You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: PaliGemma/Finetune_PaliGemma_for_object_detection.ipynb
+34-20Lines changed: 34 additions & 20 deletions
Original file line number
Diff line number
Diff line change
@@ -28,7 +28,7 @@
28
28
"# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
29
29
"# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
30
30
"# See the License for the specific language governing permissions and\n",
31
-
"# limitations under the License."
31
+
"# limitations under the License."
32
32
]
33
33
},
34
34
{
@@ -48,7 +48,7 @@
48
48
"source": [
49
49
"<table align=\"left\">\n",
50
50
" <td>\n",
51
-
" <a target=\"_blank\" href=\"https://colab.research.google.com/drive/13fSUAhRviSI1YKhOmesjktw5BaI87sfm?usp=sharing\"><img src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" />Run in Google Colab</a>\n",
51
+
" <a target=\"_blank\" href=\"https://colab.research.google.com/github/google-gemini/gemma-cookbook/blob/main/PaliGemma/Finetune_PaliGemma_for_object_detection.ipynb\"><img src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" />Run in Google Colab</a>\n",
"This notebook demonstrated the fine-tuning of Paligemma on a fashion dataset for object detection. While the complete dataset of 4.5k images could not be utilized due to resource constraints, a subset of 640 images was used, which resulted in measurable improvements in detecting clothing items.\n",
2075
+
"This notebook demonstrated the fine-tuning of Paligemma on a fashion dataset for object detection. While the complete dataset of 4.5k images could not be utilized due to resource constraints, a subset of 640 images was used, which resulted in measurable improvements in detecting clothing items.\n",
2062
2076
"\n",
2063
2077
"Model was fine-tuned for 80 steps on T4 GPUs;\n",
0 commit comments