notkshitij/CropCompass
1
1
Fork 0
Code Issues 8 Pull Requests Projects 1 Releases Activity

test2, i.e. vishnu is the chosen model. Shall be using that going forward. Perfectly working right now. Will be attempting to locally reference it now.

Browse Source
This commit is contained in:
K
2025-02-22 22:41:43 +05:30
parent f43890faab
commit c254f356bf
1 changed files with 5 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
models/test2.py
+5 -4
View File
@@ -1,3 +1,4 @@
# Import libraries
from PIL import Image, UnidentifiedImageError from PIL import Image, UnidentifiedImageError
from transformers import ViTImageProcessor, ViTForImageClassification from transformers import ViTImageProcessor, ViTForImageClassification
@@ -9,11 +10,11 @@ model = ViTForImageClassification.from_pretrained(
ignore_mismatched_sizes=True ignore_mismatched_sizes=True
) )
# Load your image # Load image
try: try:
image = Image.open('/home/overnion/Status200/potato.png') # Replace with the actual path to your image image = Image.open('/home/overnion/Status200/tomato.png')
# Convert the image to RGB if it's not already # Convert the image to RGB if it's not already
if image.mode != 'RGB': if (image.mode != 'RGB'):
image = image.convert('RGB') image = image.convert('RGB')
except FileNotFoundError: except FileNotFoundError:
print("Error: Image file not found.") print("Error: Image file not found.")
@@ -25,7 +26,7 @@ except Exception as e:
print(f"An error occurred: {e}") print(f"An error occurred: {e}")
exit() exit()
# Prepare the image for the model # Preparing the image for the model
inputs = image_processor(images=image, return_tensors="pt") inputs = image_processor(images=image, return_tensors="pt")
# Make the prediction # Make the prediction