someshfengde · August 18, 2023 05:30
diff --git a/blog_10.py b/blog_10.py
 smooth_loss_function(out1, torch.tensor(400)), smooth_loss_function(out2, torch.tensor(420))
diff --git a/blog_11.py b/blog_11.py
 # Let's check what will happen to both the losses when the losses are increasing  
 # let's generate data for dummy predictions and actual values
 dummy_preds = torch.tensor(np.sort( np.random.uniform(0, 2, 100))).unsqueeze(1)
 dummy_actuals = torch.tensor(np.ones(100)).unsqueeze(1)
diff --git a/blog_12.py b/blog_12.py
 fig = px.line(y = [dummy_preds.squeeze(), dummy_actuals.squeeze()], title = 'Sample data for understanding')
 fig.data[0].name = "dummy predictions"
 fig.data[1].name = "dummy acutal values "
 fig.update_layout(legend_title_text="Legend")
 fig.show()
diff --git a/blog_13.py b/blog_13.py
 dummy_l1_loss = [loss_function(pred,act) for pred,act in zip(dummy_preds,dummy_actuals)]
 dummy_smooth_l1_loss = [smooth_loss_function(pred,act) for pred,act in zip(dummy_preds, dummy_actuals)]
diff --git a/blog_14.py b/blog_14.py
 fig = px.line(
    y=[dummy_l1_loss, dummy_smooth_l1_loss],
    title="Dummy values losses for L1 and smooth L1",
    labels={"y": "Loss", "x": "increasing losses"},
    color_discrete_sequence=["blue", "green"],  # Optional custom colors
 )
 fig.data[0].name = "L1 Loss Output"
 fig.data[1].name = "Smooth Loss Output"
 fig.update_layout(legend_title_text="Loss Type")
 fig.show()
diff --git a/blog_4.py b/blog_4.py
 px.line( loss_output, title = "L1 loss across 200 epochs")
diff --git a/blog_5.py b/blog_5.py
 out1 = model(torch.tensor([20]).to(torch.float32))
 out2 = model(torch.tensor([21]).to(torch.float32))

 out1, out2 
diff --git a/blog_6.py b/blog_6.py
 loss_function(out1, torch.tensor(400)), loss_function(out2, torch.tensor(420))
diff --git a/blog_7.py b/blog_7.py
 model_1 = LinearRegressor()
 smooth_loss_function = torch.nn.SmoothL1Loss()
 smooth_loss_output = train_model(model_1,smooth_loss_function)
diff --git a/blog_8.py b/blog_8.py
 fig = px.line(
    y=[loss_output, smooth_loss_output],
    title="Smooth_L1_loss across 200 epochs",
    labels={"y": "Loss", "x": "Epoch"},
    color_discrete_sequence=["blue", "green"],  # Optional custom colors
 )
 fig.data[0].name = "L1 Loss Output"
 fig.data[1].name = "Smooth Loss Output"
 fig.update_layout(legend_title_text="Loss Type")
 fig.show()
diff --git a/blog_9.py b/blog_9.py
 out1 = model_1(torch.tensor([20]).to(torch.float32))
 out2 = model_1(torch.tensor([21]).to(torch.float32))

 out1, out2
	# Let's check what will happen to both the losses when the losses are increasing
	# let's generate data for dummy predictions and actual values
	dummy_preds = torch.tensor(np.sort( np.random.uniform(0, 2, 100))).unsqueeze(1)
	dummy_actuals = torch.tensor(np.ones(100)).unsqueeze(1)
	fig = px.line(y = [dummy_preds.squeeze(), dummy_actuals.squeeze()], title = 'Sample data for understanding')
	fig.data[0].name = "dummy predictions"
	fig.data[1].name = "dummy acutal values "
	fig.update_layout(legend_title_text="Legend")
	fig.show()
	dummy_l1_loss = [loss_function(pred,act) for pred,act in zip(dummy_preds,dummy_actuals)]
	dummy_smooth_l1_loss = [smooth_loss_function(pred,act) for pred,act in zip(dummy_preds, dummy_actuals)]
	fig = px.line(
	y=[dummy_l1_loss, dummy_smooth_l1_loss],
	title="Dummy values losses for L1 and smooth L1",
	labels={"y": "Loss", "x": "increasing losses"},
	color_discrete_sequence=["blue", "green"], # Optional custom colors
	)
	fig.data[0].name = "L1 Loss Output"
	fig.data[1].name = "Smooth Loss Output"
	fig.update_layout(legend_title_text="Loss Type")
	fig.show()
	out1 = model(torch.tensor([20]).to(torch.float32))
	out2 = model(torch.tensor([21]).to(torch.float32))

	out1, out2
	model_1 = LinearRegressor()
	smooth_loss_function = torch.nn.SmoothL1Loss()
	smooth_loss_output = train_model(model_1,smooth_loss_function)
	fig = px.line(
	y=[loss_output, smooth_loss_output],
	title="Smooth_L1_loss across 200 epochs",
	labels={"y": "Loss", "x": "Epoch"},
	color_discrete_sequence=["blue", "green"], # Optional custom colors
	)
	fig.data[0].name = "L1 Loss Output"
	fig.data[1].name = "Smooth Loss Output"
	fig.update_layout(legend_title_text="Loss Type")
	fig.show()
	out1 = model_1(torch.tensor([20]).to(torch.float32))
	out2 = model_1(torch.tensor([21]).to(torch.float32))

	out1, out2