Codebase release

Author: abdur75648

.DS_Store

@@ -29,14 +29,56 @@ Our model was rigorously validated on the public CAMUS and EchoNet-Dynamic datas
 
 ---
 
-## 📦 Code Availability
-
-> 🚧 Code coming soon...
-
-We are currently in the process of cleaning up and preparing the codebase and model weights for public release. We aim to make them available in this repository to facilitate further research and reproducibility. Please stay tuned for updates!
+## ⚙️ Setup & Installation
+
+1.  **Clone the repository:**
+    ```bash
+    git clone https://github.com/abdur75648/Echo-DND.git
+    cd Echo-DND
+    ```
+
+2.  **Install Dependencies:**
+    ```bash
+    pip install -r requirements.txt
+    ```
+
+3. **Prepare the Dataset:**
+   - Download the CAMUS and EchoNet-Dynamic datasets.
+   - Organize them into a root data directory with the following structure:
+     ```
+     <your_data_root_dir>/
+     ├── CAMUS/
+     │   ├── patient0001/
+     │   │   ├── patient0001_4CH_ED.mhd
+     │   │   ├── patient0001_4CH_ED_gt.mhd
+     │   │   └── ... (other patient files)
+     │   └── ... (other patient folders)
+     └── EchoNet-Dynamic/
+         ├── Train/
+         │   ├── Frames/
+         │   │   └── 0X100037609D9A4939_image0001.png
+         │   └── Masks/
+         │       └── 0X100037609D9A4939_image0001.png (corresponding mask)
+         ├── Val/
+             └── ...
+     ```
+   - The `echo_dnd_dataset.py` script is configured to load data assuming this structure.
 
 ---
 
+## 🏃‍♂️ Training & Inference
+### Training
+To train the Echo-DND model, run the following command:
+```bash
+python training_echo_dnd.py --data_dir /path/to/your_data_root_dir --batch_size 4 --lr 1e-4 --out_dir ./results/training_run1
+```
+
+### Inference
+To perform inference on a single image, use the following command:
+```bash
+python inference_echo_dnd.py --image_path /path/to/your/test_image.png --model_path /path/to/your/pretrained_echodnd_model.pt --out_dir ./results/inference_output
+```
+
 ## 📄 Citation
 
 If you find this work useful, please consider citing:

README.md

@@ -0,0 +1,87 @@
+"""
+Helpers for distributed training.
+"""
+
+import io
+import os
+import socket
+
+import blobfile as bf
+#from mpi4py import MPI
+import torch as th
+import torch.distributed as dist
+
+# Change this to reflect your cluster layout.
+# The GPU for a given rank is (rank % GPUS_PER_NODE).
+GPUS_PER_NODE = 8
+
+SETUP_RETRY_COUNT = 3
+
+
+def setup_dist(args):
+    """
+    Setup a distributed process group.
+    """
+    if dist.is_initialized():
+        return
+    if not args.multi_gpu:
+        os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu_dev
+
+    backend = "gloo" if not th.cuda.is_available() else "nccl"
+
+    if backend == "gloo":
+        hostname = "localhost"
+    else:
+        hostname = socket.gethostbyname(socket.getfqdn())
+    os.environ["MASTER_ADDR"] = '127.0.1.1'#comm.bcast(hostname, root=0)
+    os.environ["RANK"] = '0'#str(comm.rank)
+    os.environ["WORLD_SIZE"] = '1'#str(comm.size)
+
+    s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+    s.bind(("", 0))
+    s.listen(1)
+    port = s.getsockname()[1]
+    s.close()
+    os.environ["MASTER_PORT"] = str(port)
+    dist.init_process_group(backend=backend, init_method="env://")
+
+def dev():
+    """
+    Get the device to use for torch.distributed.
+    """
+    if th.cuda.is_available():
+        return th.device(f"cuda")
+    return th.device("cpu")
+
+
+def load_state_dict(path, **kwargs):
+    """
+    Load a PyTorch file without redundant fetches across MPI ranks.
+    """
+    mpigetrank=0
+    if mpigetrank==0:
+        with bf.BlobFile(path, "rb") as f:
+            data = f.read()
+    else:
+        data = None
+    
+    return th.load(io.BytesIO(data), **kwargs)
+
+
+def sync_params(params):
+    """
+    Synchronize a sequence of Tensors across ranks from rank 0.
+    """
+    for p in params:
+        with th.no_grad():
+            dist.broadcast(p, 0)
+
+
+def _find_free_port():
+    try:
+        s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+        s.bind(("", 0))
+        s.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
+        return s.getsockname()[1]
+    finally:
+        s.close()