notha99y/unet

Semantic Segmentation using U-Net

Hi there, I'm Ren Jie 👋

• 🇸🇬 I’m currently working as a Data Scientist in Singapore
• 📚 I've graduated with MTech (Knowledge Engineering) and BSc (Physics) from NUS
• 🌱 I’m currently learning Swift.
• ⚡ In my free time I love to play tennis 🎾

Connect with me:

Languages and Tools:

📕 Latest Blog Posts

• Breaking Down Mean Average Precision (mAP)
• A Starter Pack to Exploratory Data Analysis with Python, pandas, seaborn, and scikit-learn
• How I improved a Human Action Classifier to 80% Validation Accuracy in 6 Easy Steps

unet's Issues

TypeError: src data type = 17 when run train_unet.py

raceback (most recent call last):
File "C:/Users/path/U_Net/src/train_unet.py", line 127, in
image_path, mask_path, verbose=False, plot=False)
File "C:\Users\path\U_Net\src\utils.py", line 65, in resizing
images.append(cv2.resize(img_temp, (320, 240)))
TypeError: src data type = 17 is not supported

layers and surfaces labels

I read the code completely but I did not understand how layers and surfaces labels were used?
I want to use this code for my own application. I don't know how to create these 2 labels. If I have just regions labels does it work?
Thanks

loss calculation problem

after 5 epoch when i ran load_weights_and_test.py
this error occured

Traceback (most recent call last):
File "src/load_weights_and_test.py", line 144, in
loss = weights_names[0].split(".")[1].split("-")[1] + "." + weights_names[0].split(".")[2]
IndexError: list index out of range

how to solve it
thank you

conda env create -f=environment.yml

conda env create -f=environment.yml
Collecting package metadata (repodata.json): failed

CondaHTTPError: HTTP 429 TOO MANY REQUESTS for url https://mirrors.ustc.edu.cn/anaconda/pkgs/main/linux-64/repodata.json
Elapsed: 00:26.243557

An HTTP error occurred when trying to retrieve this URL.
HTTP errors are often intermittent, and a simple retry will get you on your way.
'https//mirrors.ustc.edu.cn/anaconda/pkgs/main/linux-64'