "source": [
19
+ "image = PILImage.create(\"Dog_1098119012_Teaser.png\")\n",
20
+ "image.thumbnail((192,192))"
21
+ ]
22
+ },
23
+ {
24
+ "cell_type": "code",
25
+ "execution_count": 3,
26
+ "metadata": {},
27
+ "outputs": [
28
+ {
29
+ "data": {
30
+ "image/png": "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",
31
+ "text/plain": [
32
+ "PILImage mode=RGB size=192x108"
33
+ ]
34
+ },
35
+ "execution_count": 3,
36
+ "metadata": {},
37
+ "output_type": "execute_result"
38
+ }
39
+ ],
40
+ "source": [
41
+ "image"
42
+ ]
43
+ },
44
+ {
45
+ "cell_type": "code",
46
+ "execution_count": 4,
47
+ "metadata": {},
48
+ "outputs": [],
49
+ "source": [
50
+ "learn = load_learner('model.pkl')"
51
+ ]
52
+ },
53
+ {
54
+ "cell_type": "code",
55
+ "execution_count": 6,
56
+ "metadata": {},
57
+ "outputs": [
58
+ {
59
+ "data": {
60
+ "text/html": [
61
+ "\n",
62
+ "<style>\n",
63
+ " /* Turns off some styling */\n",
64
+ " progress {\n",
65
+ " /* gets rid of default border in Firefox and Opera. */\n",
66
+ " border: none;\n",
67
+ " /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
68
+ " background-size: auto;\n",
69
+ " }\n",
70
+ " progress:not([value]), progress:not([value])::-webkit-progress-bar {\n",
71
+ " background: repeating-linear-gradient(45deg, #7e7e7e, #7e7e7e 10px, #5c5c5c 10px, #5c5c5c 20px);\n",
72
+ " }\n",
73
+ " .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
74
+ " background: #F44336;\n",
75
+ " }\n",
76
+ "</style>\n"
77
+ ],
78
+ "text/plain": [
79
+ "<IPython.core.display.HTML object>"
80
+ ]
81
+ },
82
+ "metadata": {},
83
+ "output_type": "display_data"
84
+ },
85
+ {
86
+ "data": {
87
+ "text/html": [],
88
+ "text/plain": [
89
+ "<IPython.core.display.HTML object>"
90
+ ]
91
+ },
92
+ "metadata": {},
93
+ "output_type": "display_data"
94
+ },
95
+ {
96
+ "data": {
97
+ "text/plain": [
98
+ "('False', TensorBase(0), TensorBase([9.9996e-01, 3.6510e-05]))"
99
+ ]
100
+ },
101
+ "execution_count": 6,
102
+ "metadata": {},
103
+ "output_type": "execute_result"
104
+ }
105
+ ],
106
+ "source": [
107
+ "learn.predict(\"Dog_1098119012_Teaser.png\")"
108
+ ]
109
+ },
110
+ {
111
+ "cell_type": "code",
112
+ "execution_count": null,
113
+ "metadata": {},
114
+ "outputs": [],
115
+ "source": []
116
+ }
117
+ ],
118
+ "metadata": {
119
+ "kernelspec": {
120
+ "display_name": "fast_ai_course_linux",
121
+ "language": "python",
122
+ "name": "python3"
123
+ },
124
+ "language_info": {
125
+ "codemirror_mode": {
126
+ "name": "ipython",
127
+ "version": 3
128
+ },
129
+ "file_extension": ".py",
130
+ "mimetype": "text/x-python",
131
+ "name": "python",
132
+ "nbconvert_exporter": "python",
133
+ "pygments_lexer": "ipython3",
134
+ "version": "3.10.11"
135
+ },
136
+ "orig_nbformat": 4
137
+ },
138
+ "nbformat": 4,
139
+ "nbformat_minor": 2
140
+ }
tmp/Cat_November_2010-1a.jpg ADDED
tmp/German-shepherd.png ADDED