国内那些免费的CPU训练平台都是挂羊头卖狗肉 - 查问我看

原国内那些免费的CPU训练平台都是挂羊头卖狗肉

PHPer 2025-09-03 72 0 0

配置听着高的吓人，用测试用的训练代码一测试，数据低的离谱

# train_simple.py
$ .....
# 训练的代码
# 优化器（后面会重建）
optimizer = None

# -----------------------------
# 3. 阶段1：CPU 训练
# -----------------------------
print("? 开始 CPU 训练...")
cpu_start_time = time.time()

# 使用 CPU
model_cpu = UNet2DModel(
    sample_size=32,
    in_channels=3,
    out_channels=3,
    layers_per_block=1,
    block_out_channels=(32, 64),
    down_block_types=("DownBlock2D", "AttnDownBlock2D"),
    up_block_types=("UpBlock2D", "AttnUpBlock2D"),
)
model_cpu.train()
model_cpu = model_cpu.to("cpu")

optimizer = torch.optim.Adam(model_cpu.parameters(), lr=1e-3)
n_steps = 10

for step in range(n_steps):
    optimizer.zero_grad()
    output = model_cpu(x_cpu, timesteps_cpu).sample
    loss = torch.nn.functional.mse_loss(output, y_cpu)
    loss.backward()
    optimizer.step()
    print(f"Step {step+1:2d} | Device: CPU | Loss: {loss.item():.6f}")

cpu_end_time = time.time()
cpu_elapsed = cpu_end_time - cpu_start_time
print(f"⏱️  CPU 训练耗时: {cpu_elapsed:.2f} 秒")

# -----------------------------
# 4. 阶段2：GPU 训练（如果可用）
# -----------------------------
gpu_elapsed = 0.0
if torch.cuda.is_available():
    print("? 开始 GPU 训练...")
    gpu_start_time = time.time()

    model_gpu = UNet2DModel(
        sample_size=32,
        in_channels=3,
        out_channels=3,
        layers_per_block=1,
        block_out_channels=(32, 64),
        down_block_types=("DownBlock2D", "AttnDownBlock2D"),
        up_block_types=("UpBlock2D", "AttnUpBlock2D"),
    )
    model_gpu.train()
    device = torch.device("cuda")
    model_gpu = model_gpu.to(device)

    x_gpu = x_cpu.to(device)
    y_gpu = y_cpu.to(device)
    timesteps_gpu = timesteps_cpu.to(device)
    optimizer = torch.optim.Adam(model_gpu.parameters(), lr=1e-3)

    for step in range(n_steps):
        optimizer.zero_grad()
        output = model_gpu(x_gpu, timesteps_gpu).sample
        loss = torch.nn.functional.mse_loss(output, y_gpu)
        loss.backward()
        optimizer.step()
        print(f"Step {step+1:2d} | Device: GPU | Loss: {loss.item():.6f}")

    gpu_end_time = time.time()
    gpu_elapsed = gpu_end_time - gpu_start_time
    print(f"⏱️  GPU 训练耗时: {gpu_elapsed:.2f} 秒")
else:
    print("⚠️  GPU 不可用，跳过 GPU 训练阶段")
# .......

20250903 1357 ...