Merge branch 'feature/DDP_fixed' of https://github.com/MagicFrogSJTU/…

…yolov5 into feature/DDP_fixed

README.md

@@ -25,8 +25,8 @@ This repository represents Ultralytics open-source research into future object d
 
 
 ** AP<sup>test</sup> denotes COCO [test-dev2017](http://cocodataset.org/#upload) server results, all other AP results in the table denote val2017 accuracy.  
-** All AP numbers are for single-model single-scale without ensemble or test-time augmentation. Reproduce by `python test.py --data data/coco.yaml --img 736 --conf 0.001`  
-** Speed<sub>GPU</sub> measures end-to-end time per image averaged over 5000 COCO val2017 images using a GCP [n1-standard-16](https://cloud.google.com/compute/docs/machine-types#n1_standard_machine_types) instance with one V100 GPU, and includes image preprocessing, PyTorch FP16 image inference at --batch-size 32 --img-size 640, postprocessing and NMS. Average NMS time included in this chart is 1-2ms/img.  Reproduce by `python test.py --data data/coco.yaml --img 640 --conf 0.1`  
+** All AP numbers are for single-model single-scale without ensemble or test-time augmentation. Reproduce by `python test.py --data coco.yaml --img 736 --conf 0.001`  
+** Speed<sub>GPU</sub> measures end-to-end time per image averaged over 5000 COCO val2017 images using a GCP [n1-standard-16](https://cloud.google.com/compute/docs/machine-types#n1_standard_machine_types) instance with one V100 GPU, and includes image preprocessing, PyTorch FP16 image inference at --batch-size 32 --img-size 640, postprocessing and NMS. Average NMS time included in this chart is 1-2ms/img.  Reproduce by `python test.py --data coco.yaml --img 640 --conf 0.1`  
 ** All checkpoints are trained to 300 epochs with default settings and hyperparameters (no autoaugmentation). 
 
 
@@ -41,7 +41,7 @@ $ pip install -U -r requirements.txt
 ## Tutorials
 
 * [Notebook](https://github.com/ultralytics/yolov5/blob/master/tutorial.ipynb) <a href="https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
-* [Kaggle](https://www.kaggle.com/ultralytics/yolov5-tutorial)
+* [Kaggle](https://www.kaggle.com/ultralytics/yolov5)
 * [Train Custom Data](https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data)
 * [PyTorch Hub](https://github.com/ultralytics/yolov5/issues/36)
 * [ONNX and TorchScript Export](https://github.com/ultralytics/yolov5/issues/251)

requirements.txt

@@ -1,6 +1,6 @@
 # pip install -U -r requirements.txt
 Cython
-numpy==1.17
+numpy==1.17.3
 opencv-python
 torch>=1.5.1
 matplotlib

train.py

@@ -208,15 +208,15 @@ def train(hyp, tb_writer, opt, device):
     model.names = names
 
     # Class frequency
+    labels = np.concatenate(dataset.labels, 0)
+    c = torch.tensor(labels[:, 0])  # classes
+    # cf = torch.bincount(c.long(), minlength=nc) + 1.
+    # model._initialize_biases(cf.to(device))
+    plot_labels(labels, save_dir=log_dir)
     if tb_writer:
-        labels = np.concatenate(dataset.labels, 0)
-        c = torch.tensor(labels[:, 0])  # classes
-        # cf = torch.bincount(c.long(), minlength=nc) + 1.
-        # model._initialize_biases(cf.to(device))
-        plot_labels(labels)
+        tb_writer.add_hparams(hyp, {})
         tb_writer.add_histogram('classes', c, 0)
 
-
     # Check anchors
     if not opt.noautoanchor:
         check_anchors(dataset, model=model, thr=hyp['anchor_t'], imgsz=imgsz)

utils/datasets.py

@@ -59,7 +59,7 @@ def create_dataloader(path, imgsz, batch_size, stride, opt, hyp=None, augment=Fa
                                     pad=pad)
 
     batch_size = min(batch_size, len(dataset))
-    nw = min([os.cpu_count()//opt.world_size, batch_size if batch_size > 1 else 0, 8])  # number of workers
+    nw = min([os.cpu_count()//(opt.world_size if hasattr(opt, "world_size") else 1), batch_size if batch_size > 1 else 0, 8])  # number of workers
     train_sampler = torch.utils.data.distributed.DistributedSampler(dataset) if local_rank != -1 else None
     dataloader = torch.utils.data.DataLoader(dataset,
                                              batch_size=batch_size,