Spaces:
Runtime error
Runtime error
Usando from_pretrained_fastai para carga limpia
Browse files
app.py
CHANGED
|
@@ -3,7 +3,6 @@ import gradio as gr
|
|
| 3 |
import torch
|
| 4 |
import timm
|
| 5 |
from PIL import Image
|
| 6 |
-
from torchvision import transforms
|
| 7 |
from fastai.vision.all import *
|
| 8 |
|
| 9 |
# 1. Categorías (Asegúrate de que el orden sea el mismo que dls.vocab en Colab)
|
|
@@ -12,16 +11,15 @@ categories = ['Bug', 'Dark', 'Dragon', 'Electric', 'Fairy', 'Fighting',
|
|
| 12 |
'Normal', 'Poison', 'Psychic', 'Rock', 'Steel', 'Water']
|
| 13 |
|
| 14 |
def load_model_fastai_style(weights_path):
|
| 15 |
-
#
|
| 16 |
-
# Esto es universal y no depende de métodos de clase que cambian
|
| 17 |
empty_ds = Datasets([None], [[]])
|
| 18 |
dls = DataLoaders.from_dsets(empty_ds, empty_ds, path='.', bs=1, device='cpu')
|
| 19 |
dls.vocab = categories
|
| 20 |
|
| 21 |
-
#
|
| 22 |
-
learn = vision_learner(dls, 'convnext_tiny', pretrained=False)
|
| 23 |
|
| 24 |
-
# Cargar pesos
|
| 25 |
state = torch.load(weights_path, map_location='cpu', weights_only=False)
|
| 26 |
if isinstance(state, dict) and 'model' in state:
|
| 27 |
learn.model.load_state_dict(state['model'])
|
|
@@ -31,19 +29,12 @@ def load_model_fastai_style(weights_path):
|
|
| 31 |
learn.model.eval()
|
| 32 |
return learn
|
| 33 |
|
| 34 |
-
#
|
| 35 |
learn = load_model_fastai_style('checkpoint_1.pth')
|
| 36 |
|
| 37 |
def predict(img):
|
| 38 |
-
|
| 39 |
-
img = PILImage.create(img)
|
| 40 |
-
# 2. Resize manual al tamaño de entrenamiento
|
| 41 |
-
img = img.resize((126, 126))
|
| 42 |
-
|
| 43 |
-
# 3. Predicción
|
| 44 |
-
# El método predict gestiona internamente la normalización que el modelo espera
|
| 45 |
pred, pred_idx, probs = learn.predict(img)
|
| 46 |
-
|
| 47 |
return {categories[i]: float(probs[i]) for i in range(len(categories))}
|
| 48 |
|
| 49 |
# Interfaz
|
|
|
|
| 3 |
import torch
|
| 4 |
import timm
|
| 5 |
from PIL import Image
|
|
|
|
| 6 |
from fastai.vision.all import *
|
| 7 |
|
| 8 |
# 1. Categorías (Asegúrate de que el orden sea el mismo que dls.vocab en Colab)
|
|
|
|
| 11 |
'Normal', 'Poison', 'Psychic', 'Rock', 'Steel', 'Water']
|
| 12 |
|
| 13 |
def load_model_fastai_style(weights_path):
|
| 14 |
+
# Creamos dls mínimos
|
|
|
|
| 15 |
empty_ds = Datasets([None], [[]])
|
| 16 |
dls = DataLoaders.from_dsets(empty_ds, empty_ds, path='.', bs=1, device='cpu')
|
| 17 |
dls.vocab = categories
|
| 18 |
|
| 19 |
+
# Especificamos loss_func explícitamente para evitar el AssertionError
|
| 20 |
+
learn = vision_learner(dls, 'convnext_tiny', pretrained=False, loss_func=CrossEntropyLossFlat())
|
| 21 |
|
| 22 |
+
# Cargar pesos
|
| 23 |
state = torch.load(weights_path, map_location='cpu', weights_only=False)
|
| 24 |
if isinstance(state, dict) and 'model' in state:
|
| 25 |
learn.model.load_state_dict(state['model'])
|
|
|
|
| 29 |
learn.model.eval()
|
| 30 |
return learn
|
| 31 |
|
| 32 |
+
# Carga
|
| 33 |
learn = load_model_fastai_style('checkpoint_1.pth')
|
| 34 |
|
| 35 |
def predict(img):
|
| 36 |
+
img = PILImage.create(img).resize((126, 126))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
pred, pred_idx, probs = learn.predict(img)
|
|
|
|
| 38 |
return {categories[i]: float(probs[i]) for i in range(len(categories))}
|
| 39 |
|
| 40 |
# Interfaz
|