Hy guys, I have different values in my code if I use mode.eval (That give the results almost right) instead of model.eval(). I am going to explain better.
I use my training set for testing and, cause I have a loss in training time of zero, I think that my net give me the same result of ground truth. But it doesn’t. and I note that if I use m model.eval() the results are very far from GT and if use model.eval the results are near the GT. I put my code here if I have made same mistake.
import dataset
import torch
import numpy as np
from torch.utils.data import DataLoader
from torchvision import transforms
import csv
import time
import pandas as pd
def get_test_batches():
transform = transforms.Compose([transforms.Resize(224),
transforms.ToTensor(), # conversione in tensore
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])
train = dataset.Dataset("./Dataset/immagini/", "./Dataset/train.csv", transform=transform)
# dataloader
test_loader = DataLoader(train, batch_size=1)
return test_loader
def predictions(model_reg, test_loader):
since = time.time()
print("---- START INFERENCE ----")
print
preds1 = []
preds2 = []
preds3 = []
preds4 = []
preds5 = []
imgs_name = [] #
columns=["ID1","PX", "PZ", "PU", "PV", "R"]
df = pd.DataFrame(columns=columns)
device = "cuda" if torch.cuda.is_available() else "cpu"
model_reg.to(device)
model_reg.eval. #WHY???
for batch in test_loader:
x = batch['image'].to(device)
state = batch['start']
imgs_name.append(state.item())
with torch.no_grad():
pred_reg = model_reg(x)
preds1.append(pred_reg[0][0].item())
preds2.append(pred_reg[0][1].item())
preds3.append(pred_reg[0][2].item())
preds4.append(pred_reg[0][3].item())
#print(imgs_name, preds1, preds2, preds3, preds4)
reward = test_loader.dataset.get_reward(state.item(), pred_reg[0][0],
pred_reg[0][1],
pred_reg[0][2],
pred_reg[0][3])
preds5.append(reward)
df["ID1"] = imgs_name
df["PX"] = preds1
df["PZ"] = preds2
df["PU"] = preds3
df["PV"] = preds4
df["R"] = preds5
df.to_csv("Predictions.csv", index=False)
time_elapsed = time.time() - since
print('---- INFERENCE COMPLETE in {:.0f}m {:.0f}s ----'.format(time_elapsed // 60, time_elapsed % 60))
and I call all in main loading my trained model:
resnet_reg_model = nets.resNet50_model(). #resnet with fine tuning
resnet_reg_model.load_state_dict(torch.load(“What’s the reward?.pth”, map_location=‘cpu’))
predictions(resnet_reg_model, get_test_batches())
