test wood furnishing

20230321_wood_furnishes_34_10ep_22er_good.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63c5356cde93f474f12204c25ce071dcc0f12f318f6ce1273e0087ace064a0fd
+size 88249899

app.py

@@ -7,18 +7,18 @@ import numpy as np
 
 def is_cat(x): return x[0].isupper()
 
-learn = load_learner('styles_20230420_new_datasets_34.pkl')
+learn = load_learner('20230321_wood_furnishes_34_10ep_22er_good.pkl')
 
 #categories = ('cool-colors', 'earth-tones', 'jewel', 'neutral-colors', 'pastel', 'warm-colors')
 
-categories = ('classic', 'coastal', 'contemporary', 'industrial', 'midcentury', 'pacific-northwest', 'shabby chic')
+categories = ('blackstain', 'brass', 'brushednickel', 'chinoiserie', 'chrome', 'copper', 'darkwood', 'glass', 'goldleaf', 'lightwood', 'marble', 'oiledbronze', 'rattan', 'silverleaf', 'stainlesssteel')
 def classify_image(img):
     pred, idx, probs = learn.predict(img)
     return dict(zip(categories, map(float, probs)))
 
 image = gr.inputs.Image(shape=(192,192))
 label = gr.outputs.Label()
-examples = ['armchair.png', 'bean-bag.png', 'puf.png']
+examples = ['glass.webp', 'goldleaf.jpeg', 'lightwood.webp', 'oiledbronze.jpeg']
 
 intf = gr.Interface(fn=classify_image, inputs=image, outputs=label, examples=examples)