Hello,
I’ve made the FastAI’s Cat vs Dog model into model that distinguishes lemons from limes and it all works fine in a notebook.
I am now looking to transform this model into Core ML for my iOS app using TorchScript and Apple official guidelines for coremltools.
Model converts but I cannot see the Preview Tab in. Xcode. Have anyone of you tried to convert to Core ML? I guess my input types are not matching with coremltools expectations for preview . I made a model with review the does not fetch the results since the fastAI output is tensor and Core ML expects Dictionary, String . How to convert this properly ?
import torch
import coremltools as ct
from fastai.vision.all import *
import json
from torchvision import transforms
# Load your Fastai model (replace with your actual path)
learn = load_learner('lemonmodel.pkl')
# Example input image (you can use any image from your dataset)
input_image = PILImage.create('example.jpg')
# Preprocess the image (assuming you used these transforms during training)
to_tensor = transforms.ToTensor()
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
input_tensor = to_tensor(input_image)
input_tensor = normalize(input_tensor) # Apply normalization
# Add a batch dimension
input_tensor = input_tensor.unsqueeze(0)
# Ensure float32 type
input_tensor = input_tensor.float()
# Trace the model
trace = torch.jit.trace(learn.model, input_tensor)
# Define the Core ML input type (considering your model's input shape)
_input = ct.ImageType(
name="input_1",
shape=input_tensor.shape,
bias=[-0.485/0.229, -0.456/0.224, -0.406/0.225],
scale=1./(255*0.226)
)
# Convert the model to Core ML format
mlmodel = ct.convert(
trace,
inputs=[_input],
minimum_deployment_target=ct.target.iOS14 # Optional, set deployment target
)
# Set model type as 'imageClassifier' for the Preview tab
mlmodel.type = 'imageClassifier'
# Correct structure for preview parameters** (assuming two classes: 'lemon' and 'lime')
labels_json = {
"imageClassifier": {
"labels": ["lemon", "lime"],
"input": {
"shape": list(input_tensor.shape), # Provide the actual input shape
"mean": [0.485, 0.456, 0.406], # Match normalization mean
"std": [0.229, 0.224, 0.225] # Match normalization std
},
"output": {
"shape": [1, 2] # Output shape for your model (2 classes)
}
}
}
# Setting up the metadata with correct 'preview' params
mlmodel.user_defined_metadata['com.apple.coreml.model.preview.params'] = json.dumps(labels_json)
# Save the model as .mlmodel
mlmodel.save("LemonClassifierGemini.mlmodel")
mlmodel = ct.convert(
trace,
inputs=[_input],
minimum_deployment_target=ct.target.iOS14 # Optional, set deployment target
)
# Set model type as 'imageClassifier' for the Preview tab**
mlmodel.type = 'imageClassifier'
# Correct structure for preview parameters** (assuming two classes: 'lemon' and 'lime')
labels_json = {
"imageClassifier": {
"labels": ["lemon", "lime"],
"input": {
"shape": list(input_tensor.shape), # Provide the actual input shape
"mean": [0.485, 0.456, 0.406], # Match normalization mean
"std": [0.229, 0.224, 0.225] # Match normalization std
},
"output": {
"shape": [1, 2] # Output shape for your model (2 classes)
}
}
}
# Setting up the metadata with correct 'preview' params**
mlmodel.user_defined_metadata['com.apple.coreml.model.preview.params'] = json.dumps(labels_json)
# Save the model as .mlmodel
mlmodel.save("LemonClassifierGemini.mlmodel")
My model is :
Input batch shape: torch.Size([32, 3, 192, 192]) Labels batch shape: torch.Size([32])
Validation Loss: None, Validation Metric: None
Predictions shape: torch.Size([63, 2]) Targets shape: torch.Size([63])
Code for the model :
searches = 'lemon','lime'
path = Path('lemon_or_not')
for o in searches:
dest = (path/o)
dest.mkdir(exist_ok=True, parents=True)
download_images(dest, urls=search_images(f'{o} photo'))
time.sleep(5)
resize_images(path/o, max_size=400, dest=path/o)
dls = DataBlock(
blocks=(ImageBlock, CategoryBlock),
get_items=get_image_files,
splitter=RandomSplitter(valid_pct=0.2, seed=42),
get_y=parent_label,
item_tfms=[Resize(192, method='squish')]
).dataloaders(path, bs=32)
dls.show_batch(max_n=6)
learn = vision_learner(dls, resnet18, metrics=error_rate)
learn.fine_tune(3)
is_lemon,_,probs = learn.predict(PILImage.create('lemon.jpg'))
print(f"This is a: {is_lemon}.")
print(f"Probability it's a lemon: {probs[0]:.4f}")
This is a: lemon. Probability it’s a lemon: 1.0000
learn.export(‘lemonmodel.pkl’)
I was stuck to why it doest show the Preview Tab.
I was able to get the results with this code and with preview working but:
in preview it says “unable to retrieve results from the vision request”.
import torch
import coremltools as ct
from fastai.vision.all import *
import json
from PIL import Image
from torchvision import transforms
# Load your Fastai model (replace with your actual path)
learn = load_learner('lemonmodel.pkl')
# Set the model to eval mode before tracing
learn.model.eval()
# Example input image (you can use any image from your dataset)
input_image = PILImage.create('example.jpg')
# Preprocess the image (assuming you used these transforms during training)
resize = transforms.Resize((192, 192)) # Resize image to match model input size (e.g., 192x192)
to_tensor = transforms.ToTensor()
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
# Apply preprocessing: Resize, Convert to tensor, Normalize
input_image = resize(input_image) # Resize to expected size
input_tensor = to_tensor(input_image) # Convert to tensor
input_tensor = normalize(input_tensor) # Normalize with mean and std
# Add a batch dimension
input_tensor = input_tensor.unsqueeze(0)
# Ensure float32 type
input_tensor = input_tensor.float()
# Trace the model (using the batch-size of 1)
trace = torch.jit.trace(learn.model, input_tensor)
# Define the Core ML input type (image type with correct shape for Core ML)
_input = ct.ImageType(
name="input_1",
shape=(1, 3, 192, 192), # Correct shape for Core ML [batch_size, channels, height, width]
bias=[-0.485 / 0.229, -0.456 / 0.224, -0.406 / 0.225], # Mean normalization
scale=1.0 / 255 # Scale normalization
)
# Define the Core ML output type (we do NOT specify the shape, let Core ML infer it)
_output = ct.TensorType(
name="output_1", # Name for the output
)
# Convert the model to Core ML format
mlmodel = ct.convert(
trace,
inputs=[_input],
outputs=[_output], # Let Core ML infer the output shape
minimum_deployment_target=ct.target.iOS14 # iOS deployment target
)
# Set model type as 'imageClassifier' for the Preview tab
mlmodel.type = 'imageClassifier'
# Define labels for classification
labels_json = {
"labels": ["lemon", "lime"], # Replace with your actual class labels
}
# Setting up the metadata with correct 'preview' params
mlmodel.user_defined_metadata['com.apple.coreml.model.preview.params'] = json.dumps(labels_json)
# Set model metadata for Xcode integration
mlmodel.user_defined_metadata["com.apple.coreml.model.preview.type"] = "imageClassifier"
mlmodel.input_description["input_1"] = "Input image to be classified"
mlmodel.output_description["output_1"] = "Classification probabilities for each label"
# Set additional metadata for the Xcode UI (optional)
mlmodel.author = "Your Name or Organization"
mlmodel.short_description = "A classifier for detecting lemon and lime in images."
mlmodel.version = "1.0"
# Save the model as .mlmodel
mlmodel.save("LemonClassifier333.mlmodel"
