FixMatch-pytorch
FixMatch-pytorch copied to clipboard
Unofficial PyTorch implementation of "FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence"
I found that this is because the _model.train()_ did not open again when evaluation ends. solution: just move _mode.train()_ to the epoch loop: - model.train() for epoch in range(args.start_epoch, args.epochs):...
When using DistributedDataParallel, if N labeled training images and K GPUs are used, should we set num_labeled = N / K instead of N? since np.random.shuffle(idx) generate different idxs in...
Just wondering if it is necessary to use 4 GPUs to reproduce the reported the results? I have been struggling to get the same results with 1 GPU. Anyone succesfully...
When fix patch is applied to my dataset, the dataset is unbalanced. Why does the training set perform well, but the loss of verification set first decreases and then keeps...
Hi, thanks for your impressive work! It seems that we can get quite a lot better results with your implementation. Could you let me know what is the reason for...
If train the model with multiple GPU's the total batch size becomes bigger (batch_size_total = batch_size * num_gpus) but the number of eval_steps in one epoch stays equal. This causes...
Wonderful job! I want to know what role does do_interleave function do, is the performance dropping when removing it? logits = de_interleave(logits, 2*args.mu+1)
Hello, I am currently experimenting with the FixMatch algorithm with this repo, using smaller models (specifically ResNet34 and ResNet18) instead of the larger models (WideResNet and ResNeXt) mentioned in the...
每次加载训练好的模型,和训练的时候最好的结果对比,结果都不一样,怎么回事,加载的模型重新推理一遍,结果和训练的时候不同
C:\Users\15727\.conda\envs\pytorch\python.exe C:\Users\15727\Desktop\FixMatch-pytorch-master\train.py 03/08/2024 16:07:44 - WARNING - __main__ - Process rank: -1, device: cuda:0, n_gpu: 1, distributed training: False, 16-bits training: False 03/08/2024 16:07:44 - INFO - __main__ - {'gpu_id':...