tlearner 0.1.5

A python library for neural network transfer learning.

About

We provide a set of transfer learning-based model training and evaluation functions. ImageNet pretrained weights are used.
The series of Efficient Net models are supported. There is always a trade-off between model size and accuracy. Our guideline is as follows:
For tfjs apps, use EfficientNetB0 or EfficientNetB1; For tf-lite apps, use EfficientNetB2 ~ B4; For desktop apps, use EfficientNetB5 and above.

The following table is from keras website:

Model	Size (MB)	Top-1 Accuracy	Top-5 Accuracy	Parameters	Depth	Time (ms) per inference step (CPU)	Time (ms) per inference step (GPU)
Xception	88	79.0%	94.5%	22.9M	81	109.4	8.1
VGG16	528	71.3%	90.1%	138.4M	16	69.5	4.2
VGG19	549	71.3%	90.0%	143.7M	19	84.8	4.4
ResNet50	98	74.9%	92.1%	25.6M	107	58.2	4.6
ResNet50V2	98	76.0%	93.0%	25.6M	103	45.6	4.4
ResNet101	171	76.4%	92.8%	44.7M	209	89.6	5.2
ResNet101V2	171	77.2%	93.8%	44.7M	205	72.7	5.4
ResNet152	232	76.6%	93.1%	60.4M	311	127.4	6.5
ResNet152V2	232	78.0%	94.2%	60.4M	307	107.5	6.6
InceptionV3	92	77.9%	93.7%	23.9M	189	42.2	6.9
InceptionResNetV2	215	80.3%	95.3%	55.9M	449	130.2	10.0
MobileNet	16	70.4%	89.5%	4.3M	55	22.6	3.4
MobileNetV2	14	71.3%	90.1%	3.5M	105	25.9	3.8
DenseNet121	33	75.0%	92.3%	8.1M	242	77.1	5.4
DenseNet169	57	76.2%	93.2%	14.3M	338	96.4	6.3
DenseNet201	80	77.3%	93.6%	20.2M	402	127.2	6.7
NASNetMobile	23	74.4%	91.9%	5.3M	389	27.0	6.7
NASNetLarge	343	82.5%	96.0%	88.9M	533	344.5	20.0
EfficientNetB0	29	77.1%	93.3%	5.3M	132	46.0	4.9
EfficientNetB1	31	79.1%	94.4%	7.9M	186	60.2	5.6
EfficientNetB2	36	80.1%	94.9%	9.2M	186	80.8	6.5
EfficientNetB3	48	81.6%	95.7%	12.3M	210	140.0	8.8
EfficientNetB4	75	82.9%	96.4%	19.5M	258	308.3	15.1
EfficientNetB5	118	83.6%	96.7%	30.6M	312	579.2	25.3
EfficientNetB6	166	84.0%	96.8%	43.3M	360	958.1	40.4
EfficientNetB7	256	84.3%	97.0%	66.7M	438	1578.9	61.6
EfficientNetV2B0	29	78.7%	94.3%	7.2M	-	-	-
EfficientNetV2B1	34	79.8%	95.0%	8.2M	-	-	-
EfficientNetV2B2	42	80.5%	95.1%	10.2M	-	-	-
EfficientNetV2B3	59	82.0%	95.8%	14.5M	-	-	-
EfficientNetV2S	88	83.9%	96.7%	21.6M	-	-	-
EfficientNetV2M	220	85.3%	97.4%	54.4M	-	-	-
EfficientNetV2L	479	85.7%	97.5%	119.0M	-	-	-

Install

pip install tensorflow-gpu >= 2
pip install tlearner

How to use

1. Initialize

   from tlearner.efficientnet import transfer_learner learner = transfer_learner("my_model", W = 224) # my_model.h5df will be the model name

2. Load data

   learner.load_dataset('my_data_folder', PKL_PATH = "my_dataset.pkl") # Images in each subfolder of my_data_folder are treated as one class. If PKL_PATH is specified, a pkl that contains X_train, y_train, X_val, y_val, etc. will be generated.
   print(learner.class_names) # print class names

3. Train a new model

   hist = learner.train_custom_model("EfficientNetB1", batch = 8, epochs = [10,0], optimizer = "adam") # EfficientNetB0-B7 can be used.
   plot_history(hist) # plot training curves

4. Evaluate

   learner.evaluate(N = 30) # predict the first N samples in X_val

5. Predict

   learner.predict_file('my_image.jpg')

6. Convert [Optional]

   learner.convert_to_tflite(v1 = True) # convert to a local tflite model

7. Load an existing model

   learner.load_best_model() # if you have an existing local model
   learner.get_best_model().summary() # print model architecture
   learner.plot_best_model() # save model architecture to a local image file

Jupyter notebooks

Under /notebooks, we provide two examples. One is flower image classification; the other is fundus image classification.

Deployment

After training, you will get a keras h5 model file. You can further convert it to tflite format, or tfjs format (efficient net is not supported yet).
Then you can deploy on mobile device or browser-based apps.